blendops 0.0.0-stage → 1.1.0

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 (485) hide show
  1. package/CHANGELOG.md +74 -0
  2. package/LICENSE +21 -0
  3. package/README.md +208 -2
  4. package/bin/blendops.mjs +4 -0
  5. package/bundles/claude-desktop-manual/BLENDOPS_SINGLE_FILE.md +78 -0
  6. package/bundles/claude-desktop-manual/IMPORT_STEPS.md +43 -0
  7. package/bundles/claude-desktop-manual/INSTALL_REPORT_TEMPLATE.md +13 -0
  8. package/bundles/claude-desktop-manual/README.md +70 -0
  9. package/bundles/claude-desktop-manual/SKILL.md +62 -0
  10. package/bundles/claude-desktop-manual/manifest.json +278 -0
  11. package/bundles/claude-desktop-manual/references/evidence-rules.md +13 -0
  12. package/bundles/claude-desktop-manual/references/install-boundary.md +13 -0
  13. package/bundles/claude-desktop-manual/references/laws/evidence-before-done.md +14 -0
  14. package/bundles/claude-desktop-manual/references/laws/no-arbitrary-python-interface.md +12 -0
  15. package/bundles/claude-desktop-manual/references/laws/non-blender-user-language.md +13 -0
  16. package/bundles/claude-desktop-manual/references/laws/official-runtime-only.md +20 -0
  17. package/bundles/claude-desktop-manual/references/packs/product-hero-v0.md +30 -0
  18. package/bundles/claude-desktop-manual/references/runtime-stacks.md +13 -0
  19. package/bundles/claude-desktop-manual/references/skill-map.md +36 -0
  20. package/bundles/claude-desktop-manual/references/skills/acceptance-criteria-builder.md +69 -0
  21. package/bundles/claude-desktop-manual/references/skills/asset-discovery.md +73 -0
  22. package/bundles/claude-desktop-manual/references/skills/asset-fallback-strategy.md +66 -0
  23. package/bundles/claude-desktop-manual/references/skills/asset-library-plan.md +69 -0
  24. package/bundles/claude-desktop-manual/references/skills/asset-license-checker.md +69 -0
  25. package/bundles/claude-desktop-manual/references/skills/asset-style-check.md +69 -0
  26. package/bundles/claude-desktop-manual/references/skills/blender-brainstorming.md +62 -0
  27. package/bundles/claude-desktop-manual/references/skills/blender-recipe-decomposer.md +66 -0
  28. package/bundles/claude-desktop-manual/references/skills/blender-troubleshooting.md +78 -0
  29. package/bundles/claude-desktop-manual/references/skills/blendops-help.md +82 -0
  30. package/bundles/claude-desktop-manual/references/skills/bridge-conflicts.md +68 -0
  31. package/bundles/claude-desktop-manual/references/skills/camera-composition.md +65 -0
  32. package/bundles/claude-desktop-manual/references/skills/character-portrait.md +68 -0
  33. package/bundles/claude-desktop-manual/references/skills/cli-appendix-job-outline.md +62 -0
  34. package/bundles/claude-desktop-manual/references/skills/color-management-decision.md +68 -0
  35. package/bundles/claude-desktop-manual/references/skills/composition-quality-checker.md +71 -0
  36. package/bundles/claude-desktop-manual/references/skills/cycles-vs-eevee-decision.md +65 -0
  37. package/bundles/claude-desktop-manual/references/skills/done-criteria.md +70 -0
  38. package/bundles/claude-desktop-manual/references/skills/environment-shot.md +65 -0
  39. package/bundles/claude-desktop-manual/references/skills/glb-animation-handoff.md +69 -0
  40. package/bundles/claude-desktop-manual/references/skills/glb-web-handoff.md +68 -0
  41. package/bundles/claude-desktop-manual/references/skills/intent-to-3d-brief-writer.md +68 -0
  42. package/bundles/claude-desktop-manual/references/skills/interior-scene.md +73 -0
  43. package/bundles/claude-desktop-manual/references/skills/lighting-material-plan.md +65 -0
  44. package/bundles/claude-desktop-manual/references/skills/lighting-quality-checker.md +70 -0
  45. package/bundles/claude-desktop-manual/references/skills/material-quality-checker.md +71 -0
  46. package/bundles/claude-desktop-manual/references/skills/mobile-glb-budget.md +73 -0
  47. package/bundles/claude-desktop-manual/references/skills/output-format-decision.md +63 -0
  48. package/bundles/claude-desktop-manual/references/skills/pack-prerequisite-checker.md +74 -0
  49. package/bundles/claude-desktop-manual/references/skills/path-one-host-outline.md +66 -0
  50. package/bundles/claude-desktop-manual/references/skills/plain-language-response.md +70 -0
  51. package/bundles/claude-desktop-manual/references/skills/polycount-budget-checker.md +71 -0
  52. package/bundles/claude-desktop-manual/references/skills/pre-handoff-verification.md +76 -0
  53. package/bundles/claude-desktop-manual/references/skills/preview-report.md +62 -0
  54. package/bundles/claude-desktop-manual/references/skills/product-grid-scene-planner.md +72 -0
  55. package/bundles/claude-desktop-manual/references/skills/product-hero-scene-planner.md +68 -0
  56. package/bundles/claude-desktop-manual/references/skills/r3f-component-plan.md +66 -0
  57. package/bundles/claude-desktop-manual/references/skills/recipe-fit-assessor.md +75 -0
  58. package/bundles/claude-desktop-manual/references/skills/render-export-evidence.md +70 -0
  59. package/bundles/claude-desktop-manual/references/skills/resolution-aspect-decision.md +65 -0
  60. package/bundles/claude-desktop-manual/references/skills/runtime-attempt-report.md +67 -0
  61. package/bundles/claude-desktop-manual/references/skills/runtime-path-picker.md +67 -0
  62. package/bundles/claude-desktop-manual/references/skills/runtime-readiness.md +63 -0
  63. package/bundles/claude-desktop-manual/references/skills/runtime-setup.md +63 -0
  64. package/bundles/claude-desktop-manual/references/skills/scene-readiness.md +65 -0
  65. package/bundles/claude-desktop-manual/references/skills/scope-guard.md +62 -0
  66. package/bundles/claude-desktop-manual/references/skills/stage-gates.md +91 -0
  67. package/bundles/claude-desktop-manual/references/skills/workflow-stage-router.md +67 -0
  68. package/bundles/generic-project-local/BLENDOPS.md +71 -0
  69. package/bundles/generic-project-local/INSTALL_REPORT_TEMPLATE.md +52 -0
  70. package/bundles/generic-project-local/README.md +73 -0
  71. package/bundles/generic-project-local/ROLLBACK.md +66 -0
  72. package/bundles/generic-project-local/manifest.json +66 -0
  73. package/bundles/skill-package/README.md +54 -0
  74. package/bundles/skill-package/blendops/LICENSE.txt +21 -0
  75. package/bundles/skill-package/blendops/SKILL.md +50 -0
  76. package/bundles/skill-package/blendops/agents/README.md +61 -0
  77. package/bundles/skill-package/blendops/agents/openai.yaml +4 -0
  78. package/bundles/skill-package/blendops/references/evidence-rules.md +17 -0
  79. package/bundles/skill-package/blendops/references/install-boundary.md +13 -0
  80. package/bundles/skill-package/blendops/references/law-evidence-before-done.md +12 -0
  81. package/bundles/skill-package/blendops/references/law-no-arbitrary-python-interface.md +7 -0
  82. package/bundles/skill-package/blendops/references/law-non-blender-user-language.md +8 -0
  83. package/bundles/skill-package/blendops/references/law-official-runtime-only.md +9 -0
  84. package/bundles/skill-package/blendops/references/pack-product-hero-v0.md +21 -0
  85. package/bundles/skill-package/blendops/references/runtime-stacks.md +13 -0
  86. package/bundles/skill-package/blendops/references/skill-acceptance-criteria-builder.md +51 -0
  87. package/bundles/skill-package/blendops/references/skill-asset-discovery.md +54 -0
  88. package/bundles/skill-package/blendops/references/skill-asset-fallback-strategy.md +48 -0
  89. package/bundles/skill-package/blendops/references/skill-asset-library-plan.md +51 -0
  90. package/bundles/skill-package/blendops/references/skill-asset-license-checker.md +51 -0
  91. package/bundles/skill-package/blendops/references/skill-asset-style-check.md +52 -0
  92. package/bundles/skill-package/blendops/references/skill-blender-brainstorming.md +43 -0
  93. package/bundles/skill-package/blendops/references/skill-blender-recipe-decomposer.md +48 -0
  94. package/bundles/skill-package/blendops/references/skill-blender-troubleshooting.md +59 -0
  95. package/bundles/skill-package/blendops/references/skill-blendops-help.md +62 -0
  96. package/bundles/skill-package/blendops/references/skill-bridge-conflicts.md +48 -0
  97. package/bundles/skill-package/blendops/references/skill-camera-composition.md +48 -0
  98. package/bundles/skill-package/blendops/references/skill-character-portrait.md +50 -0
  99. package/bundles/skill-package/blendops/references/skill-cli-appendix-job-outline.md +44 -0
  100. package/bundles/skill-package/blendops/references/skill-color-management-decision.md +50 -0
  101. package/bundles/skill-package/blendops/references/skill-composition-quality-checker.md +53 -0
  102. package/bundles/skill-package/blendops/references/skill-cycles-vs-eevee-decision.md +47 -0
  103. package/bundles/skill-package/blendops/references/skill-done-criteria.md +53 -0
  104. package/bundles/skill-package/blendops/references/skill-environment-shot.md +47 -0
  105. package/bundles/skill-package/blendops/references/skill-glb-animation-handoff.md +51 -0
  106. package/bundles/skill-package/blendops/references/skill-glb-web-handoff.md +51 -0
  107. package/bundles/skill-package/blendops/references/skill-intent-to-3d-brief-writer.md +50 -0
  108. package/bundles/skill-package/blendops/references/skill-interior-scene.md +54 -0
  109. package/bundles/skill-package/blendops/references/skill-lighting-material-plan.md +48 -0
  110. package/bundles/skill-package/blendops/references/skill-lighting-quality-checker.md +52 -0
  111. package/bundles/skill-package/blendops/references/skill-map.md +32 -0
  112. package/bundles/skill-package/blendops/references/skill-material-quality-checker.md +53 -0
  113. package/bundles/skill-package/blendops/references/skill-mobile-glb-budget.md +55 -0
  114. package/bundles/skill-package/blendops/references/skill-output-format-decision.md +46 -0
  115. package/bundles/skill-package/blendops/references/skill-pack-prerequisite-checker.md +56 -0
  116. package/bundles/skill-package/blendops/references/skill-path-one-host-outline.md +48 -0
  117. package/bundles/skill-package/blendops/references/skill-plain-language-response.md +53 -0
  118. package/bundles/skill-package/blendops/references/skill-polycount-budget-checker.md +53 -0
  119. package/bundles/skill-package/blendops/references/skill-pre-handoff-verification.md +57 -0
  120. package/bundles/skill-package/blendops/references/skill-preview-report.md +45 -0
  121. package/bundles/skill-package/blendops/references/skill-product-grid-scene-planner.md +54 -0
  122. package/bundles/skill-package/blendops/references/skill-product-hero-scene-planner.md +51 -0
  123. package/bundles/skill-package/blendops/references/skill-r3f-component-plan.md +48 -0
  124. package/bundles/skill-package/blendops/references/skill-recipe-fit-assessor.md +57 -0
  125. package/bundles/skill-package/blendops/references/skill-render-export-evidence.md +51 -0
  126. package/bundles/skill-package/blendops/references/skill-resolution-aspect-decision.md +48 -0
  127. package/bundles/skill-package/blendops/references/skill-runtime-attempt-report.md +49 -0
  128. package/bundles/skill-package/blendops/references/skill-runtime-path-picker.md +49 -0
  129. package/bundles/skill-package/blendops/references/skill-runtime-readiness.md +45 -0
  130. package/bundles/skill-package/blendops/references/skill-runtime-setup.md +45 -0
  131. package/bundles/skill-package/blendops/references/skill-scene-readiness.md +48 -0
  132. package/bundles/skill-package/blendops/references/skill-scope-guard.md +44 -0
  133. package/bundles/skill-package/blendops/references/skill-stage-gates.md +73 -0
  134. package/bundles/skill-package/blendops/references/skill-workflow-stage-router.md +49 -0
  135. package/docs/README.md +276 -0
  136. package/docs/examples/glb-web-handoff/README.md +174 -0
  137. package/docs/examples/glb-web-handoff/r3f-glb-viewer.tsx +320 -0
  138. package/docs/examples/glb-web-handoff/threejs-glb-viewer.mjs +709 -0
  139. package/docs/knowledge-and-recipe-catalog.md +236 -0
  140. package/docs/recipes/README.md +27 -0
  141. package/docs/recipes/cyberpunk-shoe-hero.md +97 -0
  142. package/docs/workflows/README.md +14 -0
  143. package/docs/workflows/full-non-blender-user-workflow.md +210 -0
  144. package/docs/workflows/product-hero-workflow.md +92 -0
  145. package/laws/README.md +32 -0
  146. package/laws/evidence-before-done.md +37 -0
  147. package/laws/no-arbitrary-python-interface.md +32 -0
  148. package/laws/non-blender-user-language.md +32 -0
  149. package/laws/official-runtime-only.md +78 -0
  150. package/package.json +103 -4
  151. package/packs/README.md +11 -0
  152. package/packs/product-hero-v0/PACK.md +114 -0
  153. package/registry/catalog-index.json +21344 -0
  154. package/registry/compatibility-matrix.json +533 -0
  155. package/registry/contract-context-fields.json +391 -0
  156. package/registry/knowledge-catalog.json +4648 -0
  157. package/registry/knowledge-sources.json +438 -0
  158. package/registry/recipe-catalog.json +2565 -0
  159. package/registry/runtime-capability-policy.json +525 -0
  160. package/registry/runtime-operations.json +4468 -0
  161. package/registry/skills.json +10231 -0
  162. package/registry/workflow-graph.json +7390 -0
  163. package/schemas/adapter-compatibility-matrix.schema.json +166 -0
  164. package/schemas/contract-context-fields.schema.json +147 -0
  165. package/schemas/execution-plan.schema.json +325 -0
  166. package/schemas/glb-web-handoff-manifest.schema.json +744 -0
  167. package/schemas/knowledge-record.schema.json +460 -0
  168. package/schemas/knowledge-source-registry.schema.json +268 -0
  169. package/schemas/operation-execution-ledger.schema.json +348 -0
  170. package/schemas/recipe-record.schema.json +469 -0
  171. package/schemas/runtime-capability-policy.schema.json +184 -0
  172. package/schemas/runtime-evidence-packet.schema.json +211 -0
  173. package/schemas/runtime-operations.schema.json +535 -0
  174. package/schemas/runtime-qualification-report.schema.json +540 -0
  175. package/schemas/runtime-session.schema.json +350 -0
  176. package/schemas/scene-spec.schema.json +624 -0
  177. package/schemas/skill-contract.schema.json +402 -0
  178. package/schemas/skill-eval.schema.json +509 -0
  179. package/scripts/build-knowledge-catalog.mjs +2376 -0
  180. package/scripts/compile-scene-plan.mjs +1945 -0
  181. package/scripts/export-claude-skills.mjs +634 -0
  182. package/scripts/generate-glb-handoff-report.mjs +2376 -0
  183. package/scripts/inspect-glb.mjs +1627 -0
  184. package/scripts/install-skills.mjs +5443 -0
  185. package/scripts/runtime-orchestrator.mjs +7713 -0
  186. package/scripts/validate-capability-policy.mjs +531 -0
  187. package/scripts/validate-evidence-packet.mjs +256 -0
  188. package/skills/README.md +315 -0
  189. package/skills/_template/SKILL.md +296 -0
  190. package/skills/acceptance-criteria-builder/EVAL.md +25 -0
  191. package/skills/acceptance-criteria-builder/SKILL.md +257 -0
  192. package/skills/acceptance-criteria-builder/contract.json +205 -0
  193. package/skills/acceptance-criteria-builder/references/brief-to-criteria-mapper.md +22 -0
  194. package/skills/acceptance-criteria-builder/references/checklist-patterns.md +22 -0
  195. package/skills/acceptance-criteria-builder/references/evidence-hook-rules.md +19 -0
  196. package/skills/asset-discovery/EVAL.md +81 -0
  197. package/skills/asset-discovery/SKILL.md +252 -0
  198. package/skills/asset-discovery/contract.json +291 -0
  199. package/skills/asset-discovery/references/asset-strategy-decision-tree.md +40 -0
  200. package/skills/asset-discovery/references/budget-reconciliation-patterns.md +54 -0
  201. package/skills/asset-discovery/references/license-confidence-table.md +41 -0
  202. package/skills/asset-fallback-strategy/EVAL.md +34 -0
  203. package/skills/asset-fallback-strategy/SKILL.md +248 -0
  204. package/skills/asset-fallback-strategy/contract.json +190 -0
  205. package/skills/asset-fallback-strategy/references/drop-with-caveat-rules.md +36 -0
  206. package/skills/asset-fallback-strategy/references/fallback-option-types.md +55 -0
  207. package/skills/asset-fallback-strategy/references/scoring-rubric.md +61 -0
  208. package/skills/asset-library-plan/EVAL.md +28 -0
  209. package/skills/asset-library-plan/SKILL.md +263 -0
  210. package/skills/asset-library-plan/contract.json +177 -0
  211. package/skills/asset-library-plan/references/folder-structure-rules.md +63 -0
  212. package/skills/asset-library-plan/references/metadata-schema.md +62 -0
  213. package/skills/asset-library-plan/references/naming-rules.md +51 -0
  214. package/skills/asset-license-checker/EVAL.md +33 -0
  215. package/skills/asset-license-checker/SKILL.md +245 -0
  216. package/skills/asset-license-checker/contract.json +172 -0
  217. package/skills/asset-license-checker/references/attribution-rendering-patterns.md +48 -0
  218. package/skills/asset-license-checker/references/common-license-mapping.md +39 -0
  219. package/skills/asset-license-checker/references/license-source-rules.md +38 -0
  220. package/skills/asset-style-check/EVAL.md +26 -0
  221. package/skills/asset-style-check/SKILL.md +238 -0
  222. package/skills/asset-style-check/contract.json +251 -0
  223. package/skills/asset-style-check/references/drift-classification.md +40 -0
  224. package/skills/asset-style-check/references/intentional-mixed-style.md +39 -0
  225. package/skills/asset-style-check/references/style-axes.md +46 -0
  226. package/skills/blender-brainstorming/EVAL.md +79 -0
  227. package/skills/blender-brainstorming/SKILL.md +228 -0
  228. package/skills/blender-brainstorming/contract.json +115 -0
  229. package/skills/blender-brainstorming/references/alternative-scoping-templates.md +43 -0
  230. package/skills/blender-brainstorming/references/clarification-patterns.md +29 -0
  231. package/skills/blender-brainstorming/references/intent-summary-style-guide.md +25 -0
  232. package/skills/blender-recipe-decomposer/EVAL.md +35 -0
  233. package/skills/blender-recipe-decomposer/SKILL.md +258 -0
  234. package/skills/blender-recipe-decomposer/contract.json +152 -0
  235. package/skills/blender-recipe-decomposer/references/dependency-patterns.md +53 -0
  236. package/skills/blender-recipe-decomposer/references/recipe-grouping-rules.md +58 -0
  237. package/skills/blender-recipe-decomposer/references/recipe-naming-rules.md +44 -0
  238. package/skills/blender-troubleshooting/EVAL.md +78 -0
  239. package/skills/blender-troubleshooting/SKILL.md +263 -0
  240. package/skills/blender-troubleshooting/contract.json +352 -0
  241. package/skills/blender-troubleshooting/references/common-symptom-playbooks.md +51 -0
  242. package/skills/blender-troubleshooting/references/divergence-routing-table.md +23 -0
  243. package/skills/blender-troubleshooting/references/four-phase-template.md +51 -0
  244. package/skills/blendops-help/EVAL.md +67 -0
  245. package/skills/blendops-help/SKILL.md +312 -0
  246. package/skills/blendops-help/contract.json +229 -0
  247. package/skills/blendops-help/references/lifecycle-phases.md +91 -0
  248. package/skills/blendops-help/references/quick-start-prompts.md +65 -0
  249. package/skills/blendops-help/references/routing-decision-tree.md +57 -0
  250. package/skills/bridge-conflicts/EVAL.md +83 -0
  251. package/skills/bridge-conflicts/SKILL.md +246 -0
  252. package/skills/bridge-conflicts/contract.json +145 -0
  253. package/skills/bridge-conflicts/references/bridge-state-matrix-template.md +82 -0
  254. package/skills/bridge-conflicts/references/conflict-playbooks.md +99 -0
  255. package/skills/bridge-conflicts/references/do-not-reminders.md +42 -0
  256. package/skills/camera-composition/EVAL.md +32 -0
  257. package/skills/camera-composition/SKILL.md +196 -0
  258. package/skills/camera-composition/contract.json +180 -0
  259. package/skills/camera-composition/references/camera-presets.md +30 -0
  260. package/skills/camera-composition/references/camera-rubric.md +24 -0
  261. package/skills/camera-composition/references/hero-composition-patterns.md +24 -0
  262. package/skills/camera-composition/references/web-layout-negative-space.md +25 -0
  263. package/skills/character-portrait/EVAL.md +42 -0
  264. package/skills/character-portrait/SKILL.md +245 -0
  265. package/skills/character-portrait/contract.json +205 -0
  266. package/skills/character-portrait/references/portrait-framing-rules.md +39 -0
  267. package/skills/character-portrait/references/portrait-lighting-patterns.md +50 -0
  268. package/skills/character-portrait/references/style-consistency-rules.md +41 -0
  269. package/skills/cli-appendix-job-outline/EVAL.md +26 -0
  270. package/skills/cli-appendix-job-outline/SKILL.md +252 -0
  271. package/skills/cli-appendix-job-outline/contract.json +147 -0
  272. package/skills/cli-appendix-job-outline/references/flag-order-reminders.md +16 -0
  273. package/skills/cli-appendix-job-outline/references/job-type-matrix.md +13 -0
  274. package/skills/cli-appendix-job-outline/references/stateless-limitations.md +12 -0
  275. package/skills/color-management-decision/EVAL.md +28 -0
  276. package/skills/color-management-decision/SKILL.md +254 -0
  277. package/skills/color-management-decision/contract.json +162 -0
  278. package/skills/color-management-decision/references/look-comparison.md +44 -0
  279. package/skills/color-management-decision/references/per-channel-rules.md +49 -0
  280. package/skills/color-management-decision/references/pipeline-mapping.md +47 -0
  281. package/skills/composition-quality-checker/EVAL.md +38 -0
  282. package/skills/composition-quality-checker/SKILL.md +260 -0
  283. package/skills/composition-quality-checker/contract.json +221 -0
  284. package/skills/composition-quality-checker/references/aspect-ratio-rules.md +37 -0
  285. package/skills/composition-quality-checker/references/composition-rules.md +58 -0
  286. package/skills/composition-quality-checker/references/headroom-leadroom-rules.md +46 -0
  287. package/skills/cycles-vs-eevee-decision/EVAL.md +26 -0
  288. package/skills/cycles-vs-eevee-decision/SKILL.md +249 -0
  289. package/skills/cycles-vs-eevee-decision/contract.json +142 -0
  290. package/skills/cycles-vs-eevee-decision/references/engine-feature-matrix.md +39 -0
  291. package/skills/cycles-vs-eevee-decision/references/gpu-device-rules.md +51 -0
  292. package/skills/cycles-vs-eevee-decision/references/samples-by-quality.md +53 -0
  293. package/skills/done-criteria/EVAL.md +33 -0
  294. package/skills/done-criteria/SKILL.md +225 -0
  295. package/skills/done-criteria/contract.json +199 -0
  296. package/skills/done-criteria/references/done-vs-perfect.md +56 -0
  297. package/skills/done-criteria/references/out-of-scope-patterns.md +50 -0
  298. package/skills/done-criteria/references/stop-condition-templates.md +39 -0
  299. package/skills/environment-shot/EVAL.md +44 -0
  300. package/skills/environment-shot/SKILL.md +237 -0
  301. package/skills/environment-shot/contract.json +162 -0
  302. package/skills/environment-shot/references/depth-layering-rules.md +49 -0
  303. package/skills/environment-shot/references/time-and-weather-rules.md +35 -0
  304. package/skills/environment-shot/references/wide-shot-camera-rules.md +51 -0
  305. package/skills/glb-animation-handoff/EVAL.md +39 -0
  306. package/skills/glb-animation-handoff/SKILL.md +271 -0
  307. package/skills/glb-animation-handoff/contract.json +247 -0
  308. package/skills/glb-animation-handoff/references/animation-types.md +36 -0
  309. package/skills/glb-animation-handoff/references/transition-rules.md +55 -0
  310. package/skills/glb-animation-handoff/references/web-stack-caveats.md +40 -0
  311. package/skills/glb-web-handoff/EVAL.md +33 -0
  312. package/skills/glb-web-handoff/SKILL.md +212 -0
  313. package/skills/glb-web-handoff/contract.json +171 -0
  314. package/skills/glb-web-handoff/references/artifact-status-language.md +26 -0
  315. package/skills/glb-web-handoff/references/glb-handoff-checklist.md +30 -0
  316. package/skills/glb-web-handoff/references/performance-caveats.md +26 -0
  317. package/skills/glb-web-handoff/references/threejs-r3f-handoff.md +28 -0
  318. package/skills/intent-to-3d-brief-writer/EVAL.md +82 -0
  319. package/skills/intent-to-3d-brief-writer/SKILL.md +238 -0
  320. package/skills/intent-to-3d-brief-writer/contract.json +195 -0
  321. package/skills/intent-to-3d-brief-writer/references/acceptance-criteria-patterns.md +46 -0
  322. package/skills/intent-to-3d-brief-writer/references/eight-slot-template.md +123 -0
  323. package/skills/intent-to-3d-brief-writer/references/mixed-audience-handling.md +39 -0
  324. package/skills/interior-scene/EVAL.md +44 -0
  325. package/skills/interior-scene/SKILL.md +261 -0
  326. package/skills/interior-scene/contract.json +277 -0
  327. package/skills/interior-scene/references/furniture-layout-rules.md +51 -0
  328. package/skills/interior-scene/references/interior-architecture-rules.md +47 -0
  329. package/skills/interior-scene/references/interior-camera-rules.md +47 -0
  330. package/skills/lighting-material-plan/EVAL.md +32 -0
  331. package/skills/lighting-material-plan/SKILL.md +194 -0
  332. package/skills/lighting-material-plan/contract.json +213 -0
  333. package/skills/lighting-material-plan/references/cyberpunk-lookdev.md +22 -0
  334. package/skills/lighting-material-plan/references/lighting-patterns.md +30 -0
  335. package/skills/lighting-material-plan/references/material-portability.md +25 -0
  336. package/skills/lighting-material-plan/references/reflective-floor-pattern.md +22 -0
  337. package/skills/lighting-material-plan/references/web-material-simplification.md +23 -0
  338. package/skills/lighting-quality-checker/EVAL.md +41 -0
  339. package/skills/lighting-quality-checker/SKILL.md +247 -0
  340. package/skills/lighting-quality-checker/contract.json +187 -0
  341. package/skills/lighting-quality-checker/references/hdri-balance-rules.md +48 -0
  342. package/skills/lighting-quality-checker/references/intensity-ranges.md +73 -0
  343. package/skills/lighting-quality-checker/references/shadow-softness-rules.md +38 -0
  344. package/skills/material-quality-checker/EVAL.md +40 -0
  345. package/skills/material-quality-checker/SKILL.md +261 -0
  346. package/skills/material-quality-checker/contract.json +244 -0
  347. package/skills/material-quality-checker/references/consumer-stack-rules.md +62 -0
  348. package/skills/material-quality-checker/references/pbr-sanity-rules.md +78 -0
  349. package/skills/material-quality-checker/references/texture-budget-rules.md +48 -0
  350. package/skills/mobile-glb-budget/EVAL.md +40 -0
  351. package/skills/mobile-glb-budget/SKILL.md +264 -0
  352. package/skills/mobile-glb-budget/contract.json +309 -0
  353. package/skills/mobile-glb-budget/references/budget-tiers.md +30 -0
  354. package/skills/mobile-glb-budget/references/degradation-plan.md +34 -0
  355. package/skills/mobile-glb-budget/references/violation-rules.md +43 -0
  356. package/skills/output-format-decision/EVAL.md +27 -0
  357. package/skills/output-format-decision/SKILL.md +222 -0
  358. package/skills/output-format-decision/contract.json +179 -0
  359. package/skills/output-format-decision/references/bit-depth-rules.md +56 -0
  360. package/skills/output-format-decision/references/compression-tradeoffs.md +62 -0
  361. package/skills/output-format-decision/references/format-decision-matrix.md +34 -0
  362. package/skills/pack-prerequisite-checker/EVAL.md +26 -0
  363. package/skills/pack-prerequisite-checker/SKILL.md +272 -0
  364. package/skills/pack-prerequisite-checker/contract.json +214 -0
  365. package/skills/pack-prerequisite-checker/references/blocked-start-playbook.md +21 -0
  366. package/skills/pack-prerequisite-checker/references/pack-readiness-template.md +38 -0
  367. package/skills/pack-prerequisite-checker/references/prerequisite-matrix.md +20 -0
  368. package/skills/path-one-host-outline/EVAL.md +26 -0
  369. package/skills/path-one-host-outline/SKILL.md +251 -0
  370. package/skills/path-one-host-outline/contract.json +167 -0
  371. package/skills/path-one-host-outline/references/connector-vs-manual-matrix.md +21 -0
  372. package/skills/path-one-host-outline/references/host-checklist-template.md +35 -0
  373. package/skills/path-one-host-outline/references/lab-addon-reminders.md +12 -0
  374. package/skills/plain-language-response/EVAL.md +33 -0
  375. package/skills/plain-language-response/SKILL.md +194 -0
  376. package/skills/plain-language-response/contract.json +242 -0
  377. package/skills/plain-language-response/references/caveat-language.md +25 -0
  378. package/skills/plain-language-response/references/plain-language-patterns.md +30 -0
  379. package/skills/plain-language-response/references/stakeholder-friendly-examples.md +30 -0
  380. package/skills/plain-language-response/references/status-summary-templates.md +50 -0
  381. package/skills/polycount-budget-checker/EVAL.md +40 -0
  382. package/skills/polycount-budget-checker/SKILL.md +251 -0
  383. package/skills/polycount-budget-checker/contract.json +196 -0
  384. package/skills/polycount-budget-checker/references/instance-counting-rules.md +39 -0
  385. package/skills/polycount-budget-checker/references/per-mesh-rules.md +43 -0
  386. package/skills/polycount-budget-checker/references/topology-hints.md +56 -0
  387. package/skills/pre-handoff-verification/EVAL.md +84 -0
  388. package/skills/pre-handoff-verification/SKILL.md +252 -0
  389. package/skills/pre-handoff-verification/contract.json +295 -0
  390. package/skills/pre-handoff-verification/references/downgrade-rules.md +39 -0
  391. package/skills/pre-handoff-verification/references/seven-point-checklist.md +46 -0
  392. package/skills/pre-handoff-verification/references/text-only-mode-handling.md +36 -0
  393. package/skills/preview-report/EVAL.md +39 -0
  394. package/skills/preview-report/SKILL.md +254 -0
  395. package/skills/preview-report/contract.json +141 -0
  396. package/skills/preview-report/references/handoff-recipients.md +41 -0
  397. package/skills/preview-report/references/report-schema.md +60 -0
  398. package/skills/preview-report/references/truth-label-rules.md +36 -0
  399. package/skills/product-grid-scene-planner/EVAL.md +42 -0
  400. package/skills/product-grid-scene-planner/SKILL.md +246 -0
  401. package/skills/product-grid-scene-planner/contract.json +257 -0
  402. package/skills/product-grid-scene-planner/references/grid-consistency-rules.md +53 -0
  403. package/skills/product-grid-scene-planner/references/grid-layout-rules.md +42 -0
  404. package/skills/product-grid-scene-planner/references/grid-output-naming-rules.md +52 -0
  405. package/skills/product-hero-scene-planner/EVAL.md +33 -0
  406. package/skills/product-hero-scene-planner/SKILL.md +227 -0
  407. package/skills/product-hero-scene-planner/contract.json +228 -0
  408. package/skills/product-hero-scene-planner/references/clarification-patterns.md +24 -0
  409. package/skills/product-hero-scene-planner/references/cyberpunk-shoe-example.md +28 -0
  410. package/skills/product-hero-scene-planner/references/product-hero-playbooks.md +22 -0
  411. package/skills/product-hero-scene-planner/references/scene-plan-schema.md +35 -0
  412. package/skills/r3f-component-plan/EVAL.md +43 -0
  413. package/skills/r3f-component-plan/SKILL.md +290 -0
  414. package/skills/r3f-component-plan/contract.json +171 -0
  415. package/skills/r3f-component-plan/references/component-shape-patterns.md +54 -0
  416. package/skills/r3f-component-plan/references/suspense-placement-rules.md +50 -0
  417. package/skills/r3f-component-plan/references/usegltf-caching-rules.md +53 -0
  418. package/skills/recipe-fit-assessor/EVAL.md +28 -0
  419. package/skills/recipe-fit-assessor/SKILL.md +266 -0
  420. package/skills/recipe-fit-assessor/contract.json +220 -0
  421. package/skills/recipe-fit-assessor/references/recipe-catalog.md +30 -0
  422. package/skills/recipe-fit-assessor/references/scope-gap-rules.md +27 -0
  423. package/skills/recipe-fit-assessor/references/workflow-recommendation-template.md +34 -0
  424. package/skills/render-export-evidence/EVAL.md +86 -0
  425. package/skills/render-export-evidence/SKILL.md +339 -0
  426. package/skills/render-export-evidence/contract.json +206 -0
  427. package/skills/render-export-evidence/references/attempted-vs-failed-rubric.md +75 -0
  428. package/skills/render-export-evidence/references/evidence-record-templates.md +143 -0
  429. package/skills/render-export-evidence/references/truth-label-decision-tree.md +57 -0
  430. package/skills/resolution-aspect-decision/EVAL.md +26 -0
  431. package/skills/resolution-aspect-decision/SKILL.md +246 -0
  432. package/skills/resolution-aspect-decision/contract.json +160 -0
  433. package/skills/resolution-aspect-decision/references/aspect-defaults.md +41 -0
  434. package/skills/resolution-aspect-decision/references/print-vs-screen-rules.md +58 -0
  435. package/skills/resolution-aspect-decision/references/resolution-defaults.md +64 -0
  436. package/skills/runtime-attempt-report/EVAL.md +26 -0
  437. package/skills/runtime-attempt-report/SKILL.md +268 -0
  438. package/skills/runtime-attempt-report/contract.json +176 -0
  439. package/skills/runtime-attempt-report/references/attempt-record-template.md +49 -0
  440. package/skills/runtime-attempt-report/references/triage-next-steps.md +15 -0
  441. package/skills/runtime-attempt-report/references/truth-label-blocks.md +27 -0
  442. package/skills/runtime-path-picker/EVAL.md +26 -0
  443. package/skills/runtime-path-picker/SKILL.md +268 -0
  444. package/skills/runtime-path-picker/contract.json +191 -0
  445. package/skills/runtime-path-picker/references/anti-patterns.md +14 -0
  446. package/skills/runtime-path-picker/references/decision-tree.md +29 -0
  447. package/skills/runtime-path-picker/references/path-constraints-table.md +18 -0
  448. package/skills/runtime-readiness/EVAL.md +33 -0
  449. package/skills/runtime-readiness/SKILL.md +218 -0
  450. package/skills/runtime-readiness/contract.json +190 -0
  451. package/skills/runtime-readiness/references/blocker-report-template.md +28 -0
  452. package/skills/runtime-readiness/references/evidence-examples.md +23 -0
  453. package/skills/runtime-readiness/references/readiness-matrix.md +46 -0
  454. package/skills/runtime-setup/EVAL.md +33 -0
  455. package/skills/runtime-setup/SKILL.md +209 -0
  456. package/skills/runtime-setup/contract.json +171 -0
  457. package/skills/runtime-setup/references/runtime-option-decision-tree.md +28 -0
  458. package/skills/runtime-setup/references/setup-summary-template.md +33 -0
  459. package/skills/runtime-setup/references/source-confidence-labels.md +23 -0
  460. package/skills/scene-readiness/EVAL.md +33 -0
  461. package/skills/scene-readiness/SKILL.md +195 -0
  462. package/skills/scene-readiness/contract.json +198 -0
  463. package/skills/scene-readiness/references/blocker-catalog.md +24 -0
  464. package/skills/scene-readiness/references/not-run-handling.md +22 -0
  465. package/skills/scene-readiness/references/quality-rubric.md +23 -0
  466. package/skills/scene-readiness/references/verdict-language.md +22 -0
  467. package/skills/scope-guard/EVAL.md +33 -0
  468. package/skills/scope-guard/SKILL.md +222 -0
  469. package/skills/scope-guard/contract.json +171 -0
  470. package/skills/scope-guard/references/options-language-template.md +51 -0
  471. package/skills/scope-guard/references/recurring-creep-patterns.md +55 -0
  472. package/skills/scope-guard/references/scope-addition-classification.md +55 -0
  473. package/skills/stage-gates/EVAL.md +40 -0
  474. package/skills/stage-gates/SKILL.md +257 -0
  475. package/skills/stage-gates/contract.json +490 -0
  476. package/skills/stage-gates/references/failed-gate-handling.md +42 -0
  477. package/skills/stage-gates/references/gate-template.md +46 -0
  478. package/skills/stage-gates/references/stage-decomposition-patterns.md +55 -0
  479. package/skills/workflow-stage-router/EVAL.md +25 -0
  480. package/skills/workflow-stage-router/SKILL.md +259 -0
  481. package/skills/workflow-stage-router/contract.json +150 -0
  482. package/skills/workflow-stage-router/references/milestone-model.md +20 -0
  483. package/skills/workflow-stage-router/references/routing-decision-tree.md +32 -0
  484. package/skills/workflow-stage-router/references/stage-handoff-template.md +37 -0
  485. package/skills.sh.json +102 -0
@@ -0,0 +1,252 @@
1
+ ---
2
+ name: pre-handoff-verification
3
+ description: Verification gate before claiming any deliverable is ready. Forces evidence checks (path, file existence, validation notes) per evidence-before-done law. Use before any 'Verified' claim.
4
+ ---
5
+
6
+ # pre-handoff-verification
7
+
8
+ ## Purpose
9
+
10
+ Run a structured verification pass before any BlendOps output is handed to the user as "ready" or "Verified". Forces explicit evidence checks per the `evidence-before-done` law and downgrades any unsupported claim to a lower truth label.
11
+
12
+ Inspired by the `/verification-before-completion` skill in Anthropic Superpowers, adapted for the BlendOps evidence-before-done discipline.
13
+
14
+ This skill **complements** `render-export-evidence` (which classifies artifact evidence) by enforcing the discipline at the moment of handoff, not just at evidence recording.
15
+
16
+ ## Quick start
17
+
18
+ - read the proposed handoff (response text, artifact list, evidence fields)
19
+ - run the 7-point verification checklist
20
+ - downgrade any unsupported claim explicitly
21
+ - gate handoff on all 7 checks passing or explicit caveats
22
+
23
+ ## When to use
24
+
25
+ - `workflow-stage-router` routes here as the final gate before handoff, or exits here on any failed upstream gate to lock in an honest downgraded truth label
26
+ - `blendops-help` routes a user directly to verify an existing deliverable or evidence claim
27
+ - a planner / executor / response writer says "the output is ready"
28
+ - before saving an evidence file under `docs/evals/path-X-...md` via `runtime-attempt-report` or `render-export-evidence`
29
+ - before answering a user with `Verified` or `Produced` status
30
+ - before tagging a release or confirming whether a claim holds or must be downgraded
31
+ - when the operator is tempted to claim "done" but evidence is fuzzy
32
+
33
+ ## When not to use
34
+ <!-- blendops:generated:start exclusions -->
35
+ - the workflow is still in planning / brainstorming / brief stage (no claim to verify yet) → use `../scene-readiness/SKILL.md` (no claim to verify yet)
36
+ - the user explicitly asked for a draft, not a verified deliverable → use `../blender-troubleshooting/SKILL.md` (Delegates out-of-scope requests to blender-troubleshooting)
37
+ - runtime status is Not Run and the user knows it (no verification needed when Not Run is the explicit state) → use `../render-export-evidence/SKILL.md` (no verification needed when Not Run is the explicit state)
38
+ <!-- blendops:generated:end exclusions -->
39
+
40
+ ## Trigger phrases
41
+ <!-- blendops:generated:start triggers -->
42
+ - "looks ready, can we ship?"
43
+ - "I think the render is good — verify before sending"
44
+ - "before saving the evidence file..."
45
+ - "is this Verified or do we downgrade?"
46
+ - "confirm whether this claim holds or must be downgraded"
47
+ <!-- blendops:generated:end triggers -->
48
+
49
+ ## Prerequisites / readiness
50
+
51
+ - a proposed handoff exists (response text, file paths, status claims)
52
+ - evidence sources exist (file paths, logs, validation notes)
53
+ - ability to read evidence without modifying it; no Blender execution required
54
+
55
+ ## Input schema
56
+
57
+ ### Required inputs
58
+
59
+ - proposed handoff content (response or evidence file draft)
60
+ - runtime truth state claimed (`Not Run` | `Attempted` | `Produced` | `Verified` | `Failed`)
61
+ - artifact truth state claimed (`Not Run` | `Not Produced` | `Produced` | `Verified` | `Failed`; default `Not Produced`)
62
+ - artifact paths referenced (if any)
63
+ - runtime path used:
64
+ - Path 1: Official Blender Lab MCP in Blender 5.1+ (`blender_version_min = "5.1.0"`), hosted from (a) Anthropic Connector in Claude Desktop (installs the Lab add-on inside Blender; not standalone) or (b) any manually configured MCP client
65
+ - Path 2: community `mcp-for-blender` (Blender 3.0+, with explicit caveats, never release evidence)
66
+ - CLI fallback: appendix only (`blender --background --python`, never a peer path without an eval record)
67
+ - Text-only (no runtime executed)
68
+
69
+ ### Optional inputs
70
+
71
+ - prior evidence record paths
72
+ - validation notes from `scene-readiness`, `material-quality-checker`, `lighting-quality-checker`, `composition-quality-checker`, `polycount-budget-checker`, or `render-export-evidence`
73
+ - user's explicit acceptance level ("draft is fine" vs. "must be production-ready")
74
+
75
+ ### Assumptions to confirm
76
+
77
+ - the proposed claim is the maximum truth label justified by evidence (downgrade-only, never upgrade)
78
+ - file paths are real and inspectable, not invented
79
+ - the operator can pause before handoff to downgrade unsupported claims or gather missing evidence upstream
80
+
81
+ ## Output schema
82
+
83
+ ### Primary output
84
+
85
+ - verification verdict: Pass / Warn / Fail
86
+ - if Pass: confirmed status label
87
+ - if Warn / Fail: downgraded status label + reason
88
+
89
+ ### Secondary output
90
+
91
+ - 7-point verification record
92
+ - specific missing evidence per failed check
93
+
94
+ ### Evidence / caveat output
95
+
96
+ - explicit downgrade reasoning
97
+ - no claim is upgraded; only downgraded or kept
98
+
99
+ ## Required laws
100
+
101
+ - ../../laws/evidence-before-done.md
102
+ - ../../laws/non-blender-user-language.md
103
+ - ../../laws/no-arbitrary-python-interface.md
104
+ - ../../laws/official-runtime-only.md
105
+
106
+ ## Official runtime boundary
107
+
108
+ This skill does not run Blender, mutate scenes, or generate artifacts. It reads the proposed handoff and existing evidence, and either confirms or downgrades the truth label.
109
+
110
+ ## Operating procedure
111
+
112
+ Run all 7 checks. Each applicable check must pass before a claim is upheld; otherwise downgrade.
113
+
114
+ 1. **Claim is named explicitly** — handoff states an exact runtime truth label (`Not Run` | `Attempted` | `Produced` | `Verified` | `Failed`) and artifact truth label (`Not Run` | `Not Produced` | `Produced` | `Verified` | `Failed`, defaulting to `Not Produced`). No vague "ready" / "done" / "good".
115
+ 2. **Path attribution and boundary compliance are explicit** — runtime path is named: Path 1 host (a) Anthropic Connector in Claude Desktop or host (b) manually configured MCP client on Blender 5.1+ (`blender_version_min = "5.1.0"`); Path 2 (`mcp-for-blender`, Blender 3.0+, caveated only and **never release evidence**); CLI appendix (`blender --background --python`, **never a peer path without an eval record**); or text-only. Reject "we used the connector" without host attribution or with standalone/pre-5.1 claims.
116
+ 3. **Artifact paths exist** — for any `Produced` or `Verified` artifact claim, every referenced file path exists and is inspectable. If artifact state is `Not Produced` or `Not Run`, no artifact path is asserted.
117
+ 4. **Validation notes present** — for any `Verified` claim, validation notes record what was checked and how it passed. Empty validation = automatic downgrade to `Produced` (or lower).
118
+ 5. **Tool / command names recorded** — exact verified tool or CLI names are recorded:
119
+ - Path 1 read-only: `get_blendfile_summary_path_info`, `get_blendfile_summary_datablocks`, `get_objects_summary`, `get_object_detail_summary`, and `*_for_cli` variants
120
+ - Path 1 mutation: `execute_blender_code`
121
+ - Path 2: `get_scene_info`, `execute_blender_code` (within its 9-tool surface)
122
+ - CLI appendix: exact `blender` command using documented flags (`--background`, `--python`, `-E`/`--engine`; run `blender -E help` for exact engine tokens)
123
+ 6. **No-mutation guarantee for read-only smoke** — if the claim is read-only smoke evidence, explicit confirmation that `execute_blender_code` was not called on either backend.
124
+ 7. **Plain-language summary present** — final user-facing text passes `non-blender-user-language` check (no unexplained Blender/MCP internals).
125
+
126
+ ## Decision tree
127
+
128
+ - all 7 checks pass → confirm truth label, allow handoff
129
+ - 1-2 checks warn on non-blocking metadata (e.g., minor jargon explained inline) AND all required evidence for the truth label exists → keep truth label only with explicit caveat; if validation notes are missing on `Verified` or Path 2 is used as release evidence, mandatory downgrade applies
130
+ - any required evidence check fails or 3+ checks fail → downgrade claim by one or more truth steps to the highest label strictly supported by evidence; explain downgrade
131
+ - check 1 fails (no valid truth label named) → block handoff and downgrade to `Not Run` / `Not Produced` until an explicit truth label is set
132
+
133
+ ## Playbooks
134
+
135
+ - Playbook A: "Operator wants to confirm `Verified`" — run all 7 checks; downgrade to `Produced` if validation notes (check 4) are missing, or to `Attempted` / `Not Produced` if artifact paths (check 3) are missing. Ensure Path 2 is never accepted as release evidence.
136
+ - Playbook B: "Operator wants to confirm read-only smoke test evidence" — run all 7 checks: confirm runtime truth label (check 1), Path 1 host a/b on Blender 5.1+ or caveated Path 2 (check 2), artifact state `Not Produced` (check 3), smoke validation notes (check 4), read-only tool names recorded (check 5), explicit no-`execute_blender_code` guarantee (check 6), and plain-language summary (check 7).
137
+ - Playbook C: "Final user-facing response" — run all 7 checks with strict enforcement of check 7 via `plain-language-response`.
138
+ - Playbook D: "Evidence file save" — run checks 1-6 strictly for the record (`runtime-attempt-report` / `render-export-evidence`), and check 7 for any user-facing summary section.
139
+
140
+ ## Mode handling
141
+
142
+ ### Text-only mode
143
+
144
+ - verifies a text-only deliverable (plan, brief, response) — checks 1, 2, 7 apply; checks 3-6 marked N/A explicitly
145
+ - runtime status: must be `Not Run` (if input claims `Attempted`, `Produced`, or `Verified` without runtime execution, downgrade to `Not Run`)
146
+ - artifact status: must be `Not Produced` (downgrade any higher claim)
147
+
148
+ ### Runtime-ready mode
149
+
150
+ - all 7 checks apply
151
+ - if checks 3-6 fail and operator wants `Verified`, downgrade runtime state to `Produced`, `Attempted`, or `Failed` and artifact state to `Produced` or `Not Produced` per actual evidence
152
+
153
+ ### Blocked runtime mode
154
+
155
+ - Entered when `workflow-stage-router` exits here on a failed readiness or execution gate
156
+ - checks 1, 2, 7 apply; checks 3-6 marked N/A or Failed per upstream block
157
+ - enforce downgrade: runtime status cannot exceed `Not Run`, `Attempted`, or `Failed`, and artifact status must be `Not Produced` (or `Failed`) — no `Verified` or `Produced` claim may leak past a blocked gate
158
+
159
+ ## Validation checklist
160
+
161
+ - [ ] claim label named explicitly
162
+ - [ ] runtime path attributed (path + host or text-only)
163
+ - [ ] artifact paths exist or `Not Produced` is honest
164
+ - [ ] validation notes present for `Verified`
165
+ - [ ] tool / command names recorded
166
+ - [ ] no-mutation guarantee for read-only smoke
167
+ - [ ] plain-language user-facing summary
168
+ - [ ] downgrade reasoning explicit when applied
169
+ - [ ] no claim upgraded by this skill
170
+
171
+ ## Pass / Warn / Fail rubric
172
+
173
+ | Category | Pass | Warn | Fail |
174
+ |---|---|---|---|
175
+ | Claim named | Explicit truth label | Vague but downgrade applied | "ready" / "done" allowed through |
176
+ | Path attribution | Path + host or text-only | Path named, host ambiguous | No path attribution |
177
+ | Artifact paths | All exist or honestly absent | Some exist, missing flagged | Path asserted but not inspectable |
178
+ | Validation notes | Present for `Verified` | Missing but `Verified` downgraded to `Produced` | `Verified` claimed without notes |
179
+ | Tool names | All recorded | Partial, gap flagged | Path claimed without tool names |
180
+ | No-mutation guarantee | Explicit for read-only | Implicit but consistent | Smoke claim with mutation tools |
181
+ | Plain language | No jargon | Minor jargon explained | Jargon-heavy user response |
182
+
183
+ ## Failure handling
184
+
185
+ - check fails: downgrade runtime and/or artifact claim to the highest truth label strictly proven by existing evidence. Re-run remaining checks.
186
+ - when entered via `workflow-stage-router` failed-gate exit: lock in the downgraded truth label (`Not Run`, `Attempted`, or `Failed` for runtime; `Not Produced` or `Failed` for artifact) and state the exact upstream gate that failed.
187
+ - operator attempts to override downgrade: refuse to upgrade or keep an unsupported truth label. Log the discrepancy in the verification record and output only the downgraded label.
188
+ - evidence file would misrepresent path, version floor, or artifact existence: block handoff and force honest downgrade.
189
+
190
+ ## Troubleshooting
191
+
192
+ - if 3+ checks fail, the workflow upstream has bigger problems — route to `blender-troubleshooting`.
193
+ - if check 7 fails repeatedly, route through `plain-language-response` before re-attempting verification.
194
+
195
+ ## Best practices
196
+
197
+ - run before every handoff, not just before release
198
+ - never upgrade a claim; only downgrade or keep
199
+ - explicit caveats are better than soft language
200
+
201
+ ## Good examples
202
+
203
+ - "Operator wants Verified for cyberpunk-shoe-render. 7-check pass: claim explicit, Path 1 host a, artifact paths exist (`renders/preview-2026-05-09.png`), validation notes record subject framing + lighting + neon mood checks pass, tool `execute_blender_code` recorded, no smoke guarantee needed (this is a render not smoke), plain-language summary clean. Verdict: Pass. Verified upheld."
204
+
205
+ ## Bad examples
206
+
207
+ - "The render is ready." (no truth label, no path attribution, no artifact path, no validation, no tool names, no plain-language check — would fail all 7)
208
+
209
+ ## User-facing response template
210
+
211
+ - Claim being verified
212
+ - 7-check verdict (each check Pass/Warn/Fail with one-line reason)
213
+ - Final status (claim upheld or downgraded with explicit reason)
214
+ - What is allowed to be said next
215
+
216
+ ## Anti-patterns
217
+
218
+ - letting "ready" / "done" / "looks good" stand as a truth label
219
+ - upgrading a claim based on operator confidence (this skill only downgrades)
220
+ - skipping checks because the operator is tired
221
+ - treating a passed read-only smoke as a `Verified` for mutation/render/export
222
+
223
+ ## Cross-skill handoff
224
+ <!-- blendops:generated:start handoffs -->
225
+ - [boundary_delegation] Entry wiring (blendops-help) → `../blendops-help/SKILL.md`
226
+ - [upstream_reference] Entry wiring (workflow-stage-router) → `../workflow-stage-router/SKILL.md`
227
+ - [conditional] If verdict is Pass (plain-language-response) → `../plain-language-response/SKILL.md`
228
+ - [upstream_reference] If verdict is Pass (render-export-evidence) → `../render-export-evidence/SKILL.md`
229
+ - [upstream_reference] If verdict is Pass (runtime-attempt-report) → `../runtime-attempt-report/SKILL.md`
230
+ - [upstream_reference] scene/asset quality gap (scene-readiness) → `../scene-readiness/SKILL.md`
231
+ - [upstream_reference] scene/asset quality gap (composition-quality-checker) → `../composition-quality-checker/SKILL.md`
232
+ - [upstream_reference] scene/asset quality gap (lighting-quality-checker) → `../lighting-quality-checker/SKILL.md`
233
+ - [upstream_reference] scene/asset quality gap (material-quality-checker) → `../material-quality-checker/SKILL.md`
234
+ - [upstream_reference] scene/asset quality gap (polycount-budget-checker) → `../polycount-budget-checker/SKILL.md`
235
+ - [fallback] runtime/bridge failure (blender-troubleshooting) → `../blender-troubleshooting/SKILL.md`
236
+ - [fallback] runtime/bridge failure (runtime-readiness) → `../runtime-readiness/SKILL.md`
237
+ - [fallback] runtime/bridge failure (bridge-conflicts) → `../bridge-conflicts/SKILL.md`
238
+ <!-- blendops:generated:end handoffs -->
239
+
240
+ ## Non-goals
241
+
242
+ - running Blender
243
+ - generating evidence
244
+ - upgrading claims
245
+ - replacing `render-export-evidence` (that classifies; this gates handoff)
246
+
247
+ ## References
248
+
249
+ - Inspired by Anthropic Superpowers `/verification-before-completion` skill (https://github.com/anthropics/skills)
250
+ - BlendOps law: ../../laws/evidence-before-done.md
251
+ - BlendOps skill: ../../skills/render-export-evidence/SKILL.md
252
+ - Skill system: ../../docs/skill-system.md
@@ -0,0 +1,295 @@
1
+ {
2
+ "$schema": "../../schemas/skill-contract.schema.json",
3
+ "id": "pre-handoff-verification",
4
+ "version": "1.0.0",
5
+ "category": "evidence-and-handoff",
6
+ "role": "final-7-point-release-gate",
7
+ "purpose": "Verification gate before claiming any deliverable is ready. Forces evidence checks (path, file existence, validation notes) per evidence-before-done law. Use before any 'Verified' claim.",
8
+ "capabilityTier": "L0",
9
+ "triggers": [
10
+ "looks ready, can we ship?",
11
+ "I think the render is good — verify before sending",
12
+ "before saving the evidence file...",
13
+ "is this Verified or do we downgrade?",
14
+ "confirm whether this claim holds or must be downgraded"
15
+ ],
16
+ "exclusions": [
17
+ {
18
+ "condition": "the workflow is still in planning / brainstorming / brief stage (no claim to verify yet)",
19
+ "delegateTo": "scene-readiness",
20
+ "reason": "no claim to verify yet"
21
+ },
22
+ {
23
+ "condition": "the user explicitly asked for a draft, not a verified deliverable",
24
+ "delegateTo": "blender-troubleshooting",
25
+ "reason": "Delegates out-of-scope requests to blender-troubleshooting"
26
+ },
27
+ {
28
+ "condition": "runtime status is Not Run and the user knows it (no verification needed when Not Run is the explicit state)",
29
+ "delegateTo": "render-export-evidence",
30
+ "reason": "no verification needed when Not Run is the explicit state"
31
+ }
32
+ ],
33
+ "inputs": {
34
+ "required": [
35
+ {
36
+ "name": "candidate_delivery_package",
37
+ "type": "object",
38
+ "description": "Complete set of planning, quality validation, runtime attempt, and artifact evidence records"
39
+ },
40
+ {
41
+ "name": "proposed_truth_state_claims",
42
+ "type": "object",
43
+ "description": "Proposed Runtime status and Artifact status labels to audit against the 7-point release gate"
44
+ }
45
+ ],
46
+ "optional": [
47
+ {
48
+ "name": "active_blocker_or_failed_gate_notes",
49
+ "type": "array",
50
+ "description": "Any upstream Warn/Fail quality verdicts or unresolved runtime blockers"
51
+ }
52
+ ]
53
+ },
54
+ "outputs": {
55
+ "primary": [
56
+ "seven_point_release_gate_table",
57
+ "enforced_downgrade_only_truth_states",
58
+ "release_clearance_or_remediation_route"
59
+ ],
60
+ "truthStatePolicy": {
61
+ "runtimeDefault": "Not Run",
62
+ "artifactDefault": "Not Produced",
63
+ "mutationRule": "downgrade_only"
64
+ }
65
+ },
66
+ "handoffs": [
67
+ {
68
+ "target": "blendops-help",
69
+ "type": "boundary_delegation",
70
+ "label": "Entry wiring (blendops-help)",
71
+ "when": {
72
+ "all": [
73
+ {
74
+ "field": "request.scope",
75
+ "operator": "equals",
76
+ "value": "general_help"
77
+ }
78
+ ]
79
+ }
80
+ },
81
+ {
82
+ "target": "workflow-stage-router",
83
+ "type": "upstream_reference",
84
+ "label": "Entry wiring (workflow-stage-router)",
85
+ "when": {
86
+ "all": [
87
+ {
88
+ "field": "preflight.passed",
89
+ "operator": "equals",
90
+ "value": true
91
+ },
92
+ {
93
+ "field": "inventory.exists",
94
+ "operator": "equals",
95
+ "value": true
96
+ }
97
+ ]
98
+ }
99
+ },
100
+ {
101
+ "target": "plain-language-response",
102
+ "type": "conditional",
103
+ "label": "If verdict is Pass (plain-language-response)",
104
+ "when": {
105
+ "all": [
106
+ {
107
+ "field": "stage.current",
108
+ "operator": "equals",
109
+ "value": "final_communication"
110
+ }
111
+ ]
112
+ }
113
+ },
114
+ {
115
+ "target": "render-export-evidence",
116
+ "type": "upstream_reference",
117
+ "label": "If verdict is Pass (render-export-evidence)",
118
+ "when": {
119
+ "all": [
120
+ {
121
+ "field": "stage.current",
122
+ "operator": "equals",
123
+ "value": "post_execution_audit"
124
+ }
125
+ ]
126
+ }
127
+ },
128
+ {
129
+ "target": "runtime-attempt-report",
130
+ "type": "upstream_reference",
131
+ "label": "If verdict is Pass (runtime-attempt-report)",
132
+ "when": {
133
+ "all": [
134
+ {
135
+ "field": "runtime.status",
136
+ "operator": "in",
137
+ "value": [
138
+ "Attempted",
139
+ "Produced",
140
+ "Verified",
141
+ "Failed"
142
+ ]
143
+ },
144
+ {
145
+ "field": "request.topic",
146
+ "operator": "equals",
147
+ "value": "attempt_report"
148
+ }
149
+ ]
150
+ }
151
+ },
152
+ {
153
+ "target": "scene-readiness",
154
+ "type": "upstream_reference",
155
+ "label": "scene/asset quality gap (scene-readiness)",
156
+ "when": {
157
+ "all": [
158
+ {
159
+ "field": "quality.domain",
160
+ "operator": "equals",
161
+ "value": "holistic"
162
+ },
163
+ {
164
+ "field": "stage.current",
165
+ "operator": "equals",
166
+ "value": "quality_validation"
167
+ }
168
+ ]
169
+ }
170
+ },
171
+ {
172
+ "target": "composition-quality-checker",
173
+ "type": "upstream_reference",
174
+ "label": "scene/asset quality gap (composition-quality-checker)",
175
+ "when": {
176
+ "all": [
177
+ {
178
+ "field": "quality.domain",
179
+ "operator": "equals",
180
+ "value": "composition"
181
+ },
182
+ {
183
+ "field": "quality.verdict",
184
+ "operator": "equals",
185
+ "value": "not_run"
186
+ }
187
+ ]
188
+ }
189
+ },
190
+ {
191
+ "target": "lighting-quality-checker",
192
+ "type": "upstream_reference",
193
+ "label": "scene/asset quality gap (lighting-quality-checker)",
194
+ "when": {
195
+ "all": [
196
+ {
197
+ "field": "quality.domain",
198
+ "operator": "equals",
199
+ "value": "lighting"
200
+ },
201
+ {
202
+ "field": "quality.verdict",
203
+ "operator": "equals",
204
+ "value": "not_run"
205
+ }
206
+ ]
207
+ }
208
+ },
209
+ {
210
+ "target": "material-quality-checker",
211
+ "type": "upstream_reference",
212
+ "label": "scene/asset quality gap (material-quality-checker)",
213
+ "when": {
214
+ "all": [
215
+ {
216
+ "field": "quality.domain",
217
+ "operator": "equals",
218
+ "value": "material"
219
+ },
220
+ {
221
+ "field": "quality.verdict",
222
+ "operator": "equals",
223
+ "value": "not_run"
224
+ }
225
+ ]
226
+ }
227
+ },
228
+ {
229
+ "target": "polycount-budget-checker",
230
+ "type": "upstream_reference",
231
+ "label": "scene/asset quality gap (polycount-budget-checker)",
232
+ "when": {
233
+ "all": [
234
+ {
235
+ "field": "quality.domain",
236
+ "operator": "equals",
237
+ "value": "polycount"
238
+ },
239
+ {
240
+ "field": "budget.verdict",
241
+ "operator": "equals",
242
+ "value": "Not Run"
243
+ }
244
+ ]
245
+ }
246
+ },
247
+ {
248
+ "target": "blender-troubleshooting",
249
+ "type": "fallback",
250
+ "label": "runtime/bridge failure (blender-troubleshooting)",
251
+ "when": {
252
+ "all": [
253
+ {
254
+ "field": "runtime.errorDetected",
255
+ "operator": "equals",
256
+ "value": true
257
+ }
258
+ ]
259
+ }
260
+ },
261
+ {
262
+ "target": "runtime-readiness",
263
+ "type": "fallback",
264
+ "label": "runtime/bridge failure (runtime-readiness)",
265
+ "when": {
266
+ "all": [
267
+ {
268
+ "field": "runtime.path",
269
+ "operator": "not_equals",
270
+ "value": "unselected"
271
+ },
272
+ {
273
+ "field": "runtime.verifiedReady",
274
+ "operator": "equals",
275
+ "value": false
276
+ }
277
+ ]
278
+ }
279
+ },
280
+ {
281
+ "target": "bridge-conflicts",
282
+ "type": "fallback",
283
+ "label": "runtime/bridge failure (bridge-conflicts)",
284
+ "when": {
285
+ "all": [
286
+ {
287
+ "field": "runtime.conflictDetected",
288
+ "operator": "equals",
289
+ "value": true
290
+ }
291
+ ]
292
+ }
293
+ }
294
+ ]
295
+ }
@@ -0,0 +1,39 @@
1
+ # Downgrade Rules
2
+
3
+ This skill **never upgrades** a claim. It either confirms or downgrades. Use this table when checks fail.
4
+
5
+ ## Downgrade matrix
6
+
7
+ | Original claim | Failed check | Downgrade to |
8
+ |---|---|---|
9
+ | `Verified` | check 4 (validation notes missing) | `Produced` |
10
+ | `Verified` | check 3 (artifact paths missing) | `Attempted` |
11
+ | `Verified` | check 5 (tool names missing) | `Attempted` |
12
+ | `Produced` | check 3 (artifact paths missing) | `Attempted` |
13
+ | `Produced` | check 5 (tool names missing) | `Attempted` |
14
+ | Smoke `Pass` | check 6 (mutation tool found in list) | non-smoke evidence; relabel as `Produced` if file exists, else `Attempted` |
15
+ | Any | check 1 (no truth label named) | **Reject handoff** until operator names a label |
16
+ | Any | check 2 (no path attribution) | Add caveat; downgrade by one truth step until attribution recorded |
17
+ | Any | check 7 (jargon-heavy user-facing summary) | Send back to `plain-language-response` before retrying |
18
+
19
+ ## Multiple-failure rule
20
+
21
+ If 3+ checks fail simultaneously, downgrade to the **lowest justified label** and route to `blender-troubleshooting`.
22
+
23
+ | Number of failures | Action |
24
+ |---|---|
25
+ | 0 | Claim upheld. Handoff proceeds. |
26
+ | 1 | Downgrade by one truth step. Note in evidence record. |
27
+ | 2 | Downgrade by one or two truth steps depending on severity. Note explicitly. |
28
+ | 3+ | Downgrade to lowest justified label + route to `blender-troubleshooting` for upstream diagnosis. |
29
+
30
+ ## Override handling
31
+
32
+ If the operator overrides the downgrade ("ignore the verification, mark Verified anyway"):
33
+
34
+ 1. **Log the override explicitly** in the evidence record. Use the exact wording: "Operator override: claim retained as <X> despite check <N> failure. Reason given: <reason>."
35
+ 2. **Do not change the check result.** Check N stays Fail.
36
+ 3. **Flag the override in `pre-handoff-verification` rubric** as a Fail in the "no-claim-upgrade" axis.
37
+ 4. **Hand off downstream with the override caveat visible** so the next reader sees the discrepancy.
38
+
39
+ This skill never silently upgrades a claim. An operator override is an explicit, logged, downstream-visible exception.
@@ -0,0 +1,46 @@
1
+ # 7-Point Verification Checklist
2
+
3
+ Run all 7 before any handoff. Each must Pass (or be N/A in text-only mode for checks 3-6) before claim is upheld.
4
+
5
+ ## Checklist with examples
6
+
7
+ | # | Check | Pass example | Fail example |
8
+ |---|---|---|---|
9
+ | 1 | **Claim is named explicitly** (one of `Not Run` / `Attempted` / `Produced` / `Verified` / `Failed`). No vague "ready" / "done" / "good". | "Verified for Path 1 host (a) Anthropic Connector render of cyberpunk shoe." | "It's ready, ship it." |
10
+ | 2 | **Path attribution is explicit** (Path 1 host a/b, Path 2, CLI fallback, or text-only). | "Path 1, host (a) Anthropic Connector, Blender 5.1.0." | "We used the connector." |
11
+ | 3 | **Artifact paths exist** for any `Produced` or `Verified` claim. | `renders/preview-2026-05-09.png` resolves; `exports/hero.glb` resolves. | "The render is at renders/preview.png" but file does not exist on disk. |
12
+ | 4 | **Validation notes present** for any `Verified` claim. | "Subject framing centered, neon visible, GLB ≤ 10MB, web import test passed." | (Empty validation field; just a file path.) |
13
+ | 5 | **Tool / command names recorded** for any runtime claim. | Path 1: `execute_blender_code` recorded (mutation) or read-only summary tools recorded (smoke). Path 2: `get_scene_info` + `execute_blender_code`. CLI: exact `blender --background --python` command. | "We ran Blender." (no tool names) |
14
+ | 6 | **No-mutation guarantee** for any read-only smoke claim. | Tool list = `get_blendfile_summary_path_info`, `get_objects_summary`. No `execute_blender_code` on either backend. | Smoke claim with `execute_blender_code` in the tool list. |
15
+ | 7 | **Plain-language summary** passes `non-blender-user-language` check. | "Your render is ready. The shoe is centered, the neon mood is visible, and the GLB is small enough for web." | "BSDF subsurf scattering applied; topology budget at 8k tris; tangent-space NaN handled." |
16
+
17
+ ## Mode-aware applicability
18
+
19
+ | Claim type | Checks 1, 2, 7 | Checks 3, 4, 5, 6 |
20
+ |---|---|---|
21
+ | Text-only plan / brief | Required | Mark **N/A explicitly** |
22
+ | Read-only smoke evidence | Required | Required (check 6 especially important) |
23
+ | Mutation / render / export claim | Required | Required |
24
+ | Final user-facing response | Required | Required if response cites runtime claims |
25
+
26
+ ## The Iron Law & Red Flags (Anti-Rationalization)
27
+
28
+ > **Violating the letter of the verification gate is violating the spirit of the verification gate. NO `Verified` or `Produced` CLAIM WITHOUT FRESH, INSPECTABLE EVIDENCE.**
29
+
30
+ ### Red Flags — STOP and Downgrade Immediately
31
+
32
+ - Using hedging language as proof ("should work", "probably rendered", "looks clean", "seems ready")
33
+ - Expressing completion before running checks ("Done!", "Perfect!", "Ship it!")
34
+ - Treating a read-only smoke test as evidence that scene mutation, rendering, or GLB export succeeded
35
+ - Treating Path 2 (`mcp-for-blender`) transcripts as official Draft/Release certification
36
+ - Citing an old or unlinked pre-existing file without proving current-run provenance
37
+
38
+ ### Rationalization Prevention Table
39
+
40
+ | Excuse | Reality |
41
+ |---|---|
42
+ | "The MCP call returned success, so the artifact is Verified." | A tool call transcript without a verified disk path and validation notes stays capped at `Produced` (or `Attempted`). |
43
+ | "I already inspected the render mentally / from code." | Visual and structural checks require inspectable output artifacts; mental confidence is not evidence. |
44
+ | "Just this once, the user knows what I mean by 'ready'." | Vague claims hide failure states. Name one exact state (`Not Run` / `Attempted` / `Produced` / `Verified` / `Failed`). |
45
+ | "The smoke test passed, so Path 1 works end-to-end." | Smoke pass confirms read-only connectivity only (`Artifact status: Not Produced`). Never extrapolate to render/export. |
46
+ | "Different wording means the 7-point gate doesn't apply." | Paraphrases of "finished" or "complete" trigger the same 7 checks. |
@@ -0,0 +1,36 @@
1
+ # Text-Only Mode Handling
2
+
3
+ When the deliverable is a plan / brief / response (not a runtime artifact), checks 3-6 are **N/A**, not Skipped or Failed. This file is the canonical reference for that distinction.
4
+
5
+ ## What "text-only mode" means
6
+
7
+ A handoff is text-only when **no runtime artifact is referenced or claimed**:
8
+
9
+ - a confirmed brief from `intent-to-3d-brief-writer`
10
+ - a scene plan from `product-hero-scene-planner`
11
+ - a composition / lighting / material plan
12
+ - a non-Blender-user response that summarizes status only
13
+ - a brainstorming output
14
+
15
+ In text-only mode, only checks **1, 2, 7** apply.
16
+
17
+ ## How to mark N/A
18
+
19
+ For every check that is N/A, **explicitly write `N/A` plus the reason**, not blank, not skipped:
20
+
21
+ | Check | N/A note example |
22
+ |---|---|
23
+ | 3 (artifact paths exist) | `N/A — text-only deliverable, no artifact path asserted.` |
24
+ | 4 (validation notes) | `N/A — no `Verified` claim made; deliverable is a plan, not a runtime output.` |
25
+ | 5 (tool names recorded) | `N/A — no runtime tool was called; deliverable is a plan.` |
26
+ | 6 (no-mutation guarantee) | `N/A — no runtime smoke; deliverable is a plan.` |
27
+
28
+ ## Anti-patterns
29
+
30
+ - Skipping checks silently. Always write N/A + reason.
31
+ - Treating "the operator might run this later" as a runtime claim. Until runtime evidence exists, the deliverable is text-only.
32
+ - Letting check 7 (plain language) lapse just because checks 3-6 are N/A. Plain language always applies for user-facing text.
33
+
34
+ ## Promotion to runtime mode
35
+
36
+ If the deliverable is later combined with runtime evidence (e.g. plan + actual render), re-run **all 7 checks**. The previously-N/A checks 3-6 become required.