@giljae/opencode-pstack 0.0.0-stage → 0.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (551) hide show
  1. package/LICENSE +201 -0
  2. package/NOTICE +10 -0
  3. package/README.md +176 -2
  4. package/package.json +42 -4
  5. package/src/agents.ts +110 -0
  6. package/src/commands.ts +37 -0
  7. package/src/content.ts +119 -0
  8. package/src/host.ts +59 -0
  9. package/src/index.ts +21 -0
  10. package/src/install.ts +22 -0
  11. package/src/models.ts +112 -0
  12. package/src/pstack-setup.ts +111 -0
  13. package/src/setup.ts +42 -0
  14. package/src/skills.ts +24 -0
  15. package/vendor/pstack/LICENSE.upstream +21 -0
  16. package/vendor/pstack/README.upstream.md +290 -0
  17. package/vendor/pstack/UPSTREAM.json +545 -0
  18. package/vendor/pstack/agents/comment-sicko.md +32 -0
  19. package/vendor/pstack/agents/poteto-agent.md +10 -0
  20. package/vendor/pstack/docs/guide/01-setup.md +66 -0
  21. package/vendor/pstack/docs/guide/02-poteto-mode.md +139 -0
  22. package/vendor/pstack/docs/guide/03-understand.md +79 -0
  23. package/vendor/pstack/docs/guide/04-design.md +127 -0
  24. package/vendor/pstack/docs/guide/05-build-and-clean.md +83 -0
  25. package/vendor/pstack/docs/guide/06-verify-and-ship.md +162 -0
  26. package/vendor/pstack/docs/guide/07-overnight.md +122 -0
  27. package/vendor/pstack/docs/guide/08-principles.md +72 -0
  28. package/vendor/pstack/docs/guide/09-make-it-yours.md +100 -0
  29. package/vendor/pstack/docs/guide/10-recipes-and-pitfalls.md +182 -0
  30. package/vendor/pstack/docs/guide/README.md +38 -0
  31. package/vendor/pstack/docs/guide/images/design.jpg +0 -0
  32. package/vendor/pstack/docs/guide/images/overnight.jpg +0 -0
  33. package/vendor/pstack/docs/guide/images/recipes.jpg +0 -0
  34. package/vendor/pstack/docs/guide/images/router.jpg +0 -0
  35. package/vendor/pstack/docs/guide/images/understanding.jpg +0 -0
  36. package/vendor/pstack/docs/guide/images/verification.jpg +0 -0
  37. package/vendor/pstack/docs/harness/claude-code.md +68 -0
  38. package/vendor/pstack/skills/architect/SKILL.md +11 -0
  39. package/vendor/pstack/skills/arena/SKILL.md +48 -0
  40. package/vendor/pstack/skills/automate-me/SKILL.md +104 -0
  41. package/vendor/pstack/skills/benchmark-checklist/SKILL.md +39 -0
  42. package/vendor/pstack/skills/blast-radius/SKILL.md +50 -0
  43. package/vendor/pstack/skills/bro/SKILL.md +7 -0
  44. package/vendor/pstack/skills/correct/SKILL.md +32 -0
  45. package/vendor/pstack/skills/create-formal-verification-skill/SKILL.md +43 -0
  46. package/vendor/pstack/skills/create-verification-skill/SKILL.md +44 -0
  47. package/vendor/pstack/skills/create-verification-skill/references/feature-map-example/README.md +47 -0
  48. package/vendor/pstack/skills/create-verification-skill/references/feature-map-example/create-note.md +39 -0
  49. package/vendor/pstack/skills/create-verification-skill/references/feature-map-example/search.md +45 -0
  50. package/vendor/pstack/skills/figure-it-out/SKILL.md +52 -0
  51. package/vendor/pstack/skills/how/SKILL.md +21 -0
  52. package/vendor/pstack/skills/in-your-own-words/SKILL.md +7 -0
  53. package/vendor/pstack/skills/interrogate/SKILL.md +31 -0
  54. package/vendor/pstack/skills/ketchup/SKILL.md +43 -0
  55. package/vendor/pstack/skills/ketchup-video/SKILL.md +29 -0
  56. package/vendor/pstack/skills/maintain-formal-verification-skill/SKILL.md +58 -0
  57. package/vendor/pstack/skills/maintain-verification-skill/SKILL.md +39 -0
  58. package/vendor/pstack/skills/make-bot-ui/SKILL.md +115 -0
  59. package/vendor/pstack/skills/no-comments/SKILL.md +24 -0
  60. package/vendor/pstack/skills/poteto-help/SKILL.md +162 -0
  61. package/vendor/pstack/skills/poteto-help/references/prompting.md +51 -0
  62. package/vendor/pstack/skills/poteto-help/references/recipes.md +51 -0
  63. package/vendor/pstack/skills/poteto-mode/SKILL.md +110 -0
  64. package/vendor/pstack/skills/poteto-mode/playbooks/authoring-a-skill.md +12 -0
  65. package/vendor/pstack/skills/poteto-mode/playbooks/autonomous-run.md +13 -0
  66. package/vendor/pstack/skills/poteto-mode/playbooks/autopilot-full.md +25 -0
  67. package/vendor/pstack/skills/poteto-mode/playbooks/autopilot-stack.md +8 -0
  68. package/vendor/pstack/skills/poteto-mode/playbooks/babysit.md +10 -0
  69. package/vendor/pstack/skills/poteto-mode/playbooks/bug-fix.md +15 -0
  70. package/vendor/pstack/skills/poteto-mode/playbooks/eval.md +25 -0
  71. package/vendor/pstack/skills/poteto-mode/playbooks/feature.md +21 -0
  72. package/vendor/pstack/skills/poteto-mode/playbooks/hillclimb.md +21 -0
  73. package/vendor/pstack/skills/poteto-mode/playbooks/investigation.md +14 -0
  74. package/vendor/pstack/skills/poteto-mode/playbooks/multi-phase-plan.md +11 -0
  75. package/vendor/pstack/skills/poteto-mode/playbooks/opening-a-pr.md +9 -0
  76. package/vendor/pstack/skills/poteto-mode/playbooks/pause-safely.md +10 -0
  77. package/vendor/pstack/skills/poteto-mode/playbooks/perf-issue.md +25 -0
  78. package/vendor/pstack/skills/poteto-mode/playbooks/prototype.md +14 -0
  79. package/vendor/pstack/skills/poteto-mode/playbooks/refactoring.md +16 -0
  80. package/vendor/pstack/skills/poteto-mode/playbooks/runtime-forensics.md +11 -0
  81. package/vendor/pstack/skills/poteto-mode/playbooks/session-pickup.md +11 -0
  82. package/vendor/pstack/skills/poteto-mode/playbooks/shipping.md +12 -0
  83. package/vendor/pstack/skills/poteto-mode/playbooks/trace-forensics.md +14 -0
  84. package/vendor/pstack/skills/poteto-mode/playbooks/visual-parity.md +11 -0
  85. package/vendor/pstack/skills/poteto-mode/playbooks/worktree-cleanup.md +12 -0
  86. package/vendor/pstack/skills/poteto-mode/references/bugbot-triage.md +142 -0
  87. package/vendor/pstack/skills/poteto-mode/scripts/bootstrap.ts +62 -0
  88. package/vendor/pstack/skills/poteto-mode/scripts/bun.lock +67 -0
  89. package/vendor/pstack/skills/poteto-mode/scripts/package.json +16 -0
  90. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/cli.test.ts +224 -0
  91. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/cli.ts +223 -0
  92. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/fakes.test-helper.ts +129 -0
  93. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/github.test.ts +498 -0
  94. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/github.ts +726 -0
  95. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/policy.test.ts +482 -0
  96. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/policy.ts +842 -0
  97. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/render.ts +169 -0
  98. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/tsconfig.json +13 -0
  99. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/types.compile.ts +93 -0
  100. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/types.ts +414 -0
  101. package/vendor/pstack/skills/poteto-mode/scripts/watch-pr/watch-pr +6 -0
  102. package/vendor/pstack/skills/poteto-mode/scripts/worktree-audit.sh +134 -0
  103. package/vendor/pstack/skills/poteto-mode/worker.md +11 -0
  104. package/vendor/pstack/skills/principle-attack-the-premise/SKILL.md +15 -0
  105. package/vendor/pstack/skills/principle-boundary-discipline/SKILL.md +11 -0
  106. package/vendor/pstack/skills/principle-build-the-lever/SKILL.md +14 -0
  107. package/vendor/pstack/skills/principle-encode-lessons-in-structure/SKILL.md +11 -0
  108. package/vendor/pstack/skills/principle-exhaust-the-design-space/SKILL.md +9 -0
  109. package/vendor/pstack/skills/principle-experience-first/SKILL.md +19 -0
  110. package/vendor/pstack/skills/principle-explain-the-number/SKILL.md +14 -0
  111. package/vendor/pstack/skills/principle-fix-root-causes/SKILL.md +14 -0
  112. package/vendor/pstack/skills/principle-foundational-thinking/SKILL.md +13 -0
  113. package/vendor/pstack/skills/principle-guard-the-context-window/SKILL.md +12 -0
  114. package/vendor/pstack/skills/principle-laziness-protocol/SKILL.md +10 -0
  115. package/vendor/pstack/skills/principle-make-operations-idempotent/SKILL.md +15 -0
  116. package/vendor/pstack/skills/principle-migrate-callers-then-delete-legacy-apis/SKILL.md +14 -0
  117. package/vendor/pstack/skills/principle-minimize-reader-load/SKILL.md +15 -0
  118. package/vendor/pstack/skills/principle-model-the-domain/SKILL.md +15 -0
  119. package/vendor/pstack/skills/principle-never-block-on-the-human/SKILL.md +15 -0
  120. package/vendor/pstack/skills/principle-outcome-oriented-execution/SKILL.md +21 -0
  121. package/vendor/pstack/skills/principle-prove-it-works/SKILL.md +11 -0
  122. package/vendor/pstack/skills/principle-redesign-from-first-principles/SKILL.md +16 -0
  123. package/vendor/pstack/skills/principle-separate-before-serializing-shared-state/SKILL.md +11 -0
  124. package/vendor/pstack/skills/principle-sequence-verifiable-units/SKILL.md +13 -0
  125. package/vendor/pstack/skills/principle-subtract-before-you-add/SKILL.md +18 -0
  126. package/vendor/pstack/skills/principle-test-behavior-not-implementation/SKILL.md +16 -0
  127. package/vendor/pstack/skills/principle-type-system-discipline/SKILL.md +15 -0
  128. package/vendor/pstack/skills/recall/SKILL.md +35 -0
  129. package/vendor/pstack/skills/reflect/SKILL.md +17 -0
  130. package/vendor/pstack/skills/setup-pstack/SKILL.md +78 -0
  131. package/vendor/pstack/skills/sharpen/SKILL.md +16 -0
  132. package/vendor/pstack/skills/show-me-your-work/SKILL.md +82 -0
  133. package/vendor/pstack/skills/show-me-your-work/references/decision-log-template.tsv +1 -0
  134. package/vendor/pstack/skills/show-me-your-work/scripts/log.sh +42 -0
  135. package/vendor/pstack/skills/statechart/SKILL.md +82 -0
  136. package/vendor/pstack/skills/statechart/references/render.md +93 -0
  137. package/vendor/pstack/skills/statechart/scripts/backends/cfg.ts +33 -0
  138. package/vendor/pstack/skills/statechart/scripts/backends/mermaid.ts +249 -0
  139. package/vendor/pstack/skills/statechart/scripts/backends/plain-text.ts +72 -0
  140. package/vendor/pstack/skills/statechart/scripts/backends/report.ts +177 -0
  141. package/vendor/pstack/skills/statechart/scripts/frontends/config.ts +276 -0
  142. package/vendor/pstack/skills/statechart/scripts/frontends/dot.ts +74 -0
  143. package/vendor/pstack/skills/statechart/scripts/frontends/marks.ts +93 -0
  144. package/vendor/pstack/skills/statechart/scripts/frontends/messages.ts +52 -0
  145. package/vendor/pstack/skills/statechart/scripts/frontends/spec.ts +114 -0
  146. package/vendor/pstack/skills/statechart/scripts/frontends/trace.ts +24 -0
  147. package/vendor/pstack/skills/statechart/scripts/frontends/value.ts +166 -0
  148. package/vendor/pstack/skills/statechart/scripts/frontends/verdict.ts +40 -0
  149. package/vendor/pstack/skills/statechart/scripts/frontends/view.ts +119 -0
  150. package/vendor/pstack/skills/statechart/scripts/ir.ts +547 -0
  151. package/vendor/pstack/skills/statechart/scripts/package.json +11 -0
  152. package/vendor/pstack/skills/statechart/scripts/passes/annotate.ts +128 -0
  153. package/vendor/pstack/skills/statechart/scripts/passes/label.ts +269 -0
  154. package/vendor/pstack/skills/statechart/scripts/passes/lift.ts +85 -0
  155. package/vendor/pstack/skills/statechart/scripts/passes/loop-check.ts +68 -0
  156. package/vendor/pstack/skills/statechart/scripts/passes/paths.ts +60 -0
  157. package/vendor/pstack/skills/statechart/scripts/passes/reach.ts +135 -0
  158. package/vendor/pstack/skills/statechart/scripts/passes/region-check.ts +97 -0
  159. package/vendor/pstack/skills/statechart/scripts/passes/regions.ts +295 -0
  160. package/vendor/pstack/skills/statechart/scripts/pipeline.ts +76 -0
  161. package/vendor/pstack/skills/statechart/scripts/run.ts +506 -0
  162. package/vendor/pstack/skills/statechart/scripts/statechart +29 -0
  163. package/vendor/pstack/skills/statechart/scripts/statechart.ts +164 -0
  164. package/vendor/pstack/skills/statechart/scripts/test/ConfigOracle.java +63 -0
  165. package/vendor/pstack/skills/statechart/scripts/test/chart.test.ts +1253 -0
  166. package/vendor/pstack/skills/statechart/scripts/test/charts/Braces.mmd +7 -0
  167. package/vendor/pstack/skills/statechart/scripts/test/charts/Escapes.mmd +11 -0
  168. package/vendor/pstack/skills/statechart/scripts/test/charts/Phases.mmd +29 -0
  169. package/vendor/pstack/skills/statechart/scripts/test/cli.test.ts +1315 -0
  170. package/vendor/pstack/skills/statechart/scripts/test/config-fuzz.test.ts +263 -0
  171. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/ChartRun.out +57 -0
  172. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/Counter.cfg +3 -0
  173. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/Counter.tla +10 -0
  174. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/chart.mmd +9 -0
  175. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/graph.dot +16 -0
  176. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/report.md +7 -0
  177. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/sany.out +2 -0
  178. package/vendor/pstack/skills/statechart/scripts/test/corpus/Counter/verdict-1.out +49 -0
  179. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/ChartRun.out +60 -0
  180. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/CounterAction.cfg +4 -0
  181. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/CounterAction.tla +22 -0
  182. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/chart.mmd +26 -0
  183. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/graph.dot +19 -0
  184. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/report.md +20 -0
  185. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/sany.out +2 -0
  186. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/verdict-1.exit +1 -0
  187. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/verdict-1.out +56 -0
  188. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/verdict-2.exit +1 -0
  189. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/verdict-2.out +82 -0
  190. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterAction/verdict-3.out +57 -0
  191. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/ChartRun.out +59 -0
  192. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/CounterDeadlock.cfg +3 -0
  193. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/CounterDeadlock.tla +11 -0
  194. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/chart.mmd +22 -0
  195. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/graph.dot +16 -0
  196. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/report.md +17 -0
  197. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/sany.out +2 -0
  198. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-1.exit +1 -0
  199. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-1.out +56 -0
  200. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-2.exit +1 -0
  201. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterDeadlock/verdict-2.out +77 -0
  202. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/ChartRun.out +69 -0
  203. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/CounterFan.cfg +2 -0
  204. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/CounterFan.tla +11 -0
  205. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/chart.mmd +85 -0
  206. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/graph.dot +70 -0
  207. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/report.md +12 -0
  208. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/sany.out +2 -0
  209. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/verdict-1.exit +1 -0
  210. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/verdict-1.out +67 -0
  211. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterFan/verdict-2.out +57 -0
  212. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/ChartRun.exit +1 -0
  213. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/ChartRun.out +85 -0
  214. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/CounterGuard.cfg +6 -0
  215. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/CounterGuard.tla +13 -0
  216. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/chart.mmd +5 -0
  217. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/graph.dot +10 -0
  218. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/report.md +31 -0
  219. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/sany.out +2 -0
  220. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/verdict-1.exit +1 -0
  221. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/verdict-1.out +64 -0
  222. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/verdict-2.exit +1 -0
  223. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterGuard/verdict-2.out +77 -0
  224. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/ChartRun.out +55 -0
  225. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/CounterInitPast.cfg +3 -0
  226. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/CounterInitPast.tla +10 -0
  227. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/chart.mmd +12 -0
  228. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/graph.dot +6 -0
  229. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/report.md +12 -0
  230. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/sany.out +2 -0
  231. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/verdict-1.exit +1 -0
  232. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/verdict-1.out +33 -0
  233. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPast/verdict-2.out +54 -0
  234. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/ChartRun.out +54 -0
  235. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/CounterInitPastHolds.cfg +3 -0
  236. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/CounterInitPastHolds.tla +10 -0
  237. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/chart.mmd +1 -0
  238. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/graph.dot +6 -0
  239. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/report.md +7 -0
  240. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/sany.out +2 -0
  241. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInitPastHolds/verdict-1.out +46 -0
  242. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/ChartRun.out +59 -0
  243. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/CounterInstance.cfg +2 -0
  244. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/CounterInstance.tla +10 -0
  245. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/CounterSteps.tla +6 -0
  246. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/chart.mmd +17 -0
  247. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/graph.dot +15 -0
  248. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/report.md +14 -0
  249. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/sany.out +3 -0
  250. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/verdict-1.exit +1 -0
  251. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterInstance/verdict-1.out +78 -0
  252. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/ChartRun.out +59 -0
  253. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/CounterJump.cfg +3 -0
  254. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/CounterJump.tla +19 -0
  255. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/chart.mmd +26 -0
  256. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/graph.dot +22 -0
  257. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/report.md +12 -0
  258. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/sany.out +2 -0
  259. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/verdict-1.exit +1 -0
  260. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/verdict-1.out +58 -0
  261. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterJump/verdict-2.out +57 -0
  262. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/ChartRun.out +57 -0
  263. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/CounterLoop.cfg +2 -0
  264. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/CounterLoop.tla +11 -0
  265. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/chart.mmd +17 -0
  266. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/graph.dot +15 -0
  267. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/report.md +14 -0
  268. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/sany.out +2 -0
  269. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/verdict-1.exit +1 -0
  270. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterLoop/verdict-1.out +76 -0
  271. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/ChartRun.out +59 -0
  272. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/CounterOrder.cfg +3 -0
  273. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/CounterOrder.tla +11 -0
  274. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/chart.mmd +19 -0
  275. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/graph.dot +10 -0
  276. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/report.md +15 -0
  277. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/sany.out +2 -0
  278. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/verdict-1.exit +1 -0
  279. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/verdict-1.out +56 -0
  280. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/verdict-2.exit +1 -0
  281. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterOrder/verdict-2.out +67 -0
  282. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/ChartRun.out +62 -0
  283. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/CounterRules.cfg +6 -0
  284. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/CounterRules.tla +24 -0
  285. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/Moves.tla +5 -0
  286. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/chart.mmd +22 -0
  287. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/graph.dot +10 -0
  288. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/report.md +23 -0
  289. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/sany.out +3 -0
  290. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-1.exit +1 -0
  291. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-1.out +58 -0
  292. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-2.exit +1 -0
  293. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-2.out +66 -0
  294. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-3.exit +1 -0
  295. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-3.out +74 -0
  296. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterRules/verdict-4.out +59 -0
  297. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/ChartRun.out +58 -0
  298. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/CounterStart.cfg +3 -0
  299. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/CounterStart.tla +15 -0
  300. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/chart.mmd +18 -0
  301. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/graph.dot +13 -0
  302. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/report.md +11 -0
  303. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/sany.out +2 -0
  304. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/verdict-1.exit +1 -0
  305. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/verdict-1.out +33 -0
  306. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStart/verdict-2.out +57 -0
  307. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/ChartRun.out +57 -0
  308. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/CounterStop.cfg +3 -0
  309. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/CounterStop.tla +15 -0
  310. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/chart.mmd +7 -0
  311. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/graph.dot +13 -0
  312. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/report.md +6 -0
  313. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/sany.out +2 -0
  314. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterStop/verdict-1.out +49 -0
  315. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/ChartRun.out +61 -0
  316. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/CounterTie.cfg +4 -0
  317. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/CounterTie.tla +14 -0
  318. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/chart.mmd +30 -0
  319. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/graph.dot +19 -0
  320. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/report.md +27 -0
  321. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/sany.out +2 -0
  322. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-1.exit +1 -0
  323. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-1.out +56 -0
  324. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-2.exit +1 -0
  325. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-2.out +64 -0
  326. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-3.exit +1 -0
  327. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-3.out +87 -0
  328. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTie/verdict-4.out +57 -0
  329. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/ChartRun.out +60 -0
  330. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/CounterTieInGraph.cfg +3 -0
  331. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/CounterTieInGraph.tla +12 -0
  332. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/chart.mmd +23 -0
  333. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/graph.dot +19 -0
  334. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/report.md +11 -0
  335. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/sany.out +2 -0
  336. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/verdict-1.exit +1 -0
  337. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/verdict-1.out +56 -0
  338. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterTieInGraph/verdict-2.out +57 -0
  339. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/ChartRun.out +61 -0
  340. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/CounterView.cfg +4 -0
  341. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/CounterView.tla +14 -0
  342. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/chart.mmd +23 -0
  343. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/graph.dot +19 -0
  344. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/report.md +27 -0
  345. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/sany.out +2 -0
  346. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-1.exit +1 -0
  347. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-1.out +56 -0
  348. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-2.exit +1 -0
  349. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-2.out +64 -0
  350. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-3.exit +1 -0
  351. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-3.out +87 -0
  352. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/verdict-4.out +57 -0
  353. package/vendor/pstack/skills/statechart/scripts/test/corpus/CounterView/view.mjs +1 -0
  354. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/ChartRun.out +59 -0
  355. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/DieHard.cfg +4 -0
  356. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/DieHard.tla +38 -0
  357. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/chart.mmd +92 -0
  358. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/graph.dot +126 -0
  359. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/report.md +17 -0
  360. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/sany.out +2 -0
  361. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/verdict-1.exit +1 -0
  362. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/verdict-1.out +91 -0
  363. package/vendor/pstack/skills/statechart/scripts/test/corpus/DieHard/verdict-2.out +57 -0
  364. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/ChartRun.out +61 -0
  365. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/FirstRule.cfg +6 -0
  366. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/FirstRule.tla +11 -0
  367. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/chart.mmd +22 -0
  368. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/graph.dot +16 -0
  369. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/report.md +25 -0
  370. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/sany.out +2 -0
  371. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-1.exit +1 -0
  372. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-1.out +56 -0
  373. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-2.exit +1 -0
  374. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-2.out +64 -0
  375. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-3.exit +1 -0
  376. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-3.out +64 -0
  377. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-4.exit +1 -0
  378. package/vendor/pstack/skills/statechart/scripts/test/corpus/FirstRule/verdict-4.out +77 -0
  379. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/ChartRun.out +57 -0
  380. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/HiddenClock.cfg +4 -0
  381. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/HiddenClock.tla +11 -0
  382. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/chart.mmd +13 -0
  383. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/graph.dot +12 -0
  384. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/report.md +11 -0
  385. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/sany.out +2 -0
  386. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/verdict-1.exit +1 -0
  387. package/vendor/pstack/skills/statechart/scripts/test/corpus/HiddenClock/verdict-1.out +72 -0
  388. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/ChartRun.out +57 -0
  389. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/Login.cfg +3 -0
  390. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/Login.tla +62 -0
  391. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/chart.mmd +28 -0
  392. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/graph.dot +40 -0
  393. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/report.md +7 -0
  394. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/sany.out +1 -0
  395. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/verdict-1.out +47 -0
  396. package/vendor/pstack/skills/statechart/scripts/test/corpus/Login/view.mjs +1 -0
  397. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/ChartRun.out +57 -0
  398. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/LoginGuarded.cfg +2 -0
  399. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/LoginGuarded.tla +64 -0
  400. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/chart.mmd +28 -0
  401. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/graph.dot +37 -0
  402. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/report.md +8 -0
  403. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/sany.out +1 -0
  404. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/verdict-1.out +47 -0
  405. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginGuarded/view.mjs +1 -0
  406. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/ChartRun.out +60 -0
  407. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/LoginParallel.cfg +3 -0
  408. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/LoginParallel.tla +64 -0
  409. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/chart.mmd +44 -0
  410. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/graph.dot +58 -0
  411. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/report.md +17 -0
  412. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/sany.out +1 -0
  413. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/verdict-1.exit +1 -0
  414. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/verdict-1.out +83 -0
  415. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/verdict-2.out +57 -0
  416. package/vendor/pstack/skills/statechart/scripts/test/corpus/LoginParallel/view.mjs +1 -0
  417. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/ChartRun.out +60 -0
  418. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/MediaPlayer.cfg +3 -0
  419. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/MediaPlayer.tla +103 -0
  420. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/chart.mmd +43 -0
  421. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/graph.dot +93 -0
  422. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/report.md +14 -0
  423. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/sany.out +1 -0
  424. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/verdict-1.exit +1 -0
  425. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/verdict-1.out +59 -0
  426. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/verdict-2.out +72 -0
  427. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayer/view.mjs +3 -0
  428. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/ChartRun.out +57 -0
  429. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/MediaPlayerFixed.cfg +2 -0
  430. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/MediaPlayerFixed.tla +100 -0
  431. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/chart.mmd +31 -0
  432. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/graph.dot +85 -0
  433. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/report.md +9 -0
  434. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/sany.out +1 -0
  435. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/verdict-1.out +47 -0
  436. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerFixed/view.mjs +3 -0
  437. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/ChartRun.out +59 -0
  438. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/MediaPlayer.tla +103 -0
  439. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/MediaPlayerProps.cfg +3 -0
  440. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/MediaPlayerProps.tla +6 -0
  441. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/chart.mmd +42 -0
  442. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/graph.dot +93 -0
  443. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/report.md +19 -0
  444. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/sany.out +2 -0
  445. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-1.exit +1 -0
  446. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-1.out +61 -0
  447. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-2.out +59 -0
  448. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-3.out +61 -0
  449. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-4.exit +1 -0
  450. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-4.out +66 -0
  451. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-5.exit +1 -0
  452. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-5.out +58 -0
  453. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/verdict-6.out +49 -0
  454. package/vendor/pstack/skills/statechart/scripts/test/corpus/MediaPlayerProps/view.mjs +3 -0
  455. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/ChartRun.out +57 -0
  456. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/PickWorker.cfg +6 -0
  457. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/PickWorker.tla +11 -0
  458. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/chart.mmd +5 -0
  459. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/graph.dot +11 -0
  460. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/report.md +7 -0
  461. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/sany.out +5 -0
  462. package/vendor/pstack/skills/statechart/scripts/test/corpus/PickWorker/verdict-1.out +70 -0
  463. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/ChartRun.out +61 -0
  464. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/Shadow.cfg +4 -0
  465. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/Shadow.tla +11 -0
  466. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/ShadowLib.tla +6 -0
  467. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/ShadowSub.tla +3 -0
  468. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/chart.mmd +9 -0
  469. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/graph.dot +16 -0
  470. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/report.md +8 -0
  471. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/sany.out +4 -0
  472. package/vendor/pstack/skills/statechart/scripts/test/corpus/Shadow/verdict-1.out +65 -0
  473. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/ChartRun.out +59 -0
  474. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/SpacedNames.cfg +2 -0
  475. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/SpacedNames.tla +9 -0
  476. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/chart.mmd +23 -0
  477. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/graph.dot +17 -0
  478. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/report.md +15 -0
  479. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/sany.out +1 -0
  480. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/verdict-1.exit +1 -0
  481. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/verdict-1.out +65 -0
  482. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/verdict-2.exit +1 -0
  483. package/vendor/pstack/skills/statechart/scripts/test/corpus/SpacedNames/verdict-2.out +75 -0
  484. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/ChartRun.out +69 -0
  485. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/TwoPhase.cfg +3 -0
  486. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/TwoPhase.tla +75 -0
  487. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/chart.mmd +60 -0
  488. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/graph.dot +297 -0
  489. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/report.md +20 -0
  490. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/sany.out +1 -0
  491. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/verdict-1.exit +1 -0
  492. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/verdict-1.out +95 -0
  493. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/verdict-2.out +57 -0
  494. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhase/view.mjs +1 -0
  495. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/ChartRun.out +57 -0
  496. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/TwoPhaseFixed.cfg +3 -0
  497. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/TwoPhaseFixed.tla +75 -0
  498. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/chart.mmd +37 -0
  499. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/graph.dot +223 -0
  500. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/report.md +11 -0
  501. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/sany.out +1 -0
  502. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/verdict-1.out +47 -0
  503. package/vendor/pstack/skills/statechart/scripts/test/corpus/TwoPhaseFixed/view.mjs +1 -0
  504. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/ChartRun.exit +1 -0
  505. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/ChartRun.out +75 -0
  506. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/TypeGuard.cfg +5 -0
  507. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/TypeGuard.tla +11 -0
  508. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/chart.mmd +18 -0
  509. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/graph.dot +14 -0
  510. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/report.md +29 -0
  511. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/sany.out +2 -0
  512. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/verdict-1.exit +1 -0
  513. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/verdict-1.out +64 -0
  514. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/verdict-2.exit +1 -0
  515. package/vendor/pstack/skills/statechart/scripts/test/corpus/TypeGuard/verdict-2.out +75 -0
  516. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/ChartRun.out +58 -0
  517. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/UserNoDeadlock.cfg +2 -0
  518. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/UserNoDeadlock.tla +8 -0
  519. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/chart.mmd +22 -0
  520. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/graph.dot +16 -0
  521. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/report.md +15 -0
  522. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/sany.out +2 -0
  523. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-1.exit +1 -0
  524. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-1.out +56 -0
  525. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-2.exit +1 -0
  526. package/vendor/pstack/skills/statechart/scripts/test/corpus/UserNoDeadlock/verdict-2.out +77 -0
  527. package/vendor/pstack/skills/statechart/scripts/test/corpus.test.ts +441 -0
  528. package/vendor/pstack/skills/statechart/scripts/test/differential.test.ts +565 -0
  529. package/vendor/pstack/skills/statechart/scripts/test/drawn.ts +20 -0
  530. package/vendor/pstack/skills/statechart/scripts/test/grid/Grid.cfg +2 -0
  531. package/vendor/pstack/skills/statechart/scripts/test/grid/Grid.tla +9 -0
  532. package/vendor/pstack/skills/statechart/scripts/test/grid/sany.out +2 -0
  533. package/vendor/pstack/skills/statechart/scripts/test/java.ts +63 -0
  534. package/vendor/pstack/skills/statechart/scripts/test/labels.ts +648 -0
  535. package/vendor/pstack/skills/statechart/scripts/test/messages.test.ts +212 -0
  536. package/vendor/pstack/skills/statechart/scripts/test/pipeline.test.ts +270 -0
  537. package/vendor/pstack/skills/statechart/scripts/test/plain-tlc.test.ts +255 -0
  538. package/vendor/pstack/skills/statechart/scripts/test/render.test.ts +145 -0
  539. package/vendor/pstack/skills/statechart/scripts/test/tlc-out.test.ts +90 -0
  540. package/vendor/pstack/skills/statechart/scripts/test/tlc.ts +158 -0
  541. package/vendor/pstack/skills/statechart/scripts/tsconfig.json +11 -0
  542. package/vendor/pstack/skills/statechart/scripts/worker.ts +35 -0
  543. package/vendor/pstack/skills/swarm/SKILL.md +41 -0
  544. package/vendor/pstack/skills/tdd/SKILL.md +42 -0
  545. package/vendor/pstack/skills/teach/SKILL.md +21 -0
  546. package/vendor/pstack/skills/technical-writing/SKILL.md +70 -0
  547. package/vendor/pstack/skills/typescript-best-practices/SKILL.md +31 -0
  548. package/vendor/pstack/skills/typescript-best-practices/references/patterns.md +328 -0
  549. package/vendor/pstack/skills/unslop/SKILL.md +40 -0
  550. package/vendor/pstack/skills/why/SKILL.md +9 -0
  551. package/vendor/pstack/upstream-plugin.json +21 -0
@@ -0,0 +1,43 @@
1
+ ---
2
+ name: create-formal-verification-skill
3
+ description: "Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, \"model-check this race\", \"prove this invariant\", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Create a formal verification skill
8
+
9
+ A test checks the cases that someone thought to write. Formal verification checks every case in a stated scope: every order of steps in a model, every input up to a bound, or every input. This skill finds the part of the repo where that matters most, verifies one property of it, and leaves a project-local skill that lets the next agent check a change against that property. Write that skill for an agent who reads it cold, mid-change, and has never seen your work. The user must be able to trust the result and act on it without learning the verification language.
10
+
11
+ ## Choose the target from the code
12
+
13
+ Answer from the codebase, and ask the user only what you cannot observe. If the user named an area or a bug, start there.
14
+
15
+ A good target is a promise the code makes, where a break harms users and tests rarely reach the case that breaks it. Choose the strongest such target in the repo, not the one that is easiest to verify.
16
+
17
+ ## Let the question choose the tool
18
+
19
+ Pick the tool that answers the question at the lowest cost: a model checker, a proof assistant, an SMT-backed verifier, or another tool. Whether events can happen in a bad order usually suits a model checker over a small model of the design, and TLA+ is the default for that in any language. Whether the code itself behaves for every input, as with memory safety, overflow, or a data-structure invariant, usually suits a verifier that runs on the code. If no verifier runs on this language, say so, and test the real code with generated inputs, not a hand model of the function. A property that must hold at every size, where a bound is not enough, can need a proof. Prefer a tool that the repo's developers can install and run, and tell the user why you chose it.
20
+
21
+ ## What makes it good
22
+
23
+ - **True to the code.** Every part of the model or proof points to code that a reviewer can open. What the verification treats as one indivisible step is one indivisible step in the code. Names come from this repo.
24
+ - **Able to fail.** A check that you have never seen fail proves nothing. Show each property failing on a broken variant of the code it guards, such as a removed check or a reordered step.
25
+ - **Findings stay findings.** When the current code breaks the property, report it with the counterexample in the code's terms. Do not weaken the property or the model until it passes, and do not change product code unless the user asks.
26
+ - **Honest about scope.** Say what is verified, under which bounds and assumptions, and what is left out. A pass covers the model or the bound, not the whole system.
27
+ - **Readable without the tool.** State the property and the harm in one plain sentence each. Tell a counterexample as a short sequence of steps in the code's words.
28
+ - **Cheap to rerun.** One command, a reproducible tool version, and a run short enough that the next agent will use it on every relevant change.
29
+ - **Kept in step with the code.** Record which files and functions each check covers, and the commit at which you last confirmed that the verification describes them. When the covered code changes after that commit, the next agent can see that the verification needs another look.
30
+
31
+ ## Generate the verify skill
32
+
33
+ Write a project-local skill with frontmatter that names the area and says when to use it. Without frontmatter, the skill never registers. From the skill alone, the next agent must be able to tell whether a change touches the verified code, run the check, tell a real bug from a modeling error, and update the verification when a change is intended. Put the coverage record and the sync commit in the skill, and tell the next agent to move the sync commit forward only after it confirms that the verification describes the code at the new commit. Use this repo's real commands, paths, and nouns, and leave no placeholders.
34
+
35
+ If the check is a TLA+ model, tell the next agent to read every result with the pstack [`/statechart`](../statechart/SKILL.md) skill. It shows each invariant violation the checker finds as its shortest path in plain words. When the check passes, `/statechart` draws a chart of how the system moves between states. Refer to `/statechart` by name. Its commands, options, and file paths change between releases and machines, so copy none of them into the generated skill or its scripts.
36
+
37
+ ## Prove it before you hand off
38
+
39
+ Follow the generated skill once, as the next agent would, on a scratch change that breaks the property in the real code. It must catch the break. Then drop the scratch change and confirm that the check is back where it started: passing, or failing only on the findings you will report. A verify skill that was never run is a draft. If the skill misses the break or a step does not run, fix the skill or the verification, not the scratch change.
40
+
41
+ ## Hand off
42
+
43
+ Tell the user what you verified, which tool you used and why, the bounds, what the check found in plain words, how to run it, and what it does not cover. Suggest a second target only if you found a close one. Point the user at `/maintain-formal-verification-skill` for bringing the verification back in line after changes that did not recheck it.
@@ -0,0 +1,44 @@
1
+ ---
2
+ name: create-verification-skill
3
+ description: "Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Create a verification skill
8
+
9
+ Every serious project needs a scripted way to drive the real app and prove behavior: launch it, exercise a feature the way a user would, and capture evidence. This skill generates that as a project-local skill (`.cursor/skills/verify-<app>/`) tailored to the repo. You write the generator's output for the next agent, not for a human: it will be read cold, mid-task, by an agent that has never seen the app.
10
+
11
+ ## 1. Interview the repo, not the user
12
+
13
+ Answer these from the codebase and only ask the user what you cannot observe:
14
+
15
+ - **Surface:** what does a user actually touch? A web UI, a CLI/TUI, a desktop app, an API, a mobile app, a library? A repo can have several; pick the primary one and note the rest.
16
+ - **Run:** how does the app start locally? Prefer the repo's own documented dev command (package scripts, Makefile, README quickstart). Note ports, env vars, seed data, auth.
17
+ - **Drive:** how can an agent interact with it programmatically? Existing harnesses first — Playwright/Cypress specs, expect scripts, PTY helpers, curl-able endpoints, a debug port. Only then pick a generic recipe: browser/CDP for web and Electron, a tmux/PTY harness for CLI/TUI, plain HTTP for services.
18
+ - **Observe:** what evidence can be captured? Screenshots, terminal transcripts, response bodies, logs, exit codes, DB state.
19
+ - **Isolate:** can two instances run side by side (ports, data dirs, profiles)? If not, say so in the generated skill: refusing to double-drive a shared instance beats corrupting the user's session.
20
+
21
+ If the checkout doesn't build or start as-is, fix that first (or report it precisely) before generating; a skill written against a broken base teaches wrong steps. When an irrelevant missing asset blocks startup (a static dir the API never serves, a sample config), the generated skill may create it, clearly marked as verification scaffolding, and remove it in cleanup.
22
+
23
+ ## 2. Generate the skill
24
+
25
+ Write `.cursor/skills/verify-<app>/SKILL.md` with YAML frontmatter (`name: verify-<app>` and a `description` that names the app, the surface, and when to reach for it — without frontmatter the skill never registers) and these sections, each grounded in what the interview actually found (no placeholders left):
26
+
27
+ - **Launch:** the exact command that starts the app for verification, and how to tell it's ready (a log line, a prompt). Launch must reach a usable state from an empty data dir, including any migrations and seed data. Ready means usable, not just that a process answers. A database health check can pass while its init scripts are still running. Include teardown. For a short-lived CLI or TUI there is no server to keep alive: launch means build the binary (or install deps) once, then start each drive in its own isolated PTY or tmux session.
28
+ - **Doctor:** one read-only check that answers "is this instance worth driving?" — process up, right version/build, port owned by us, auth valid. An agent runs this first whenever anything looks off.
29
+ - **Drive:** the harness recipe with real selectors/commands from this repo, not examples. Prefer stable handles (ARIA labels, data attributes, prompt strings, route paths) over coordinates and tab order.
30
+ - **Evidence:** what to capture for a proof and where it goes. State the proof standards: exercise the real user path, not internal setters or test-only endpoints; capture the action and the resulting state, not just the final screen; verify side effects (files written, rows inserted, messages sent) alongside what's visible; mocks only where a production boundary already isolates the external system. When the safe path is a dry-run or test mode, verify what it actually skips by observing (files, network, git refs) rather than trusting its name: some dry-runs still touch the network or open a browser.
31
+ - **Cleanup:** how to tear down instances the run created. Never kill by process name; kill what you started. Cleanup removes instances and scratch state, never the evidence: proof artifacts survive the teardown, in a location the skill names.
32
+ - **Helpers:** any script the skill ships is executable and its invocation is shown in the skill body. A helper the reader has to reverse-engineer is not a helper.
33
+
34
+ ## 3. Seed the feature map
35
+
36
+ Create `.cursor/skills/verify-<app>/features/README.md` plus one file per user-facing feature you can identify (aim for the top 3-5 to start, from routes, commands, menus, or docs). Follow the shape in [`references/feature-map-example/`](references/feature-map-example/), with a README index and one file per feature. Each file answers, from the user's point of view: what the feature is, how to reach it, how to drive it with the harness, and what observable end state proves it works. The four H2s are `Sub-features`, `How to get to it (user POV)`, `Driving it with <harness>`, and `Gotchas`. If the seed data lacks a precondition that a journey needs, the journey reports a failure and the reason goes in that feature's `Gotchas`. Never weaken the journey to make it pass. The map is the repo's maintained verification source; a proof that drives one convenient entry point is incomplete when the map lists others.
37
+
38
+ ## 4. Prove the generated skill before handing it over
39
+
40
+ Run its own instructions end to end once: launch, doctor, drive ONE mapped feature (one is enough; the map exists so later runs can cover the rest), capture evidence, clean up. After cleanup, confirm the evidence still exists at the named location — a cleanup that eats the proof fails this step. Fix what fails, and run the generated cleanup after every failed iteration too, so broken attempts don't strand processes and ports. A generated skill that was never executed is a draft, not a deliverable. If you proved it in a stand-in for the real target (a container in place of a fresh VM, a local stack in place of a remote one), list every setup step the stand-in did that the target will not. Those steps stay unverified until a run on the real target covers them.
41
+
42
+ ## 5. Offer the maintenance loop
43
+
44
+ Point the user at `/maintain-verification-skill` for keeping the map honest as the app changes. Suggest a cadence only if they ask.
@@ -0,0 +1,47 @@
1
+ # Notes verification map
2
+
3
+ This directory is the maintained source for verifying the user-facing behavior of Notes. Read the index before driving the app, then use the matching feature file as the recipe.
4
+
5
+ ## Baseline preconditions
6
+
7
+ - Launch Notes at `http://127.0.0.1:4173` with a disposable data directory.
8
+ - Set `NOTES_DATA_DIR=/tmp/notes-verify-$RUN_ID` so concurrent runs do not share state.
9
+ - Seed notes titled `Quarterly plan` and `Grocery list`.
10
+ - Put `control-notes` and the `notes` CLI on `PATH`.
11
+ - Run `control-notes doctor` and require the expected URL, data directory, and build revision.
12
+ - Never drive an instance that was not started by this verification run.
13
+
14
+ ## Driving conventions
15
+
16
+ - Start every recipe from the baseline state unless its preconditions say otherwise.
17
+ - Prefer ARIA roles and accessible names over CSS selectors or DOM position.
18
+ - Treat every command as literal. Keep quoted names and flags unchanged.
19
+ - Run browser actions through `control-notes browser`.
20
+ - Run terminal actions through `control-notes cli -- <command>`.
21
+ - Restore seeded data after a mutation. Do not remove proof artifacts during cleanup.
22
+
23
+ ## Proof and skip reporting
24
+
25
+ - Capture the user action and the resulting state, not only the final screen.
26
+ - UI proof includes an ARIA snapshot and a screenshot with the app identity visible.
27
+ - CLI proof includes the command, stdout, stderr, and exit code.
28
+ - Mutation proof includes a read-only second view of the stored value.
29
+ - Record the feature ID and entry point used with every artifact.
30
+ - Report an unreachable path with the attempted command and the unmet precondition.
31
+ - Do not report a skipped entry point as verified through a different path.
32
+
33
+ ## Feature entry contract
34
+
35
+ Each feature file starts with an H1 title and one paragraph describing the user-visible behavior. It then uses exactly four H2 sections in this order.
36
+
37
+ 1. `Sub-features` lists short IDs with one line for each behavior.
38
+ 2. `How to get to it (user POV)` lists every user entry point.
39
+ 3. `Driving it with <harness>` starts with `Preconditions:` and uses labeled bullets that pair each user action with an exact command and observable result.
40
+ 4. `Gotchas` lists traps that can waste or invalidate a verification run.
41
+
42
+ Keep implementation details out of the map. Name only user paths, stable handles, required state, commands, and observable proof.
43
+
44
+ ## Features
45
+
46
+ - [Create a note](./create-note.md) covers browser and CLI creation, cancellation, persistence, and cleanup.
47
+ - [Search notes](./search.md) covers toolbar, keyboard, and CLI search with matching, empty, and clear states.
@@ -0,0 +1,39 @@
1
+ # Create a note
2
+
3
+ Create note lets a user save a titled note from the browser or CLI, cancel an unfinished draft, and confirm the saved note from a second user-facing view.
4
+
5
+ ## Sub-features
6
+
7
+ - `create-open` opens a blank editor from each browser entry point.
8
+ - `create-save` persists a title and body.
9
+ - `create-cancel` discards an unfinished browser draft.
10
+ - `create-cli` creates the same note shape from the terminal.
11
+
12
+ ## How to get to it (user POV)
13
+
14
+ - Choose the `New note` button in the browser toolbar.
15
+ - Press `n` in the browser while focus is outside an editable field.
16
+ - Run `notes create --title <title> --body <body>` in a terminal.
17
+
18
+ ## Driving it with control-notes
19
+
20
+ Preconditions:
21
+
22
+ - Notes is healthy at `http://127.0.0.1:4173`.
23
+ - No note is titled `Release checklist`.
24
+ - `control-notes doctor` reports the expected URL and disposable data directory.
25
+
26
+ - **Open editor.** Choose `New note`. Run `control-notes browser click --role button --name "New note"`. A form named `Note editor` appears with focus in the `Title` textbox.
27
+ - **Enter content.** Type the title and body. Run `control-notes browser fill --role textbox --name "Title" --value "Release checklist"` and `control-notes browser fill --role textbox --name "Body" --value "Tag and publish"`. The `Save note` button becomes enabled.
28
+ - **Save note.** Choose `Save note`. Run `control-notes browser click --role button --name "Save note"`. A status named `Note saved` appears and the heading reads `Release checklist`.
29
+ - **Confirm persistence.** Return to the note list and reopen the note. Run `control-notes browser click --role link --name "All notes"` and `control-notes browser click --role link --name "Release checklist"`. The editor shows both saved values.
30
+ - **Cancel draft.** Open a new note, enter `Discard me`, and choose `Cancel`. Run `control-notes browser click --role button --name "New note"`, `control-notes browser fill --role textbox --name "Title" --value "Discard me"`, and `control-notes browser click --role button --name "Cancel"`. The note list returns and has no `Discard me` link.
31
+ - **CLI entry.** Create a second note. Run `control-notes cli -- notes create --title "CLI note" --body "Created from terminal" --format json`. Exit code `0` and stdout contain the new note ID and title.
32
+ - **Proof.** Reopen both saved notes from `All notes`. Run `control-notes browser snapshot --aria --path artifacts/create-note/list.aria.txt` and `control-notes browser screenshot --path artifacts/create-note/list.png`. The artifacts show `Release checklist` and `CLI note`.
33
+
34
+ ## Gotchas
35
+
36
+ - Pressing `n` while a textbox has focus types the character instead of opening a new editor.
37
+ - Titles are trimmed on save. Assert the rendered title, not the draft input value.
38
+ - A save status alone is insufficient proof. Reopen the note from the list.
39
+ - Remove `Release checklist` and `CLI note` during fixture cleanup, but retain their proof artifacts.
@@ -0,0 +1,45 @@
1
+ # Search notes
2
+
3
+ Search lets a user find notes by title or body text, inspect a matching note, and distinguish no matches from an unavailable search.
4
+
5
+ ## Sub-features
6
+
7
+ - `search-open` opens search from each supported browser entry point.
8
+ - `search-match` returns title and body matches without changing note data.
9
+ - `search-open-result` opens a result in the note editor.
10
+ - `search-empty` shows a complete empty state for a query with no matches.
11
+ - `search-clear` removes the query and restores the recent-notes view.
12
+ - `search-cli` returns the same matching notes from the terminal.
13
+
14
+ ## How to get to it (user POV)
15
+
16
+ - Choose the `Search` button in the browser toolbar.
17
+ - Press `/` in the browser while focus is outside an editable field.
18
+ - Run `notes search <query>` in a terminal.
19
+
20
+ ## Driving it with control-notes
21
+
22
+ Preconditions:
23
+
24
+ - Notes is healthy at `http://127.0.0.1:4173`.
25
+ - The disposable data directory contains `Quarterly plan` with body text `Draft budget`.
26
+ - `control-notes doctor` reports the expected URL and data directory.
27
+
28
+ - **Toolbar entry.** Choose the `Search` button. Run `control-notes browser click --role button --name "Search"`. A dialog named `Search notes` appears with focus in its searchbox.
29
+ - **Keyboard entry.** Close the dialog, focus the page, and press `/`. Run `control-notes browser press --key "/"`. The same dialog appears and the page does not insert a slash.
30
+ - **Title match.** Type `quarterly`. Run `control-notes browser fill --role searchbox --name "Search notes" --value "quarterly"`. The `Search results` list contains `Quarterly plan` and does not contain `Grocery list`.
31
+ - **Body match.** Replace the query with `budget`. Run `control-notes browser fill --role searchbox --name "Search notes" --value "budget"`. The result `Quarterly plan` remains visible with a body-match excerpt.
32
+ - **Open result.** Choose `Quarterly plan`. Run `control-notes browser click --role link --name "Quarterly plan"`. The dialog closes and the editor heading reads `Quarterly plan`.
33
+ - **Empty state.** Reopen search and enter `volcano`. Run `control-notes browser fill --role searchbox --name "Search notes" --value "volcano"`. A status named `No matching notes` appears after search completes.
34
+ - **Clear query.** Choose `Clear search`. Run `control-notes browser click --role button --name "Clear search"`. The searchbox is empty and the `Recent notes` region replaces the result list.
35
+ - **CLI match.** Search from the terminal. Run `control-notes cli -- notes search "quarterly" --format json`. Exit code `0` and stdout contain one object whose title is `Quarterly plan`.
36
+ - **CLI miss.** Search for an absent value. Run `control-notes cli -- notes search "volcano" --format json`. Exit code `0` and stdout are `[]`.
37
+ - **Proof.** Capture the populated result state. Run `control-notes browser snapshot --aria --path artifacts/search/results.aria.txt` and `control-notes browser screenshot --path artifacts/search/results.png`. Both artifacts identify Notes, the query, and `Quarterly plan`.
38
+
39
+ ## Gotchas
40
+
41
+ - Pressing `/` while the editor or searchbox has focus inserts text instead of opening search.
42
+ - Results update after a short debounce. Wait for the results list or empty status, not a fixed sleep.
43
+ - Archived notes are excluded unless the user enables `Include archived`.
44
+ - The CLI defaults to human-readable output. Use `--format json` for stable assertions.
45
+ - Opening a result changes browser state. Reopen search before proving another query.
@@ -0,0 +1,52 @@
1
+ ---
2
+ name: figure-it-out
3
+ description: "Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Figure it out
8
+
9
+ When the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away.
10
+
11
+ ## Start
12
+
13
+ Open a todolist whose first item is to read the Principles section of the **poteto-mode** skill. Then add the phases below as todos.
14
+
15
+ ## Phase A: Frame
16
+
17
+ Ground first, then commit. Don't start the run until you can state:
18
+
19
+ - The definition of done as a falsifiable predicate (the **prove-it-works** principle skill).
20
+ - Scope, quantified: rough units and effort, plus the blockers grounding surfaced.
21
+ - The rigor level, biased high. One-way doors and high blast radius get more. Reversible low-stakes steps get less. Rigor is gates and artifacts, not "try harder".
22
+
23
+ Present the framing and tradeoffs before committing to a long run. Reversible work proceeds (the **never-block-on-the-human** principle skill), but a multi-hour run earns one checkpoint.
24
+
25
+ ## Phase B: Design the workflow
26
+
27
+ Decompose into atomic, independently-landable units. Sequence riskiest-unknown-first. Scaffold and verification come before features (the **foundational-thinking** principle skill).
28
+
29
+ - Build the verification harness before the work, with the baseline captured from the pre-change state, so the check reads as "old value vs new value".
30
+ - For one-way-door design decisions, run the **architect** skill (it runs **arena**). Skip it for mechanical work whose shape is already concrete. A second arena over a settled design is over-engineering (the **laziness-protocol** principle skill).
31
+ - Decide what fans out. Parallelize only across seams, and give each worker its own worktree or branch (the **separate-before-serializing-shared-state** principle skill). Don't over-fan. Pick each subagent's reasoning level for the job, per the Subagents section of the **poteto-mode** skill.
32
+ - Write the designed phase list down. That list is what the human reviews.
33
+
34
+ Then execute the design. Add its steps to the todolist as concrete items between the Phase C and Phase D entries. Run each under the Phase C loop discipline, and weave the Phase D log through them, a row as each step lands, rather than saving the whole trail for the end.
35
+
36
+ ## Phase C: Run the loop
37
+
38
+ Each unit is an experiment. State the hypothesis, make the smallest change, measure against the predicate on the real artifact, keep it if it advanced, revert it if it didn't. Apply the **sequence-verifiable-units** principle skill, verifying each unit before starting the next instead of batching checks at the end.
39
+
40
+ - Verify by inspecting the artifact, never a self-report. When something passes too easily, suspect the observation method before the system.
41
+ - Pair delegated work with a judge. If a worker games the gate, reset and harden the contract. If the gate itself is wrong, fix the gate in its own change rather than routing around it.
42
+ - A verdict is VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Inconclusive is not a pass. Don't hide a negative.
43
+
44
+ ## Phase D: Keep the audit trail
45
+
46
+ Log the run via the **show-me-your-work** skill. figure-it-out's work is usually ambitious enough to commit the trail so the reviewer can read it in the PR. The trail plus the diff is what lets the human come back and trust the work.
47
+
48
+ ## Phase E: Verify and hand back
49
+
50
+ Check the whole against the Phase A predicate on the real product, not just the harness. Encode any recurring correction as a gate, a lint rule, a check, or a script (the **encode-lessons-in-structure** principle skill).
51
+
52
+ **Reply:** the playbook you designed, the rigor level and why, the decision-trail path, what's verified against the predicate, and what's still open.
@@ -0,0 +1,21 @@
1
+ ---
2
+ name: how
3
+ description: "Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # How
8
+
9
+ Explore the codebase to answer "how does X work?" questions.
10
+
11
+ If the scope is ambiguous, state your interpretation and explore. The user can redirect.
12
+
13
+ ## 1. Explain
14
+
15
+ Spawn one Task subagent with `subagent_type: generalPurpose` and `readonly: true` that explores and explains in one pass. Give it the user's question and this brief:
16
+
17
+ > You are writing an architectural explanation for a senior engineer. Explore the codebase and write an explanation that a senior engineer unfamiliar with this area could read and walk away with a solid mental model. They should understand the architecture well enough to start working in it confidently. You have read-only access to the codebase.
18
+
19
+ ## 2. Present
20
+
21
+ Present the subagent's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.
@@ -0,0 +1,7 @@
1
+ ---
2
+ name: in-your-own-words
3
+ description: "Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ Restate in your own words what you think the user's goals are and what problem they're trying to solve.
@@ -0,0 +1,31 @@
1
+ ---
2
+ name: interrogate
3
+ description: "Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Adversaries try to break a change or design, and only findings proven by a run survive."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Interrogate
8
+
9
+ Adversaries try to break a change or a design. A finding survives only when a run proves it. Report the findings. Do not apply fixes.
10
+
11
+ ## Frame
12
+
13
+ The scope is what the user names. Otherwise it is the branch diff from its merge base with the base branch, through the working tree. State the intent with the **in-your-own-words** skill, from the user's message, the commits, and the PR description. Ask the user when the intent is unclear.
14
+
15
+ ## Fan out
16
+
17
+ Run Phase A steps 3 and 4 and Phase B of the **arena** skill, with four changes. Read the `interrogate reviewers` line in place of `arena runners`. Copy the scope's uncommitted changes into each worktree. Spawn each adversary as `generalPurpose`. In place of the arena task and rationale, give each adversary the scope, the intent, and this brief:
18
+
19
+ > Break this change. Prove each finding with a run against the real code, such as a failing test, a repro script, or command output that shows the wrong behavior. For a design or plan, run a prototype or probe the current tree. Keep repros in your own worktree. Report each finding with a title, the exact command, the output it printed, and the output the intent requires. Leave out anything you did not run. That covers style, naming, structure, and risks that need a future change to matter. No findings is a valid result.
20
+
21
+ ## Verify
22
+
23
+ Verify each finding per arena Phase F by rerunning its command. Keep a finding when the output shows the failure and the failure breaks the intent. Drop the rest. Merge findings that share a root cause.
24
+
25
+ Skip arena Phases C, D, and E. Adversaries find different failures, so the verdict keeps every verified finding, not one adversary's list.
26
+
27
+ ## Output
28
+
29
+ - **Intent**: the restatement.
30
+ - **Findings**: for each verified finding, the command, its output, how it breaks the intent, and the adversaries that found it. Say "no verified findings" when none survive.
31
+ - **Dropped**: for each adversary, the count of dropped findings and why.
@@ -0,0 +1,43 @@
1
+ ---
2
+ name: ketchup
3
+ description: "Catch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /ketchup."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Ketchup
8
+
9
+ Catch the user up on what changed in this chat since the last message they wrote before `/ketchup`, and help them understand each change, not only where it stands. Then lay out every call waiting on them so they can make it from your reply alone. Notifications and subagent results are not their messages. Assume the user remembers their last message and nothing after it.
10
+
11
+ Use [`/bro`](../bro/SKILL.md)'s voice, not its task: plain words, short sentences, no jargon, like one person catching up another. Say what changed for the user, not how you did it. Say "the tests pass", not "CI is green". Leave out hashes, file paths, commands, build numbers, and test counts unless the user needs one to act. Call each PR, branch, or agent by a name the user would know, not by a label you invented. If a fact needs context to make sense, give the context or leave the fact out.
12
+
13
+ ## Gather what changed
14
+
15
+ Keep this turn read-only. Make visuals only from what you already have: do not change code, start an app or a job, or post anything. Collect your own work since that message, reports from subagents, and messages from anyone else in this chat. Check the current state of each PR, CI run, or agent this chat touched. Check each number you will show against the facts it comes from, and say so when you correct one.
16
+
17
+ An action item is a call or step only the user can take, such as a product choice, an approval, an irreversible action, or access you lack. Include any still waiting on the user, even one raised before their last message. Work you can still do yourself is not an action item. Never make up a call to fill the reply. A step the user did not ask for and the work does not need is not an action item, unless it is irreversible and waiting on the user: give it one line and no visual.
18
+
19
+ One call can cover many items, such as each PR in a set awaiting merge. For each item, collect its link, what it changes for users, the evidence behind your pick, its risk, and your pick. Write "unknown" for a fact the call needs that you do not know. Leave out a link you do not have.
20
+
21
+ ## Write the reply
22
+
23
+ Spend words on the calls, not on the story. Keep what happened under 100 words, not counting pictures, and shorter when less happened. Leave out work that changed nothing for the user. Give each item about 30 words. The reply grows with the number of items: two items need well under 150 words in all, not counting pictures, and thirty need far more. Never cut items or shrink them to stay under a word count: no count in place of a list, and no link in place of an item. A link can add depth, but the reply alone must be enough to decide.
24
+
25
+ Open with one short sentence that names what waits on the user, or says nothing does. The action items give the detail. If nothing happened and nothing waits on the user, say so and stop.
26
+
27
+ Then show what happened, pictures first. Embed inline the screenshots and videos the work produced, then any diagram that explains a change. Then sum up in one short bullet per thing the user asked for: what came of it, and whether it is done, still running, failed, or not checked. Write each line the way you would say it out loud: "Search was slow from a missing index", not "Search review: done" or "Slow search: missing index". Name any bug found and fixed on the way. Each line must stay true when read alone. Never mark something done that still waits on the user, and leave out anything the action items say. Under the summary, give at most three short lines that change what the user knows or must do. Then name in one line any work left that you can do yourself.
28
+
29
+ Then list the action items. Ask the call the user owns, such as merge, approve, or pick, and give your pick. A step you would take first goes in your pick. So does anything that must happen first, and anything that cannot be undone. Give the number or link of each PR, issue, or agent a call is about, also in a call between options.
30
+
31
+ Fit the shape to the call. A call about one item is one bullet: the call, your pick, what it changes for users, the evidence behind your pick, and its risk, with the item named once. When items share a call, write the call and your pick once, then give each item its own bullet, riskiest first: its link and name, what it changes for users, the evidence behind your pick, and its risk. Name an item's pick only where it differs from the call's. Give each item's risk even when it is low, such as "Low risk: only the colors change." Say what waiting costs only when it is more than a delay, such as a deadline or lost data.
32
+
33
+ For a call between options, give every option the work weighed, each with what it gets the user and what it costs, and the current state when there is one. Those costs are the call's risk, so add no separate risk line. When the screenshots above show the options, write each option's gain and cost under its screenshot.
34
+
35
+ ## Visuals
36
+
37
+ A visual is a picture: a screenshot, a video, a Mermaid diagram, a chart or diagram from `/visualize`, or a generated image. A Markdown table is not a visual, even with before and after columns.
38
+
39
+ When something is easier to grasp as a picture than as sentences, draw it: how a design or system works, a PR stack or dependency chain with each PR's state, a before and after of a fix, or options side by side. Never draw a status list, a list of action items, or boxes with nothing connecting them. Never give a fact twice, in text or across visuals.
40
+
41
+ Keep each visual small enough to read at a glance: at most six boxes, with at most eight words in each. Write labels as plain words a person would say, not tags like "Tests: pass". A fact that needs a sentence belongs in the text, or nowhere.
42
+
43
+ Embed screenshots and videos inline when the change is visible, not only as links. If a visible change has none, mark its summary line "No screenshot yet," and say there what changed on screen. Draw diagrams and charts from facts you have: a Mermaid diagram for how things connect and a `/visualize` chart for numbers. Never invent a number, and never draw or generate a picture of a screen you did not capture. Link only artifacts that exist.
@@ -0,0 +1,29 @@
1
+ ---
2
+ name: ketchup-video
3
+ description: "Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Ketchup video
8
+
9
+ Follow [`/ketchup`](../ketchup/SKILL.md), but show what happened in a short subtitled video instead of its summary and visuals. Its window starts at the last message the user wrote before `/ketchup-video`, not before any earlier `/ketchup`. Writing and rendering the video, outside the repo, is the one exception to its read-only rule. The reply is ketchup's opening sentence, the embedded video, one line naming any work left that you can do yourself, and the action items. When the video shows a call's options, call each option by the name the video gives it. If the render fails, say so in one line and give only the calls.
10
+
11
+ ## Slides
12
+
13
+ Use the screenshots, recordings, diffs, and data the work produced, not the chat's prose about them. Before you draw, write the one sentence the user should leave with and one line per slide. Drop each slide that does not change what the user knows. Use at most 10 slides, and fewer is better. Neither note goes in the reply.
14
+
15
+ Each slide makes one point. Build the slides on one picture and change it from slide to slide, rather than cut to an unrelated one. A color or shape means the same thing on every slide. Show the work in pictures, such as how a system works, a PR stack with each PR's state, a before and after of a fix, or options side by side. Point at what changed with arrows, highlights, and motion. A slide is never a bullet list, a status list, a table, or boxes with nothing connecting them.
16
+
17
+ Keep text to the minimum. Put each label on the thing it names, in plain words a person would say, not tags like "Tests: pass". Never caption what a picture shows, and never give a fact twice, across slides or in the text under them.
18
+
19
+ Show what came of each thing the user asked for, and whether it is done, still running, failed, or not checked. Never show something done that still waits on the user. Show any bug found and fixed on the way. If a visible change has no screenshot, say so on its slide and name what changed on screen. Draw only from facts you have. Never invent a number, and never draw a screen you did not capture.
20
+
21
+ ## Subtitles
22
+
23
+ Give each slide one short subtitle line, about ten words, that says its point the way you would tell the user, from only what that slide shows. Say what the picture means rather than read out its labels. Put the subtitle in a strip below the slide, the same height on every slide and empty except for the subtitle, so it never covers the slide. Set it small, but readable when the video plays at chat size.
24
+
25
+ ## Render
26
+
27
+ Render one silent landscape video, such as an mp4, with motion between slides. Every frame is the slide itself, edge to edge, above its subtitle strip. Make the frames from the slides, never by recording a screen, and burn each subtitle into its slide's frames so it stays on screen for the slide's whole hold. The hold is the time a slide is fully on screen, not counting the motion into or out of it. Hold each slide long enough to read the words it adds, at least one second for each three words. A slide adds its subtitle and each word that was not on the slide before it, including a label it changes. The first slide adds all its words. Words inside a screenshot do not count.
28
+
29
+ Before you embed the video, check the rendered file. Look at one frame from each slide at chat size, and check that its subtitle is readable and covers nothing. Measure each hold by matching the file's frames to the slide, not with a still-frame detector, which counts the faint ends of a fade as still. Count the words each slide adds against its measured hold. Fix any slide you cannot read in that time, render again, and check again.
@@ -0,0 +1,58 @@
1
+ ---
2
+ name: maintain-formal-verification-skill
3
+ description: "Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, \"is the model still true to the code\", or after merges and refactors that touched verified code without rechecking it."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Maintain a formal verification skill
8
+
9
+ A formal check proves a property of what it describes. When the code changes and the verification does not, the check can keep passing while it describes code that no longer exists. That pass is the dangerous case, because it looks like a proof. This skill is the upkeep loop for a verify skill that `/create-formal-verification-skill` generated, or for any project-local skill that runs a model checker, prover, or code-level verifier against named code. The project-local skill handles a change that an agent makes while it uses that skill. This skill handles the changes that skipped it: merges, edits made without the skill, and drift that builds up across many commits.
10
+
11
+ ## Outcomes
12
+
13
+ Give each check one outcome, and say which:
14
+
15
+ - **in sync**: no change since the last sync alters what the check describes, and the check passes.
16
+ - **updated**: the code changed, the verification now describes the new code, and the check passes.
17
+ - **bug**: the verification describes the current code, and the code breaks the property. This is a finding about the code. It is not drift.
18
+ - **blocked**: the check could not be brought back in line or could not run. Say exactly why.
19
+
20
+ A check can be both updated and bug: the update makes the verification describe the code again, and then the property fails on it.
21
+
22
+ ## Edit scope
23
+
24
+ Edit only the verification: models, harnesses, property files, and the verify skill itself. Never edit product code during a run, unless the user asks you to. When a property fails on the current code, do not weaken the property or the model to make it pass. Report the failure.
25
+
26
+ ## Pass
27
+
28
+ 1. **Find the checks.** A verify skill has no fixed name, so find it by what it does: a project skill that runs a model checker, a prover, or another verifier against named code. Read each one you find, or the one the user named. For each check, collect the property, the code it covers, the bounds and assumptions, the command that runs it, and the commit where it was last confirmed to describe the code. If no verify skill exists, stop and point at `/create-formal-verification-skill`. If the skill does not record a sync commit, use the last commit that changed the verification files, and say that you did.
29
+
30
+ 2. **Run it as it is.** Run each check once before you change anything, and record the result. A pass here does not tell you that the code is correct. It tells you that the old description still holds. A failure here can be drift or a bug. Do not decide which until step 5.
31
+
32
+ 3. **Read every change to covered code.** Diff the covered files from the sync commit to the current commit, and read each commit message. Also look for code that moved: a covered function that is renamed, split, or moved to another file is still covered code. Also look for new code that touches the state that a check guards, such as a new function that writes the same fields. For each change, decide which of these it is:
33
+ - **No effect.** The change does not alter anything the verification describes, such as formatting, comments, or code paths that the verification does not cover. Check this against the model or harness, not against the commit message.
34
+ - **The verification no longer describes the code.** A step that was one indivisible action is now two, a branch was added or removed, a check moved, a new path reaches the guarded state, or a value now has a different range. The model or harness must change.
35
+ - **The promise changed on purpose.** The change alters what the code promises, and evidence in the change says that this is intended: the doc comment, the tests, the changelog, or the commit message. The property must change, and you must cite that evidence.
36
+ - **The promise may be broken.** The code changed, and no evidence says that the promise changed. Treat a failure that follows as a bug candidate.
37
+
38
+ 4. **Update from the code, not from the result.** Change the model or harness so that each changed part again points to code that a reviewer can open, and keep one indivisible step in the code as one step in the verification. Write the update from the code before you rerun, and do not shape it by what makes the check pass. Change a property only for a promise that changed on purpose. Write down the old wording, the new wording, and the evidence. Keep the bounds unless the change makes them wrong. If you must reduce a bound, say so in the report.
39
+
40
+ 5. **Rerun and judge each result.**
41
+ - **Pass:** the check can now pass on a description that has lost the ability to fail. Break the new code the way the property guards against, such as removing a new check or reordering a new step, and confirm that the check catches it. Then drop the break.
42
+ - **Fail:** replay the counterexample against the real code, step by step. If a step cannot happen in the code, the verification is wrong. Fix the verification, and say what was wrong. If every step can happen, it is a bug. Name the commit that introduced it, tell the counterexample as a sequence of steps in the code's own words, and state the harm in one sentence. If a cheap test or reproduction against the real code shows the bug, add it to the report as evidence. Do not commit it to the product code.
43
+
44
+ 6. **Update the verify skill.** Update the code that each check covers, the commands, the bounds, the assumptions, and the sync commit. Set the sync commit to the commit that you checked. Do not move the sync commit for a blocked check, and say so in the report. Then follow the verify skill once as the next agent would, so that you know its steps still run.
45
+
46
+ ## Report
47
+
48
+ Tell the user, for each check:
49
+
50
+ - the outcome, and the commits that you read;
51
+ - what changed in the verification and why, with a short reason for each change: the code changed shape, or the promise changed on purpose (with the evidence);
52
+ - the rerun result, and the break that you used to show the updated check can still fail;
53
+ - each bug, in plain words: the counterexample as steps in the code's words, the harm, and the commit that introduced it;
54
+ - what the verification still does not cover, including new code that it should cover and does not.
55
+
56
+ Say outright which failures were drift in the verification and which were bugs in the code. For a check that passed before you updated it and fails after, say that the old pass was on a stale description.
57
+
58
+ Put the verification updates in a change of their own, separate from any product fix.
@@ -0,0 +1,39 @@
1
+ ---
2
+ name: maintain-verification-skill
3
+ description: "Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or \"audit the verify skill\"."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Maintain a verification skill
8
+
9
+ A feature map rots the moment the app changes. This skill is the upkeep loop for a skill generated by `/create-verification-skill` (or any project-local verification skill with a feature map). The unit of rigor is the feature, not every sentence: cover every feature file from source and exercise every feature live, without terminalising every bullet.
10
+
11
+ ## Outcomes
12
+
13
+ Pick one, and say which:
14
+
15
+ - **clean** — every feature got source and live coverage; nothing worth shipping. No branch, no PR.
16
+ - **changed** — one PR ships proven doc, harness, or map corrections.
17
+ - **blocked** — coverage could not finish or a proven fix could not ship safely. Say exactly what blocked it.
18
+
19
+ ## Edit scope
20
+
21
+ Only edit the verification skill's own directory (its SKILL.md, features/, and any harness scripts it owns). Never edit product code during a run: a behavior the map describes that the app no longer does is either doc drift (fix the map) or a product regression (report it, don't paper over it in docs).
22
+
23
+ ## Pass
24
+
25
+ 0. **Locate the target.** Find the verification skill to maintain: the project-local skill whose body has launch/drive sections and a feature map (usually `.cursor/skills/verify-*/`). Several candidates → ask which one; none → stop and point at `/create-verification-skill` instead of inventing a target.
26
+
27
+ 1. **Index hygiene.** Read the feature map README and glob its sibling files. Fix missing, extra, duplicate, or dead entries. Lightweight; no generated inventory.
28
+
29
+ 2. **Source wave.** One read-only subagent per feature file, launched concurrently. Each explains "how does this user-facing feature work?" from source, flags likely doc drift with citations, and returns one concise live-verification recipe. Children never drive the app and never edit files. Return shape: feature summary / source entry points / likely drift or none / one recipe.
30
+
31
+ 3. **Reconcile.** Every feature file has a returned summary. Merge overlapping recipes into as few app states as practical. Spot-check cited drift; don't re-prove clean claims. Sweep recent churn for user-facing surfaces missing from the map — require a concrete source path before calling one missing.
32
+
33
+ 4. **Live pass.** Required even when source looks clean. The coordinator owns all driving; follow the verification skill's own launch model — one long-lived instance driven serially for servers and UIs, or a fresh isolated session per drive for short-lived CLIs (the skill's Launch section decides, not this one). Exercise every feature at least once, and hold three invariants the whole pass, whatever the failure: (1) never drive an instance you haven't health-checked since it last did something surprising — doctor before first drive, doctor on each fresh session where sessions are the unit, doctor again after any failed drive, and where doctor can't see the failure (a wedged UI state on a healthy process), reset to a known state or relaunch rather than hoping; (2) evidence captured so far survives every cleanup, checked at its named location, not assumed; (3) nothing a drive started outlives that drive's usefulness — failed-iteration residue is cleaned whether the session is stuck, exited, or shared (for a shared instance, clean the residue, not the instance). A doctor failure caused by skill drift is drift: fix it under edit scope and retry once — restart whatever the fix invalidated, nothing more — before calling the pass `blocked`. A feature that can't be reached is `verified-unreachable` only with the concrete prerequisite (auth, entitlement, OS, external state) and the route attempted; if the map omits that prerequisite, that's drift. Any harness fix from triage gets re-driven live before it ships. Final teardown happens after the last drive of the run — including those re-proofs — so nothing outlives the run (evidence stays, per the skill).
34
+
35
+ 5. **Triage.** Wrong or missing user-POV description → doc drift, fix it. Working behavior the harness can't drive → harness gap, fix it; a harness fix follows the same helpers rule as generation (scripts executable, invocation documented in the skill body). App behavior that's actually broken → product gap; record it for the user, keep it out of this PR.
36
+
37
+ 6. **Ship or stop.** For changed: one PR of proven corrections, re-read every changed file first. For clean or blocked: no PR, report the outcome and the coverage honestly.
38
+
39
+ Keep concise run notes (features covered, unreachable prerequisites, confirmed drift, outcome) in a scratch location; don't commit them.