workflow-ai 1.0.62 → 1.0.64

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 (505) hide show
  1. package/README.md +61 -0
  2. package/agent-templates/CLAUDE.md.tpl +2 -0
  3. package/agent-templates/QWEN.md.tpl +2 -0
  4. package/configs/config.yaml +134 -0
  5. package/configs/pipeline.yaml +884 -0
  6. package/configs/ticket-movement-rules.yaml +80 -0
  7. package/package.json +2 -1
  8. package/src/global-dir.mjs +25 -1
  9. package/src/init.mjs +5 -4
  10. package/src/lib/agent-spawner.mjs +338 -0
  11. package/src/runner.mjs +15 -14
  12. package/src/scripts/get-next-test-id.js +94 -0
  13. package/src/scripts/migrate-backlog-to-tests.js +406 -0
  14. package/src/scripts/run-skill-tests.js +1703 -0
  15. package/src/scripts/scan-fixtures-for-secrets.js +248 -0
  16. package/src/scripts/tests/timeout-cascade.test.js +28 -0
  17. package/src/skills/analyze-report/README.md +44 -0
  18. package/src/skills/analyze-report/SKILL.md +121 -0
  19. package/src/skills/analyze-report/algorithms/progress-assessment.md +108 -0
  20. package/src/skills/analyze-report/knowledge/analysis-frameworks.md +66 -0
  21. package/src/skills/analyze-report/knowledge/report-structure.md +61 -0
  22. package/src/skills/analyze-report/scripts/calc-plan-metrics.js +234 -0
  23. package/src/skills/analyze-report/templates/analysis-report.md +80 -0
  24. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/claude-sonnet/trial-1.md +69 -0
  25. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/claude-sonnet/trial-2.md +103 -0
  26. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/claude-sonnet/trial-3.md +99 -0
  27. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/judge.json +163 -0
  28. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-deepseek/trial-1.md +89 -0
  29. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-deepseek/trial-2.md +88 -0
  30. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-deepseek/trial-3.md +100 -0
  31. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-glm/trial-1.md +77 -0
  32. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-glm/trial-2.md +64 -0
  33. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-glm/trial-3.md +110 -0
  34. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-minimax/trial-1.md +74 -0
  35. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-minimax/trial-2.md +38 -0
  36. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-minimax/trial-3.md +61 -0
  37. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/meta.json +115 -0
  38. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001-evidence-from-log.yaml +60 -0
  39. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/claude-sonnet/trial-1.md +90 -0
  40. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/claude-sonnet/trial-2.md +89 -0
  41. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/claude-sonnet/trial-3.md +77 -0
  42. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/judge.json +163 -0
  43. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-deepseek/trial-1.md +84 -0
  44. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-deepseek/trial-2.md +77 -0
  45. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-deepseek/trial-3.md +89 -0
  46. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-glm/trial-1.md +103 -0
  47. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-glm/trial-2.md +103 -0
  48. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-glm/trial-3.md +103 -0
  49. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-minimax/trial-1.md +93 -0
  50. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-minimax/trial-2.md +93 -0
  51. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-minimax/trial-3.md +86 -0
  52. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/meta.json +115 -0
  53. package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002-result-block-format.yaml +44 -0
  54. package/src/skills/analyze-report/tests/fixtures/REPORT-002-incorrect-attribution.md +27 -0
  55. package/src/skills/analyze-report/tests/fixtures/pipeline-2026-04-06_qa-001-skip.log +32 -0
  56. package/src/skills/analyze-report/tests/index.yaml +25 -0
  57. package/src/skills/analyze-report/tests/rubrics/evidence-from-log.md +22 -0
  58. package/src/skills/analyze-report/tests/rubrics/result-block-format.md +22 -0
  59. package/src/skills/analyze-report/workflows/progress.md +158 -0
  60. package/src/skills/analyze-report/workflows/retrospective.md +143 -0
  61. package/src/skills/coach/README.md +43 -0
  62. package/src/skills/coach/SKILL.md +166 -0
  63. package/src/skills/coach/SKILL.md.legacy +157 -0
  64. package/src/skills/coach/algorithms/gap-analysis.md +69 -0
  65. package/src/skills/coach/algorithms/improvement-prioritization.md +62 -0
  66. package/src/skills/coach/algorithms/skill-scoring.md +80 -0
  67. package/src/skills/coach/knowledge/audit-applied-changes-clean.txt +11 -0
  68. package/src/skills/coach/knowledge/backlog-management.md +67 -0
  69. package/src/skills/coach/knowledge/backlog-management.md.legacy +90 -0
  70. package/src/skills/coach/knowledge/common-antipatterns.md +76 -0
  71. package/src/skills/coach/knowledge/prompt-engineering.md +45 -0
  72. package/src/skills/coach/knowledge/shared-knowledge-guide.md +44 -0
  73. package/src/skills/coach/knowledge/skill-anatomy.md +49 -0
  74. package/src/skills/coach/knowledge/test-authorship.md +141 -0
  75. package/src/skills/coach/templates/audit-report.md +39 -0
  76. package/src/skills/coach/templates/coach-backlog-init.yaml +14 -0
  77. package/src/skills/coach/templates/coach-backlog-init.yaml.legacy +10 -0
  78. package/src/skills/coach/templates/improvement-plan.md +42 -0
  79. package/src/skills/coach/templates/new-skill.md +95 -0
  80. package/src/skills/coach/tests/cases/TC-COACH-001/current/claude-sonnet/trial-1.md +58 -0
  81. package/src/skills/coach/tests/cases/TC-COACH-001/current/claude-sonnet/trial-2.md +65 -0
  82. package/src/skills/coach/tests/cases/TC-COACH-001/current/claude-sonnet/trial-3.md +58 -0
  83. package/src/skills/coach/tests/cases/TC-COACH-001/current/judge.json +151 -0
  84. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-deepseek/trial-1.md +46 -0
  85. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-deepseek/trial-2.md +0 -0
  86. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-deepseek/trial-3.md +75 -0
  87. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-glm/trial-1.md +81 -0
  88. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-glm/trial-2.md +101 -0
  89. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-glm/trial-3.md +91 -0
  90. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-minimax/trial-1.md +48 -0
  91. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-minimax/trial-2.md +30 -0
  92. package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-minimax/trial-3.md +55 -0
  93. package/src/skills/coach/tests/cases/TC-COACH-001/current/meta.json +95 -0
  94. package/src/skills/coach/tests/cases/TC-COACH-001-evidence-based-temporal-diagram.yaml +53 -0
  95. package/src/skills/coach/tests/cases/TC-COACH-002/current/claude-sonnet/trial-1.md +46 -0
  96. package/src/skills/coach/tests/cases/TC-COACH-002/current/claude-sonnet/trial-2.md +50 -0
  97. package/src/skills/coach/tests/cases/TC-COACH-002/current/claude-sonnet/trial-3.md +48 -0
  98. package/src/skills/coach/tests/cases/TC-COACH-002/current/judge.json +151 -0
  99. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-deepseek/trial-1.md +0 -0
  100. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-deepseek/trial-2.md +37 -0
  101. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-deepseek/trial-3.md +30 -0
  102. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-glm/trial-1.md +23 -0
  103. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-glm/trial-2.md +29 -0
  104. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-glm/trial-3.md +35 -0
  105. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-minimax/trial-1.md +13 -0
  106. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-minimax/trial-2.md +19 -0
  107. package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-minimax/trial-3.md +33 -0
  108. package/src/skills/coach/tests/cases/TC-COACH-002/current/meta.json +95 -0
  109. package/src/skills/coach/tests/cases/TC-COACH-002-root-cause-first.yaml +57 -0
  110. package/src/skills/coach/tests/fixtures/pipeline-2026-04-06_id-collision.log +77 -0
  111. package/src/skills/coach/tests/index.yaml +29 -0
  112. package/src/skills/coach/tests/rubrics/calibration/evidence-based-bad.md +13 -0
  113. package/src/skills/coach/tests/rubrics/calibration/evidence-based-good.md +29 -0
  114. package/src/skills/coach/tests/rubrics/evidence-based.md +26 -0
  115. package/src/skills/coach/tests/rubrics/root-cause-first.md +21 -0
  116. package/src/skills/coach/workflows/analyze.md +79 -0
  117. package/src/skills/coach/workflows/analyze.md.legacy +64 -0
  118. package/src/skills/coach/workflows/audit.md +74 -0
  119. package/src/skills/coach/workflows/audit.md.legacy +59 -0
  120. package/src/skills/coach/workflows/create.md +80 -0
  121. package/src/skills/coach/workflows/create.md.legacy +67 -0
  122. package/src/skills/coach/workflows/improve.md +71 -0
  123. package/src/skills/coach/workflows/improve.md.legacy +60 -0
  124. package/src/skills/coach/workflows/research.md +55 -0
  125. package/src/skills/coach/workflows/review.md +52 -0
  126. package/src/skills/coach/workflows/review.md.legacy +48 -0
  127. package/src/skills/coach/workflows/test.md +97 -0
  128. package/src/skills/create-plan/README.md +39 -0
  129. package/src/skills/create-plan/SKILL.md +104 -0
  130. package/src/skills/create-plan/algorithms/risk-assessment.md +73 -0
  131. package/src/skills/create-plan/knowledge/plan-completeness.md +67 -0
  132. package/src/skills/create-plan/knowledge/plan-lifecycle.md +33 -0
  133. package/src/skills/create-plan/knowledge/task-verification-pairs.md +151 -0
  134. package/src/skills/create-plan/scripts/validate-completeness.js +182 -0
  135. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/claude-sonnet/trial-1.md +5 -0
  136. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/claude-sonnet/trial-2.md +39 -0
  137. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/claude-sonnet/trial-3.md +35 -0
  138. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/judge.json +167 -0
  139. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-deepseek/trial-1.md +5 -0
  140. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-deepseek/trial-2.md +10 -0
  141. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-deepseek/trial-3.md +5 -0
  142. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-glm/trial-1.md +26 -0
  143. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-glm/trial-2.md +86 -0
  144. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-glm/trial-3.md +5 -0
  145. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-minimax/trial-1.md +11 -0
  146. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-minimax/trial-2.md +15 -0
  147. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-minimax/trial-3.md +14 -0
  148. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/meta.json +119 -0
  149. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001-validate-completeness.yaml +41 -0
  150. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/claude-sonnet/trial-1.md +25 -0
  151. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/claude-sonnet/trial-2.md +30 -0
  152. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/claude-sonnet/trial-3.md +37 -0
  153. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/judge.json +164 -0
  154. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-deepseek/trial-1.md +3 -0
  155. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-deepseek/trial-2.md +11 -0
  156. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-deepseek/trial-3.md +13 -0
  157. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-glm/trial-1.md +44 -0
  158. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-glm/trial-2.md +5 -0
  159. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-glm/trial-3.md +49 -0
  160. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-minimax/trial-1.md +6 -0
  161. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-minimax/trial-2.md +11 -0
  162. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-minimax/trial-3.md +16 -0
  163. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/meta.json +116 -0
  164. package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002-task-granularity.yaml +39 -0
  165. package/src/skills/create-plan/tests/index.yaml +25 -0
  166. package/src/skills/create-plan/tests/rubrics/task-granularity.md +21 -0
  167. package/src/skills/create-plan/tests/rubrics/validate-completeness.md +21 -0
  168. package/src/skills/create-plan/workflows/create.md +136 -0
  169. package/src/skills/create-report/README.md +40 -0
  170. package/src/skills/create-report/SKILL.md +73 -0
  171. package/src/skills/create-report/algorithms/metric-calculation.md +93 -0
  172. package/src/skills/create-report/knowledge/report-metrics.md +82 -0
  173. package/src/skills/create-report/scripts/calc-metrics.js +383 -0
  174. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/claude-sonnet/trial-1.md +25 -0
  175. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/claude-sonnet/trial-2.md +26 -0
  176. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/claude-sonnet/trial-3.md +28 -0
  177. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/judge.json +163 -0
  178. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-deepseek/trial-1.md +4 -0
  179. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-deepseek/trial-2.md +3 -0
  180. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-deepseek/trial-3.md +6 -0
  181. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-glm/trial-1.md +8 -0
  182. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-glm/trial-2.md +12 -0
  183. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-glm/trial-3.md +7 -0
  184. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-minimax/trial-1.md +12 -0
  185. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-minimax/trial-2.md +22 -0
  186. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-minimax/trial-3.md +13 -0
  187. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/meta.json +115 -0
  188. package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001-root-cause-attribution.yaml +57 -0
  189. package/src/skills/create-report/tests/index.yaml +20 -0
  190. package/src/skills/create-report/tests/rubrics/root-cause-attribution.md +21 -0
  191. package/src/skills/create-report/workflows/standard.md +175 -0
  192. package/src/skills/decompose-gaps/README.md +39 -0
  193. package/src/skills/decompose-gaps/SKILL.md +78 -0
  194. package/src/skills/decompose-gaps/algorithms/scope-check.md +110 -0
  195. package/src/skills/decompose-gaps/knowledge/scope-validation.md +65 -0
  196. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/claude-sonnet/trial-1.md +49 -0
  197. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/claude-sonnet/trial-2.md +56 -0
  198. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/claude-sonnet/trial-3.md +39 -0
  199. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/judge.json +164 -0
  200. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-deepseek/trial-1.md +25 -0
  201. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-deepseek/trial-2.md +11 -0
  202. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-deepseek/trial-3.md +26 -0
  203. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-glm/trial-1.md +19 -0
  204. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-glm/trial-2.md +5 -0
  205. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-glm/trial-3.md +28 -0
  206. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-minimax/trial-1.md +23 -0
  207. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-minimax/trial-2.md +27 -0
  208. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-minimax/trial-3.md +25 -0
  209. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/meta.json +116 -0
  210. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001-scope-exclusion.yaml +46 -0
  211. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/claude-sonnet/trial-1.md +32 -0
  212. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/claude-sonnet/trial-2.md +20 -0
  213. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/claude-sonnet/trial-3.md +26 -0
  214. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/judge.json +164 -0
  215. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-deepseek/trial-1.md +7 -0
  216. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-deepseek/trial-2.md +16 -0
  217. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-deepseek/trial-3.md +7 -0
  218. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-glm/trial-1.md +5 -0
  219. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-glm/trial-2.md +11 -0
  220. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-glm/trial-3.md +13 -0
  221. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-minimax/trial-1.md +13 -0
  222. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-minimax/trial-2.md +12 -0
  223. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-minimax/trial-3.md +5 -0
  224. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/meta.json +116 -0
  225. package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002-glob-before-write.yaml +36 -0
  226. package/src/skills/decompose-gaps/tests/index.yaml +25 -0
  227. package/src/skills/decompose-gaps/tests/rubrics/glob-before-write.md +21 -0
  228. package/src/skills/decompose-gaps/tests/rubrics/scope-exclusion.md +21 -0
  229. package/src/skills/decompose-gaps/workflows/decompose.md +120 -0
  230. package/src/skills/decompose-plan/README.md +43 -0
  231. package/src/skills/decompose-plan/SKILL.md +87 -0
  232. package/src/skills/decompose-plan/algorithms/deduplication.md +101 -0
  233. package/src/skills/decompose-plan/knowledge/atomicity-checklist.md +113 -0
  234. package/src/skills/decompose-plan/knowledge/capabilities.md +44 -0
  235. package/src/skills/decompose-plan/knowledge/human-task-rules.md +67 -0
  236. package/src/skills/decompose-plan/knowledge/scope-guard-checklist.md +73 -0
  237. package/src/skills/decompose-plan/scripts/check-atomicity-limit.js +47 -0
  238. package/src/skills/decompose-plan/scripts/check-duplicates.js +323 -0
  239. package/src/skills/decompose-plan/scripts/verify-atomicity.js +408 -0
  240. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/claude-sonnet/trial-1.md +30 -0
  241. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/claude-sonnet/trial-2.md +36 -0
  242. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/claude-sonnet/trial-3.md +37 -0
  243. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/judge.json +163 -0
  244. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-deepseek/trial-1.md +20 -0
  245. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-deepseek/trial-2.md +17 -0
  246. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-deepseek/trial-3.md +28 -0
  247. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-glm/trial-1.md +114 -0
  248. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-glm/trial-2.md +137 -0
  249. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-glm/trial-3.md +188 -0
  250. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-minimax/trial-1.md +0 -0
  251. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-minimax/trial-2.md +32 -0
  252. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-minimax/trial-3.md +110 -0
  253. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/meta.json +115 -0
  254. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001-atomicity-no-1to1.yaml +56 -0
  255. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/claude-sonnet/trial-1.md +47 -0
  256. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/claude-sonnet/trial-2.md +54 -0
  257. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/claude-sonnet/trial-3.md +43 -0
  258. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/judge.json +163 -0
  259. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-deepseek/trial-1.md +15 -0
  260. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-deepseek/trial-2.md +5 -0
  261. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-deepseek/trial-3.md +12 -0
  262. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-glm/trial-1.md +34 -0
  263. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-glm/trial-2.md +30 -0
  264. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-glm/trial-3.md +35 -0
  265. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-minimax/trial-1.md +0 -0
  266. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-minimax/trial-2.md +31 -0
  267. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-minimax/trial-3.md +0 -0
  268. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/meta.json +115 -0
  269. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002-get-next-id-mandatory.yaml +44 -0
  270. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/claude-sonnet/trial-1.md +21 -0
  271. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/claude-sonnet/trial-2.md +38 -0
  272. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/claude-sonnet/trial-3.md +30 -0
  273. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/judge.json +163 -0
  274. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-deepseek/trial-1.md +31 -0
  275. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-deepseek/trial-2.md +35 -0
  276. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-deepseek/trial-3.md +48 -0
  277. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-glm/trial-1.md +167 -0
  278. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-glm/trial-2.md +62 -0
  279. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-glm/trial-3.md +174 -0
  280. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-minimax/trial-1.md +0 -0
  281. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-minimax/trial-2.md +0 -0
  282. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-minimax/trial-3.md +0 -0
  283. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/meta.json +115 -0
  284. package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003-verbatim-dod-transfer.yaml +42 -0
  285. package/src/skills/decompose-plan/tests/index.yaml +30 -0
  286. package/src/skills/decompose-plan/tests/rubrics/atomicity-no-1to1.md +21 -0
  287. package/src/skills/decompose-plan/tests/rubrics/get-next-id-mandatory.md +21 -0
  288. package/src/skills/decompose-plan/tests/rubrics/verbatim-dod-transfer.md +21 -0
  289. package/src/skills/decompose-plan/workflows/decompose.md +272 -0
  290. package/src/skills/deep-research/README.md +36 -0
  291. package/src/skills/deep-research/SKILL.md +106 -0
  292. package/src/skills/deep-research/algorithms/source-scoring.md +63 -0
  293. package/src/skills/deep-research/algorithms/synthesis.md +67 -0
  294. package/src/skills/deep-research/knowledge/data-validation.md +44 -0
  295. package/src/skills/deep-research/knowledge/perplexity-config.md +30 -0
  296. package/src/skills/deep-research/knowledge/research-methodology.md +54 -0
  297. package/src/skills/deep-research/knowledge/source-evaluation.md +33 -0
  298. package/src/skills/deep-research/scripts/perplexity-research.js +315 -0
  299. package/src/skills/deep-research/templates/brief-summary.md +25 -0
  300. package/src/skills/deep-research/templates/research-report.md +76 -0
  301. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/claude-haiku/trial-1.md +48 -0
  302. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/claude-haiku/trial-2.md +88 -0
  303. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/claude-haiku/trial-3.md +56 -0
  304. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/judge.json +163 -0
  305. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-free/trial-1.md +58 -0
  306. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-free/trial-2.md +249 -0
  307. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-free/trial-3.md +44 -0
  308. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm/trial-1.md +96 -0
  309. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm/trial-2.md +56 -0
  310. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm/trial-3.md +94 -0
  311. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm-air/trial-1.md +11 -0
  312. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm-air/trial-2.md +1 -0
  313. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm-air/trial-3.md +1 -0
  314. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/meta.json +115 -0
  315. package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001-self-check-url.yaml +58 -0
  316. package/src/skills/deep-research/tests/index.yaml +20 -0
  317. package/src/skills/deep-research/tests/rubrics/self-check-url.md +34 -0
  318. package/src/skills/deep-research/workflows/base-checklist.md +19 -0
  319. package/src/skills/deep-research/workflows/benchmark.md +38 -0
  320. package/src/skills/deep-research/workflows/competitor.md +44 -0
  321. package/src/skills/deep-research/workflows/custom.md +32 -0
  322. package/src/skills/deep-research/workflows/market.md +44 -0
  323. package/src/skills/deep-research/workflows/technology.md +40 -0
  324. package/src/skills/deep-research/workflows/trend.md +40 -0
  325. package/src/skills/execute-task/README.md +44 -0
  326. package/src/skills/execute-task/SKILL.md +292 -0
  327. package/src/skills/execute-task/algorithms/execution-strategy.md +136 -0
  328. package/src/skills/execute-task/knowledge/context-checkpoints.md +75 -0
  329. package/src/skills/execute-task/knowledge/ticket-structure.md +70 -0
  330. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/claude-haiku/trial-1.md +5 -0
  331. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/claude-haiku/trial-2.md +5 -0
  332. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/claude-haiku/trial-3.md +5 -0
  333. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/judge.json +124 -0
  334. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-free/trial-1.md +4 -0
  335. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-free/trial-2.md +4 -0
  336. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-free/trial-3.md +4 -0
  337. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-glm-air/trial-1.md +4 -0
  338. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-glm-air/trial-2.md +4 -0
  339. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-glm-air/trial-3.md +11 -0
  340. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/meta.json +89 -0
  341. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001-no-ticket-creation.yaml +48 -0
  342. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/claude-haiku/trial-1.md +5 -0
  343. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/claude-haiku/trial-2.md +6 -0
  344. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/claude-haiku/trial-3.md +5 -0
  345. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/judge.json +124 -0
  346. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-free/trial-1.md +4 -0
  347. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-free/trial-2.md +4 -0
  348. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-free/trial-3.md +8 -0
  349. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-glm-air/trial-1.md +9 -0
  350. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-glm-air/trial-2.md +26 -0
  351. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-glm-air/trial-3.md +4 -0
  352. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/meta.json +89 -0
  353. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002-no-duplicate-dod.yaml +44 -0
  354. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/claude-haiku/trial-1.md +5 -0
  355. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/claude-haiku/trial-2.md +5 -0
  356. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/claude-haiku/trial-3.md +5 -0
  357. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/judge.json +46 -0
  358. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/meta.json +37 -0
  359. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003-verification-proportionality.yaml +46 -0
  360. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/claude-haiku/trial-1.md +18 -0
  361. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/claude-haiku/trial-2.md +16 -0
  362. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/claude-haiku/trial-3.md +14 -0
  363. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/judge.json +124 -0
  364. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-free/trial-1.md +5 -0
  365. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-free/trial-2.md +5 -0
  366. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-free/trial-3.md +1 -0
  367. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-glm-air/trial-1.md +8 -0
  368. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-glm-air/trial-2.md +5 -0
  369. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-glm-air/trial-3.md +4 -0
  370. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/meta.json +89 -0
  371. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004-no-foreign-ticket-edit.yaml +50 -0
  372. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/claude-haiku/trial-1.md +5 -0
  373. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/claude-haiku/trial-2.md +5 -0
  374. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/claude-haiku/trial-3.md +5 -0
  375. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/judge.json +124 -0
  376. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-free/trial-1.md +15 -0
  377. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-free/trial-2.md +4 -0
  378. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-free/trial-3.md +5 -0
  379. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-glm-air/trial-1.md +11 -0
  380. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-glm-air/trial-2.md +11 -0
  381. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-glm-air/trial-3.md +4 -0
  382. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/meta.json +89 -0
  383. package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005-ticket-fields-updated.yaml +39 -0
  384. package/src/skills/execute-task/tests/fixtures/IMPL-902-create-file.md +41 -0
  385. package/src/skills/execute-task/tests/fixtures/IMPL-904-current-task.md +40 -0
  386. package/src/skills/execute-task/tests/fixtures/IMPL-906-fill-ticket.md +42 -0
  387. package/src/skills/execute-task/tests/fixtures/QA-901-button-click.md +41 -0
  388. package/src/skills/execute-task/tests/fixtures/QA-903-visual-figma.md +40 -0
  389. package/src/skills/execute-task/tests/fixtures/TASK-905-done-with-typo.md +36 -0
  390. package/src/skills/execute-task/tests/index.yaml +39 -0
  391. package/src/skills/execute-task/tests/rubrics/no-duplicate-dod.md +22 -0
  392. package/src/skills/execute-task/tests/rubrics/no-foreign-ticket-edit.md +20 -0
  393. package/src/skills/execute-task/tests/rubrics/no-ticket-creation.md +21 -0
  394. package/src/skills/execute-task/tests/rubrics/ticket-fields-updated.md +23 -0
  395. package/src/skills/execute-task/tests/rubrics/verification-proportionality.md +22 -0
  396. package/src/skills/execute-task/workflows/execute.md +104 -0
  397. package/src/skills/manual-testing/README.md +63 -0
  398. package/src/skills/manual-testing/SKILL.md +174 -0
  399. package/src/skills/manual-testing/algorithms/blocked-tool-strategy.md +74 -0
  400. package/src/skills/manual-testing/algorithms/bug-severity.md +73 -0
  401. package/src/skills/manual-testing/algorithms/mcp-budget.md +97 -0
  402. package/src/skills/manual-testing/algorithms/test-prioritization.md +69 -0
  403. package/src/skills/manual-testing/knowledge/browser-extension-testing.md +102 -0
  404. package/src/skills/manual-testing/knowledge/browser-tools.md +114 -0
  405. package/src/skills/manual-testing/knowledge/desktop-tools-advanced.md +92 -0
  406. package/src/skills/manual-testing/knowledge/desktop-tools-core.md +76 -0
  407. package/src/skills/manual-testing/knowledge/sandbox-advanced.md +83 -0
  408. package/src/skills/manual-testing/knowledge/sandbox-core.md +67 -0
  409. package/src/skills/manual-testing/knowledge/stateful-edge-cases.md +69 -0
  410. package/src/skills/manual-testing/knowledge/test-case-design.md +107 -0
  411. package/src/skills/manual-testing/knowledge/testing-types.md +45 -0
  412. package/src/skills/manual-testing/templates/bug-report.md +52 -0
  413. package/src/skills/manual-testing/templates/test-case.md +34 -0
  414. package/src/skills/manual-testing/templates/test-plan.md +97 -0
  415. package/src/skills/manual-testing/templates/test-session-report.md +56 -0
  416. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/claude-sonnet/trial-1.md +21 -0
  417. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/claude-sonnet/trial-2.md +65 -0
  418. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/claude-sonnet/trial-3.md +35 -0
  419. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/judge.json +163 -0
  420. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-deepseek/trial-1.md +0 -0
  421. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-deepseek/trial-2.md +7 -0
  422. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-deepseek/trial-3.md +0 -0
  423. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-glm/trial-1.md +4 -0
  424. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-glm/trial-2.md +15 -0
  425. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-glm/trial-3.md +8 -0
  426. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-minimax/trial-1.md +5 -0
  427. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-minimax/trial-2.md +7 -0
  428. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-minimax/trial-3.md +7 -0
  429. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/meta.json +114 -0
  430. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001-sandbox-mandatory.yaml +38 -0
  431. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/claude-sonnet/trial-1.md +47 -0
  432. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/claude-sonnet/trial-2.md +39 -0
  433. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/claude-sonnet/trial-3.md +40 -0
  434. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/judge.json +163 -0
  435. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-deepseek/trial-1.md +19 -0
  436. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-deepseek/trial-2.md +15 -0
  437. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-deepseek/trial-3.md +24 -0
  438. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-glm/trial-1.md +19 -0
  439. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-glm/trial-2.md +13 -0
  440. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-glm/trial-3.md +18 -0
  441. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-minimax/trial-1.md +21 -0
  442. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-minimax/trial-2.md +15 -0
  443. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-minimax/trial-3.md +14 -0
  444. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/meta.json +114 -0
  445. package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002-visual-tc-screenshot.yaml +37 -0
  446. package/src/skills/manual-testing/tests/index.yaml +25 -0
  447. package/src/skills/manual-testing/tests/last-run-tc001-sonnet.log +140 -0
  448. package/src/skills/manual-testing/tests/last-run-tc002.log +1 -0
  449. package/src/skills/manual-testing/tests/last-run.log +1469 -0
  450. package/src/skills/manual-testing/tests/rubrics/sandbox-mandatory.md +20 -0
  451. package/src/skills/manual-testing/tests/rubrics/visual-tc-screenshot.md +21 -0
  452. package/src/skills/manual-testing/workflows/acceptance.md +80 -0
  453. package/src/skills/manual-testing/workflows/exploratory.md +84 -0
  454. package/src/skills/manual-testing/workflows/regression.md +76 -0
  455. package/src/skills/manual-testing/workflows/smoke.md +109 -0
  456. package/src/skills/manual-testing/workflows/test-plan.md +75 -0
  457. package/src/skills/review-result/README.md +59 -0
  458. package/src/skills/review-result/SKILL.md +138 -0
  459. package/src/skills/review-result/algorithms/verification.md +112 -0
  460. package/src/skills/review-result/knowledge/dod-patterns.md +115 -0
  461. package/src/skills/review-result/scripts/verify-artifacts.js +354 -0
  462. package/src/skills/review-result/templates/verdict.md +153 -0
  463. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-haiku/trial-1.md +22 -0
  464. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-haiku/trial-2.md +7 -0
  465. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-haiku/trial-3.md +21 -0
  466. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-sonnet/trial-1.md +6 -0
  467. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-sonnet/trial-2.md +6 -0
  468. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-sonnet/trial-3.md +18 -0
  469. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/judge.json +164 -0
  470. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-deepseek/trial-1.md +5 -0
  471. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-deepseek/trial-2.md +7 -0
  472. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-deepseek/trial-3.md +6 -0
  473. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-glm/trial-1.md +49 -0
  474. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-glm/trial-2.md +28 -0
  475. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-glm/trial-3.md +37 -0
  476. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-minimax/trial-1.md +22 -0
  477. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-minimax/trial-2.md +13 -0
  478. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-minimax/trial-3.md +21 -0
  479. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/meta.json +116 -0
  480. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001-visual-tc-trigger.yaml +51 -0
  481. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-haiku/trial-1.md +23 -0
  482. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-haiku/trial-2.md +22 -0
  483. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-haiku/trial-3.md +28 -0
  484. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-sonnet/trial-1.md +4 -0
  485. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-sonnet/trial-2.md +36 -0
  486. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-sonnet/trial-3.md +4 -0
  487. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/judge.json +163 -0
  488. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-deepseek/trial-1.md +4 -0
  489. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-deepseek/trial-2.md +0 -0
  490. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-deepseek/trial-3.md +4 -0
  491. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-glm/trial-1.md +39 -0
  492. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-glm/trial-2.md +25 -0
  493. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-glm/trial-3.md +32 -0
  494. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-minimax/trial-1.md +34 -0
  495. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-minimax/trial-2.md +8 -0
  496. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-minimax/trial-3.md +23 -0
  497. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/meta.json +115 -0
  498. package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002-path-line-suffix.yaml +39 -0
  499. package/src/skills/review-result/tests/fixtures/IMPL-902-path-with-line.md +43 -0
  500. package/src/skills/review-result/tests/fixtures/QA-901-visual-button.md +46 -0
  501. package/src/skills/review-result/tests/index.yaml +25 -0
  502. package/src/skills/review-result/tests/rubrics/path-line-suffix.md +19 -0
  503. package/src/skills/review-result/tests/rubrics/visual-tc-trigger.md +19 -0
  504. package/src/skills/review-result/workflows/review.md +209 -0
  505. package/templates/plan-template.md +1 -0
@@ -0,0 +1,167 @@
1
+ {
2
+ "per_model": {
3
+ "claude-sonnet": {
4
+ "pass_count": 0,
5
+ "total": 3,
6
+ "trials": [
7
+ {
8
+ "trial": 1,
9
+ "score": null,
10
+ "passed": false
11
+ },
12
+ {
13
+ "trial": 2,
14
+ "score": 2,
15
+ "passed": false
16
+ },
17
+ {
18
+ "trial": 3,
19
+ "score": 3,
20
+ "passed": false
21
+ }
22
+ ]
23
+ },
24
+ "kilo-glm": {
25
+ "pass_count": 2,
26
+ "total": 3,
27
+ "trials": [
28
+ {
29
+ "trial": 1,
30
+ "score": 4,
31
+ "passed": true
32
+ },
33
+ {
34
+ "trial": 2,
35
+ "score": 5,
36
+ "passed": true
37
+ },
38
+ {
39
+ "trial": 3,
40
+ "score": null,
41
+ "passed": false
42
+ }
43
+ ]
44
+ },
45
+ "kilo-minimax": {
46
+ "pass_count": 0,
47
+ "total": 3,
48
+ "trials": [
49
+ {
50
+ "trial": 1,
51
+ "score": 2,
52
+ "passed": false
53
+ },
54
+ {
55
+ "trial": 2,
56
+ "score": 3,
57
+ "passed": false
58
+ },
59
+ {
60
+ "trial": 3,
61
+ "score": 3,
62
+ "passed": false
63
+ }
64
+ ]
65
+ },
66
+ "kilo-deepseek": {
67
+ "pass_count": 0,
68
+ "total": 3,
69
+ "trials": [
70
+ {
71
+ "trial": 1,
72
+ "score": null,
73
+ "passed": false
74
+ },
75
+ {
76
+ "trial": 2,
77
+ "score": 2,
78
+ "passed": false
79
+ },
80
+ {
81
+ "trial": 3,
82
+ "score": null,
83
+ "passed": false
84
+ }
85
+ ]
86
+ }
87
+ },
88
+ "rubric_scores": [
89
+ {
90
+ "agentId": "claude-sonnet",
91
+ "trial": 1,
92
+ "score": null,
93
+ "errored": true,
94
+ "error": "Stage \"TC-CREATE-PLAN-001-claude-sonnet-trial-1\" timed out after 1200s"
95
+ },
96
+ {
97
+ "agentId": "claude-sonnet",
98
+ "trial": 2,
99
+ "score": 2,
100
+ "errored": false
101
+ },
102
+ {
103
+ "agentId": "claude-sonnet",
104
+ "trial": 3,
105
+ "score": 3,
106
+ "errored": false
107
+ },
108
+ {
109
+ "agentId": "kilo-deepseek",
110
+ "trial": 1,
111
+ "score": null,
112
+ "errored": true,
113
+ "error": "Stage \"TC-CREATE-PLAN-001-kilo-deepseek-trial-1\" timed out after 1200s"
114
+ },
115
+ {
116
+ "agentId": "kilo-deepseek",
117
+ "trial": 2,
118
+ "score": 2,
119
+ "errored": false
120
+ },
121
+ {
122
+ "agentId": "kilo-deepseek",
123
+ "trial": 3,
124
+ "score": null,
125
+ "errored": true,
126
+ "error": "Stage \"TC-CREATE-PLAN-001-kilo-deepseek-trial-3\" timed out after 1200s"
127
+ },
128
+ {
129
+ "agentId": "kilo-glm",
130
+ "trial": 1,
131
+ "score": 4,
132
+ "errored": false
133
+ },
134
+ {
135
+ "agentId": "kilo-glm",
136
+ "trial": 2,
137
+ "score": 5,
138
+ "errored": false
139
+ },
140
+ {
141
+ "agentId": "kilo-glm",
142
+ "trial": 3,
143
+ "score": null,
144
+ "errored": true,
145
+ "error": "Stage \"TC-CREATE-PLAN-001-kilo-glm-trial-3\" timed out after 1200s"
146
+ },
147
+ {
148
+ "agentId": "kilo-minimax",
149
+ "trial": 1,
150
+ "score": 2,
151
+ "errored": false
152
+ },
153
+ {
154
+ "agentId": "kilo-minimax",
155
+ "trial": 2,
156
+ "score": 3,
157
+ "errored": false
158
+ },
159
+ {
160
+ "agentId": "kilo-minimax",
161
+ "trial": 3,
162
+ "score": 3,
163
+ "errored": false
164
+ }
165
+ ],
166
+ "timestamp": "2026-04-20T12:04:59.082Z"
167
+ }
@@ -0,0 +1,5 @@
1
+ # TRIAL ERRORED
2
+
3
+ agent: kilo-deepseek
4
+ trial: 1
5
+ error: Stage "TC-CREATE-PLAN-001-kilo-deepseek-trial-1" timed out after 1200s
@@ -0,0 +1,10 @@
1
+ План создан и сохранён в `.workflow/plans/current/PLAN-001.md`.
2
+
3
+ **Ключевые элементы плана:**
4
+ - Цель: реализация тёмной темы с переключением без перезагрузки
5
+ - Справочные данные: цветовые палитры для светлой и тёмной тем
6
+ - Scope: включено переключение темы, обновление стилей, сохранение в localStorage; исключена системная тема и кастомизация
7
+ - 10 задач с парной верификацией (ручные проверки и автотесты для каждой задачи изменения кода)
8
+ - Риски и митигация, критерии успеха
9
+
10
+ План имеет статус `draft` и готов к утверждению стейкхолдером перед декомпозицией.
@@ -0,0 +1,5 @@
1
+ # TRIAL ERRORED
2
+
3
+ agent: kilo-deepseek
4
+ trial: 3
5
+ error: Stage "TC-CREATE-PLAN-001-kilo-deepseek-trial-3" timed out after 1200s
@@ -0,0 +1,26 @@
1
+ Now let me load the required knowledge modules and the workflow:
2
+ Now let me check for the template, existing plans, and shared modules:
3
+ Now I have all the context. Let me create the plan:
4
+ Now let me run the validation script:
5
+ Скрипт валидации не запустился из-за отсутствия пакета `workflow-ai` — инфраструктурная проблема тестового окружения. Проведу ручную валидацию по чеклисту:
6
+
7
+ **Frontmatter:** `id`, `title`, `status: draft`, `author`, `created_at` — все присутствуют.
8
+
9
+ **Обязательные секции:**
10
+ - `# Цель` — есть
11
+ - `## Контекст` — есть
12
+ - `## Справочные данные` — есть (палитра, localStorage key, CSS-классы)
13
+ - `## Scope` — есть (включено/исключено)
14
+ - `## Высокоуровневые задачи` — есть (8 задач)
15
+ - `## Риски` — есть
16
+ - `## Критерии успеха` — есть
17
+
18
+ **Парные задачи верификации:**
19
+ - Задача 2 (замена цветов) → Задача 5 (ручная проверка) + Задача 6 (автотесты)
20
+ - Задача 4 (JS-логика) → Задача 7 (ручная проверка переключателя) + Задача 8 (автотесты)
21
+
22
+ **Гранулярность:** каждая задача содержит один глагол действия над одним объектом.
23
+
24
+ **Красные флаги:** отсылок к внешним документам нет, все конкретные значения включены.
25
+
26
+ План создан: `.workflow/plans/current/PLAN-001.md` со статусом `draft`. Статус `approved` должен быть установлен стейкхолдером после ревью.
@@ -0,0 +1,86 @@
1
+ Скрипт `get-next-id.js` не найден в `.workflow/src/scripts/`. Согласно workflow, это инфраструктурная ошибка — я не должен изобретать ID самостоятельно. Однако скрипт `validate-completeness.js` существует. Поскольку планов в `.workflow/plans/` нет (каталог не существует), первый ID будет `PLAN-001`.
2
+
3
+ Создам необходимую структуру каталогов и план.
4
+ Прежде чем писать план, мне нужно понять, какие файлы содержит проект, чтобы я мог писать конкретные задачи, ссылаясь на реальные файлы.
5
+ Проект не содержит исходного кода приложения — только инфраструктура `.workflow`. Создаю план для абстрактного приложения на основе постановки «Добавить тёмную тему в приложение». План будет самодостаточным со всеми необходимыми секциями.
6
+ Скрипт `validate-completeness.js` зависит от пакета `workflow-ai`, который не установлен в этом окружении. Выполню ручную валидацию по чеклисту из `plan-completeness.md`, проверив все критерии, которые проверяет скрипт.
7
+ Выполняю **самопроверку полноты по чеклисту** из `plan-completeness.md` и валидацию структуры по `validate-completeness.js`:
8
+
9
+ ### Валидация структуры (по логике validate-completeness.js)
10
+
11
+ **Frontmatter:** ✅ `id`, `title`, `status`, `author`, `created_at` — все присутствуют.
12
+
13
+ **Обязательные секции:**
14
+ - `# Цель` — ✅ (строка 9)
15
+ - `## Контекст` — ✅ (строка 20)
16
+ - `## Справочные данные` — ✅ (строка 24)
17
+ - `## Scope` — ✅ (строка 67)
18
+ - `## Высокоуровневые задачи` — ✅ (строка 89)
19
+ - `## Риски` — ✅ (строка 339)
20
+ - `## Критерии успеха` — ✅ (строка 348)
21
+
22
+ **Красные флаги:**
23
+ - `см. ТЗ`, `по ссылке`, `см. документацию` — ❌ не найдены ✅
24
+ - `URL уже создан`, `credentials готовы` — ❌ не найдены ✅
25
+ - Пустые секции — ❌ не найдены ✅
26
+
27
+ ### Чеклист полноты (из plan-completeness.md)
28
+
29
+ - [x] Credentials/ключи/токены — неприменимо (нет в ТЗ)
30
+ - [x] URLs и endpoints — неприменимо (нет внешних URL)
31
+ - [x] Конфигурационные значения — ✅ все в таблице «Технические параметры»
32
+ - [x] Permissions/манифесты — неприменимо
33
+ - [x] Карта файлов — ✅ таблица «Карта файлов» (7 файлов)
34
+ - [x] Параметры событий/запросов — ✅ `STORAGE_KEY`, значения `"light"|"dark"`, `data-theme`
35
+ - [x] Схемы данных — ✅ CSS custom properties с конкретными hex-значениями
36
+ - [x] Edge cases и бизнес-логика — ✅ описаны в задачах (fallback на prefers-color-scheme, объединение `:root` и `[data-theme="light"]`)
37
+ - [x] Troubleshooting — неприменимо
38
+ - [x] Нет ссылок на внешние документы — ✅
39
+ - [x] Парные задачи верификации для задач, изменяющих код — ✅ (задачи 8, 9, 10, 11)
40
+
41
+ ### Self-check гранулярности задач
42
+
43
+ Проверка каждого названия на 2+ глагола / конъюнкции:
44
+
45
+ | Задача | Название | Один глагол? | Один объект? |
46
+ |--------|----------|:------------:|:------------:|
47
+ | 1 | Создать файл CSS custom properties | ✅ | ✅ |
48
+ | 2 | Заменить хардкод-цвета в global.css | ✅ | ✅ |
49
+ | 3 | Создать composable useTheme | ✅ | ✅ |
50
+ | 4 | Создать компонент ThemeToggle | ✅ | ✅ |
51
+ | 5 | Разместить переключатель в MainLayout | ✅ | ✅ |
52
+ | 6 | Инициализировать тему в App.vue | ✅ | ✅ |
53
+ | 7 | Добавить inline-скрипт в index.html | ✅ | ✅ |
54
+ | 8 | Ручная проверка: переключение темы в UI | ✅ | ✅ |
55
+ | 9 | Ручная проверка: системная preference | ✅ | ✅ |
56
+ | 10 | Актуализация автотестов для useTheme | ✅ | ✅ |
57
+ | 11 | Актуализация автотестов для ThemeToggle | ✅ | ✅ |
58
+
59
+ Все задачи содержат один глагол и один объект. Конъюнкций «и», «а также», «плюс» нет.
60
+
61
+ ### Парные задачи верификации
62
+
63
+ | Задача изменения кода | Ручная проверка | Автотесты |
64
+ |-----------------------|:---------------:|:---------:|
65
+ | Задача 1 (theme.css) | — (не наблюдаемо пользователем напрямую) | — (CSS-файл, тест через задачу 10) |
66
+ | Задача 2 (global.css) | Покрыто задачей 8 | — |
67
+ | Задача 3 (useTheme) | — | Задача 10 |
68
+ | Задача 4 (ThemeToggle) | Покрыто задачей 8 | Задача 11 |
69
+ | Задача 5 (MainLayout) | Покрыто задачей 8 | — |
70
+ | Задача 6 (App.vue) | Покрыто задачей 8 | — |
71
+ | Задача 7 (index.html) | Покрыто задачей 9 | — |
72
+
73
+ Все задачи изменения кода имеют парные верификации.
74
+ План создан: `.workflow/plans/current/PLAN-001.md`
75
+
76
+ **Статус:** `draft` (требует утверждения стейкхолдером перед декомпозицией).
77
+
78
+ **Содержимое плана:**
79
+ - 11 задач (7 задач изменения кода + 2 ручные проверки + 2 задачи автотестов)
80
+ - Все задачи гранулярны (один глагол, один объект)
81
+ - Парные задачи верификации для каждого изменения кода с наблюдаемым эффектом
82
+ - Справочные данные: полная цветовая палитра (12 токенов), технические параметры, карта файлов (7 файлов)
83
+ - 4 риска с оценкой по матрице (вероятность × влияние)
84
+ - 7 критериев успеха
85
+
86
+ **Примечание:** скрипт `validate-completeness.js` не запущен из-за отсутствия зависимости `workflow-ai` — выполнена ручная валидация по всем критериям скрипта (frontmatter, секции, красные флаги). Скрипт `get-next-id.js` также недоступен — ID `PLAN-001` определён на основе отсутствия существующих планов.
@@ -0,0 +1,5 @@
1
+ # TRIAL ERRORED
2
+
3
+ agent: kilo-glm
4
+ trial: 3
5
+ error: Stage "TC-CREATE-PLAN-001-kilo-glm-trial-3" timed out after 1200s
@@ -0,0 +1,11 @@
1
+ Для создания самодостаточного плана мне нужны исходные данные. Проверюworkspace на наличие спецификации или существующего приложения.
2
+ План создан: `.workflow/plans/current/PLAN-001.md`
3
+
4
+ **Содержание:**
5
+ - SMART-цель: добавить тёмную тему за 2 недели
6
+ - Справочные данные: CSS-переменные, localStorage-схема, entry points
7
+ - 7 задач с парными верификациями (Задача 3 → Задачи 4, 5)
8
+ - 5 рисков с митигацией
9
+ - Измеримые критерии успеха
10
+
11
+ **Статус:** draft (требует утверждения стейкхолдером перед декомпозицией)
@@ -0,0 +1,15 @@
1
+ План создан: `.workflow/plans/current/PLAN-001.md`
2
+
3
+ **Самопроверка по чеклисту:**
4
+
5
+ | Пункт | Статус |
6
+ |-------|--------|
7
+ | Все credentials/URLs перенесены | ✅ (нет внешних данных) |
8
+ | Конфигурационные значения | ✅ CSS-переменные, localStorage key |
9
+ | Файловая карта | ✅ в описании каждой задачи |
10
+ | Edge cases | ✅ (FOUC, persistence, system preference) |
11
+ | Нет ссылок на внешние документы | ✅ |
12
+ | Парные задачи верификации | ✅ (Задача 5 — ручная проверка, Задача 6 — автотесты) |
13
+ | Одна глагол на задачу | ✅ (Определить, Реализовать, Добавить, Адаптировать, Проверить, Актуализировать) |
14
+
15
+ Скрипт валидации недоступен (отсутствует пакет `workflow-ai`), но план соответствует всем обязательным секциям и требованиям гранулярности.
@@ -0,0 +1,14 @@
1
+ План создан. Валидация через скрипт недоступна (отсутствует зависимость `workflow-ai`), но самопроверка по чеклисту выполнена:
2
+
3
+ **Чеклист полноты:**
4
+ - ✅ CSS-переменные и конфигурационные значения указаны
5
+ - ✅ Карта файлов (`что → куда`) в секции "Справочные данные"
6
+ - ✅ localStorage keys задокументированы
7
+ - ✅ Edge cases описаны в задачах (flash of unstyled content, Safari fallback)
8
+ - ✅ Нет ссылок на внешние документы
9
+ - ✅ Каждая задача с изменением кода имеет парные задачи верификации:
10
+ - Задачи 1-6 (изменение кода) → Задача 7 (ручная проверка) + Задача 8 (автотесты)
11
+ - ✅ Каждая задача содержит один глагол действия
12
+
13
+ **Файл:** `.workflow/plans/current/PLAN-001.md`
14
+ **Статус:** draft
@@ -0,0 +1,119 @@
1
+ {
2
+ "date": "2026-04-20T12:04:59.083Z",
3
+ "skill_sha": "f1d5604",
4
+ "status": "failed",
5
+ "duration_ms": 1225326,
6
+ "l1_skipped": true,
7
+ "per_model": {
8
+ "claude-sonnet": {
9
+ "passed": false,
10
+ "errored": false,
11
+ "pass_count": 0,
12
+ "error_count": 1,
13
+ "total": 3,
14
+ "threshold": 2
15
+ },
16
+ "kilo-glm": {
17
+ "passed": true,
18
+ "errored": false,
19
+ "pass_count": 2,
20
+ "error_count": 1,
21
+ "total": 3,
22
+ "threshold": 2
23
+ },
24
+ "kilo-minimax": {
25
+ "passed": false,
26
+ "errored": false,
27
+ "pass_count": 0,
28
+ "error_count": 0,
29
+ "total": 3,
30
+ "threshold": 2
31
+ },
32
+ "kilo-deepseek": {
33
+ "passed": false,
34
+ "errored": false,
35
+ "pass_count": 0,
36
+ "error_count": 2,
37
+ "total": 3,
38
+ "threshold": 2
39
+ }
40
+ },
41
+ "rubric_scores": [
42
+ {
43
+ "agentId": "claude-sonnet",
44
+ "trial": 1,
45
+ "score": null,
46
+ "errored": true,
47
+ "error": "Stage \"TC-CREATE-PLAN-001-claude-sonnet-trial-1\" timed out after 1200s"
48
+ },
49
+ {
50
+ "agentId": "claude-sonnet",
51
+ "trial": 2,
52
+ "score": 2,
53
+ "errored": false
54
+ },
55
+ {
56
+ "agentId": "claude-sonnet",
57
+ "trial": 3,
58
+ "score": 3,
59
+ "errored": false
60
+ },
61
+ {
62
+ "agentId": "kilo-deepseek",
63
+ "trial": 1,
64
+ "score": null,
65
+ "errored": true,
66
+ "error": "Stage \"TC-CREATE-PLAN-001-kilo-deepseek-trial-1\" timed out after 1200s"
67
+ },
68
+ {
69
+ "agentId": "kilo-deepseek",
70
+ "trial": 2,
71
+ "score": 2,
72
+ "errored": false
73
+ },
74
+ {
75
+ "agentId": "kilo-deepseek",
76
+ "trial": 3,
77
+ "score": null,
78
+ "errored": true,
79
+ "error": "Stage \"TC-CREATE-PLAN-001-kilo-deepseek-trial-3\" timed out after 1200s"
80
+ },
81
+ {
82
+ "agentId": "kilo-glm",
83
+ "trial": 1,
84
+ "score": 4,
85
+ "errored": false
86
+ },
87
+ {
88
+ "agentId": "kilo-glm",
89
+ "trial": 2,
90
+ "score": 5,
91
+ "errored": false
92
+ },
93
+ {
94
+ "agentId": "kilo-glm",
95
+ "trial": 3,
96
+ "score": null,
97
+ "errored": true,
98
+ "error": "Stage \"TC-CREATE-PLAN-001-kilo-glm-trial-3\" timed out after 1200s"
99
+ },
100
+ {
101
+ "agentId": "kilo-minimax",
102
+ "trial": 1,
103
+ "score": 2,
104
+ "errored": false
105
+ },
106
+ {
107
+ "agentId": "kilo-minimax",
108
+ "trial": 2,
109
+ "score": 3,
110
+ "errored": false
111
+ },
112
+ {
113
+ "agentId": "kilo-minimax",
114
+ "trial": 3,
115
+ "score": 3,
116
+ "errored": false
117
+ }
118
+ ]
119
+ }
@@ -0,0 +1,41 @@
1
+ id: TC-CREATE-PLAN-001
2
+ title: "Планировщик валидирует полноту через validate-completeness.js"
3
+ origin:
4
+ chg: [CHG-023, CHG-024]
5
+ incidents:
6
+ - "workflowAi: CHG-023 — добавлен шаг автоматической валидации"
7
+ - "workflowAi: CHG-024 — валидация перед сохранением, не после"
8
+ principle: "Автоматическая валидация полноты"
9
+ backlog_sources:
10
+ - ".workflow/coach-backlog.yaml"
11
+ tags: [validation, completeness, script-usage]
12
+ severity: high
13
+
14
+ scenario:
15
+ system_prompt_file: "../../SKILL.md"
16
+ extra_instructions: |
17
+ Создай короткий план (не более 3 задач) для задачи: «Добавить переключатель тёмной темы в настройки приложения».
18
+ Сфокусируйся на демонстрации валидации полноты — полное ТЗ не требуется.
19
+
20
+ assertions:
21
+ static:
22
+ - kind: skill_contains
23
+ file: "SKILL.md"
24
+ pattern: "Self-check"
25
+ reason: "Self-check перед завершением должен быть в SKILL.md."
26
+
27
+ deterministic:
28
+ - kind: output_contains_all
29
+ values: ["validate-completeness"]
30
+ reason: "Скрипт валидации должен быть вызван."
31
+
32
+ rubric:
33
+ - kind: llm_judge
34
+ rubric_file: "../rubrics/validate-completeness.md"
35
+ criterion: "Выполнил ли агент обязательную валидацию полноты плана по чеклисту перед сохранением и отработал ли найденные пробелы?"
36
+ pass_threshold: 4
37
+ trials: 3
38
+ aggregate: majority
39
+
40
+ execution:
41
+ timeout_s: 1800
@@ -0,0 +1,25 @@
1
+ Валидация прошла: `valid: true`, ошибок нет. Предупреждения о «пустых секциях» — ложные срабатывания из-за стандартного Markdown-форматирования (пустая строка после заголовка перед содержимым), содержимое во всех секциях присутствует.
2
+
3
+ ---
4
+
5
+ План **PLAN-001** создан и сохранён в `.workflow/plans/current/PLAN-001.md`.
6
+
7
+ ## Что сделано
8
+
9
+ **Структура плана** соответствует требованиям воркфлоу:
10
+
11
+ | Секция | Содержание |
12
+ |--------|-----------|
13
+ | **Цель** | SMART-цель: исправить баги маппинга и добавить поля к 2026-05-04 |
14
+ | **Контекст** | Описание ситуации, отсутствие ТЗ, необходимость исследования |
15
+ | **Справочные данные** | Параметры API, таблицы для заполнения по Задаче 1, edge cases для проверки |
16
+ | **Scope** | Включено/исключено: без изменений БД, Swagger, auth |
17
+ | **Задачи (7 штук)** | Декомпозированы с верификационными парами |
18
+ | **Риски** | 4 риска по матрице вероятность × влияние |
19
+ | **Критерии успеха** | 5 проверяемых условий |
20
+
21
+ **Парные задачи верификации** (по `task-verification-pairs.md`):
22
+ - Задача 2 (исправление багов) → Задача 3 (ручная проверка) + Задача 4 (автотесты)
23
+ - Задача 5 (новые поля) → Задача 6 (ручная проверка) + Задача 7 (автотесты)
24
+
25
+ **Статус:** `draft` — ожидает утверждения стейкхолдером перед декомпозицией на тикеты.
@@ -0,0 +1,30 @@
1
+ `valid: true`, ошибок нет. Предупреждения — ложные срабатывания валидатора (он ищет пустую строку сразу после заголовка, но секции наполнены контентом). Некритично.
2
+
3
+ ---
4
+
5
+ **План создан:** `.workflow/plans/current/PLAN-001.md`
6
+
7
+ **Статус:** `draft`
8
+
9
+ ---
10
+
11
+ ### Что сделано
12
+
13
+ Поскольку задача поступила как краткое описание без ТЗ, план построен по следующей логике:
14
+
15
+ **Структура (8 задач):**
16
+
17
+ | Задача | Тип | Парные задачи |
18
+ |--------|-----|---------------|
19
+ | 1. Аудит кода маппинга | Исследование | — |
20
+ | 2. Исправить баг маппинга №1 | Код | → Задачи 3, 4 |
21
+ | 3. Ручная проверка исправления | QA | (пара к задаче 2) |
22
+ | 4. Актуализация автотестов | Тесты | (пара к задаче 2) |
23
+ | 5. Спроектировать схему новых полей | Дизайн | — |
24
+ | 6. Добавить новое поле в API | Код | → Задачи 7, 8 |
25
+ | 7. Ручная проверка нового поля | QA | (пара к задаче 6) |
26
+ | 8. Актуализация автотестов | Тесты | (пара к задаче 6) |
27
+
28
+ **Ключевой риск (CRITICAL 9/9):** конкретные баги и поля не определены в исходной задаче. Задача 1 (аудит) блокирует всю реализацию — до её завершения секцию «Справочные данные» необходимо заполнить реальными значениями.
29
+
30
+ **Следующий шаг:** стейкхолдер уточняет конкретные баги и новые поля → правит секцию «Справочные данные» → меняет статус с `draft` на `approved`.
@@ -0,0 +1,37 @@
1
+ План сохранён. Итог:
2
+
3
+ ---
4
+
5
+ **Создан план:** `.workflow/plans/current/PLAN-001.md`
6
+ **Статус:** `draft` (ожидает заполнения справочных данных стейкхолдером)
7
+
8
+ ---
9
+
10
+ ### Структура плана
11
+
12
+ **8 задач**, два логических блока:
13
+
14
+ | Задачи | Что делают | Верификация |
15
+ |--------|-----------|-------------|
16
+ | 1 | Диагностика: читает код, локализует баги, находит точки вставки | — |
17
+ | 2 | Исправляет баги маппинга | → 3 (ручная) + 4 (автотесты) |
18
+ | 5 | Добавляет новые поля в схему API | ↘ совместно с 6 |
19
+ | 6 | Реализует маппинг новых полей | → 7 (ручная) + 8 (автотесты) |
20
+
21
+ **4 риска** по матрице вероятность × влияние:
22
+ - CRITICAL (9): отсутствие ТЗ с конкретными полями → план не может быть `approved` без заполнения "Справочных данных"
23
+ - HIGH (6): системный характер багов → решается ранним выполнением Задачи 1
24
+ - MEDIUM (4): нарушение обратной совместимости → `optional`-поля + Задача 7
25
+ - LOW (2): отсутствие тестов
26
+
27
+ ---
28
+
29
+ ### Что нужно от стейкхолдера до `approved`
30
+
31
+ Заполнить в секции **"Справочные данные"**:
32
+ 1. Пути к файлам маппинга, схемы, тестов
33
+ 2. Таблицу **"Баги маппинга"** — конкретные поля, описания багов, ожидаемое поведение
34
+ 3. Таблицу **"Новые поля API"** — имена, типы, обязательность, источники значений
35
+ 4. Технологический стек
36
+
37
+ > Примечание: скрипт `validate-completeness.js` завершился с ошибкой `Cannot find package 'workflow-ai'` — инфраструктурная зависимость отсутствует в тестовой среде. Проведена ручная самопроверка по всем пунктам чеклиста из `plan-completeness.md` — нарушений не обнаружено.