tribunal-kit 9.0.1 → 9.2.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (625) hide show
  1. package/.agent/agents/backend-specialist.md +1 -1
  2. package/.agent/agents/code-archaeologist.md +1 -1
  3. package/.agent/agents/database-architect.md +1 -1
  4. package/.agent/agents/debugger.md +1 -1
  5. package/.agent/agents/devops-engineer.md +1 -1
  6. package/.agent/agents/documentation-writer.md +1 -1
  7. package/.agent/agents/explorer-agent.md +1 -1
  8. package/.agent/agents/game-developer.md +1 -1
  9. package/.agent/agents/minimalist-reviewer.md +1 -1
  10. package/.agent/agents/mobile-developer.md +1 -1
  11. package/.agent/agents/orchestrator.md +42 -2
  12. package/.agent/agents/penetration-tester.md +1 -1
  13. package/.agent/agents/performance-optimizer.md +1 -1
  14. package/.agent/agents/product-manager.md +1 -1
  15. package/.agent/agents/product-owner.md +1 -1
  16. package/.agent/agents/project-planner.md +1 -1
  17. package/.agent/agents/qa-automation-engineer.md +1 -1
  18. package/.agent/agents/seo-specialist.md +1 -1
  19. package/.agent/agents/test-engineer.md +1 -1
  20. package/.agent/routing_index.json +265 -1530
  21. package/.agent/scripts/browser_audit.js +13 -5
  22. package/.agent/scripts/bundle_analyzer.js +7 -3
  23. package/.agent/scripts/dependency_analyzer.js +16 -16
  24. package/.agent/scripts/inner_loop_validator.js +1 -1
  25. package/.agent/scripts/payload_schemas.js +18 -0
  26. package/.agent/scripts/pipeline_engine.js +3 -2
  27. package/.agent/scripts/schema_validator.js +2 -1
  28. package/.agent/scripts/swarm_dispatcher.js +29 -2
  29. package/.agent/scripts/test_runner.js +1 -2
  30. package/.agent/skills/12-principles-of-animation/SKILL.md +21 -21
  31. package/.agent/skills/60fps-animation/SKILL.md +24 -22
  32. package/.agent/skills/accessible-animation/SKILL.md +29 -31
  33. package/.agent/skills/adapt/SKILL.md +21 -21
  34. package/.agent/skills/advanced-rag-pipelines/SKILL.md +21 -21
  35. package/.agent/skills/agent-organizer/SKILL.md +21 -21
  36. package/.agent/skills/agentic-patterns/SKILL.md +21 -21
  37. package/.agent/skills/agentic-workflows-2026/SKILL.md +21 -20
  38. package/.agent/skills/ai-app-hardening/SKILL.md +21 -20
  39. package/.agent/skills/ai-prompt-injection-defense/SKILL.md +21 -21
  40. package/.agent/skills/animation-on-scroll/SKILL.md +36 -32
  41. package/.agent/skills/animation-systems/SKILL.md +35 -35
  42. package/.agent/skills/antfu-conventions/SKILL.md +21 -21
  43. package/.agent/skills/api-patterns/SKILL.md +21 -21
  44. package/.agent/skills/api-security-auditor/SKILL.md +21 -21
  45. package/.agent/skills/app-builder/SKILL.md +21 -21
  46. package/.agent/skills/appflow-wireframe/SKILL.md +21 -23
  47. package/.agent/skills/apple-design/SKILL.md +21 -21
  48. package/.agent/skills/architecture/SKILL.md +21 -21
  49. package/.agent/skills/audit-and-fix/SKILL.md +21 -21
  50. package/.agent/skills/authentication-best-practices/SKILL.md +21 -21
  51. package/.agent/skills/backend-security-expert/SKILL.md +21 -21
  52. package/.agent/skills/baseline-ui/SKILL.md +21 -21
  53. package/.agent/skills/bash-linux/SKILL.md +20 -20
  54. package/.agent/skills/behavioral-modes/SKILL.md +21 -21
  55. package/.agent/skills/better-colors/SKILL.md +21 -21
  56. package/.agent/skills/better-typography/SKILL.md +21 -20
  57. package/.agent/skills/better-ui/SKILL.md +38 -26
  58. package/.agent/skills/bolder/SKILL.md +21 -21
  59. package/.agent/skills/brainstorming/SKILL.md +21 -20
  60. package/.agent/skills/browser-audit/SKILL.md +35 -28
  61. package/.agent/skills/browser-native-ai/SKILL.md +21 -21
  62. package/.agent/skills/build-primitive/SKILL.md +21 -21
  63. package/.agent/skills/building-native-ui/SKILL.md +21 -21
  64. package/.agent/skills/cicd-pro/SKILL.md +20 -20
  65. package/.agent/skills/clarify/SKILL.md +21 -21
  66. package/.agent/skills/clean-code/SKILL.md +21 -21
  67. package/.agent/skills/cloud-architect/SKILL.md +20 -20
  68. package/.agent/skills/cobejs/SKILL.md +21 -21
  69. package/.agent/skills/code-review-checklist/SKILL.md +21 -21
  70. package/.agent/skills/codebase-design/SKILL.md +21 -21
  71. package/.agent/skills/colorize/SKILL.md +21 -21
  72. package/.agent/skills/compact-landing/SKILL.md +21 -21
  73. package/.agent/skills/company-logos/SKILL.md +21 -21
  74. package/.agent/skills/config-validator/SKILL.md +21 -21
  75. package/.agent/skills/containerization-pro/SKILL.md +20 -20
  76. package/.agent/skills/context-engineering-pro/SKILL.md +21 -20
  77. package/.agent/skills/create-design-md/SKILL.md +21 -21
  78. package/.agent/skills/critique/SKILL.md +21 -21
  79. package/.agent/skills/csharp-developer/SKILL.md +21 -21
  80. package/.agent/skills/data-validation-schemas/SKILL.md +21 -21
  81. package/.agent/skills/database-design/SKILL.md +21 -21
  82. package/.agent/skills/delight/SKILL.md +21 -21
  83. package/.agent/skills/deployment-procedures/SKILL.md +20 -20
  84. package/.agent/skills/design-lab/SKILL.md +22 -22
  85. package/.agent/skills/devops-engineer/SKILL.md +20 -20
  86. package/.agent/skills/devops-incident-responder/SKILL.md +20 -20
  87. package/.agent/skills/diagnosing-bugs/SKILL.md +22 -22
  88. package/.agent/skills/distill/SKILL.md +21 -21
  89. package/.agent/skills/documentation-templates/SKILL.md +21 -21
  90. package/.agent/skills/domain-modeling/SKILL.md +21 -21
  91. package/.agent/skills/duckdb-analytical-sql/SKILL.md +21 -20
  92. package/.agent/skills/edge-ai-mobile/SKILL.md +21 -20
  93. package/.agent/skills/edge-computing/SKILL.md +21 -21
  94. package/.agent/skills/emil-design-eng/SKILL.md +21 -21
  95. package/.agent/skills/error-resilience/SKILL.md +21 -21
  96. package/.agent/skills/expo-router-v4/SKILL.md +21 -20
  97. package/.agent/skills/extract-design-system/SKILL.md +21 -21
  98. package/.agent/skills/fabel-protocol/SKILL.md +21 -21
  99. package/.agent/skills/fixing-accessibility/SKILL.md +21 -21
  100. package/.agent/skills/fixing-metadata/SKILL.md +21 -21
  101. package/.agent/skills/fixing-motion-performance/SKILL.md +21 -21
  102. package/.agent/skills/framer-motion-expert/SKILL.md +21 -21
  103. package/.agent/skills/frontend-design/SKILL.md +21 -21
  104. package/.agent/skills/frontend-security-expert/SKILL.md +21 -21
  105. package/.agent/skills/game-design-expert/SKILL.md +21 -21
  106. package/.agent/skills/game-engineering-expert/SKILL.md +21 -21
  107. package/.agent/skills/generative-ui-expert/SKILL.md +21 -21
  108. package/.agent/skills/geo-fundamentals/SKILL.md +21 -21
  109. package/.agent/skills/git-pro/SKILL.md +21 -21
  110. package/.agent/skills/github-operations/SKILL.md +21 -21
  111. package/.agent/skills/gpt-taste/SKILL.md +21 -21
  112. package/.agent/skills/gsap-core/SKILL.md +21 -21
  113. package/.agent/skills/gsap-frameworks/SKILL.md +21 -21
  114. package/.agent/skills/gsap-performance/SKILL.md +21 -21
  115. package/.agent/skills/gsap-plugins/SKILL.md +21 -21
  116. package/.agent/skills/gsap-react/SKILL.md +21 -21
  117. package/.agent/skills/gsap-scrolltrigger/SKILL.md +21 -21
  118. package/.agent/skills/gsap-timeline/SKILL.md +21 -21
  119. package/.agent/skills/gsap-utils/SKILL.md +21 -21
  120. package/.agent/skills/harden/SKILL.md +21 -21
  121. package/.agent/skills/harness-protocol/SKILL.md +21 -21
  122. package/.agent/skills/i18n-localization/SKILL.md +21 -21
  123. package/.agent/skills/impeccable/SKILL.md +21 -21
  124. package/.agent/skills/improve-codebase-architecture/SKILL.md +21 -21
  125. package/.agent/skills/improve-ui/SKILL.md +21 -21
  126. package/.agent/skills/intelligent-routing/SKILL.md +21 -20
  127. package/.agent/skills/knowledge-graph/SKILL.md +21 -21
  128. package/.agent/skills/landing-page/SKILL.md +21 -21
  129. package/.agent/skills/lint-and-validate/SKILL.md +21 -21
  130. package/.agent/skills/llm-engineering/SKILL.md +21 -21
  131. package/.agent/skills/local-first/SKILL.md +21 -21
  132. package/.agent/skills/local-first-architecture/SKILL.md +21 -21
  133. package/.agent/skills/lottie-animation/SKILL.md +21 -21
  134. package/.agent/skills/marquee-loop/SKILL.md +21 -21
  135. package/.agent/skills/masked-reveal/SKILL.md +21 -21
  136. package/.agent/skills/mcp-builder/SKILL.md +21 -21
  137. package/.agent/skills/micro-interaction/SKILL.md +39 -32
  138. package/.agent/skills/mobile-design/SKILL.md +21 -21
  139. package/.agent/skills/monorepo-management/SKILL.md +21 -21
  140. package/.agent/skills/morphing-icons/SKILL.md +21 -21
  141. package/.agent/skills/motion-engineering/SKILL.md +21 -21
  142. package/.agent/skills/nextjs-react-expert/SKILL.md +21 -21
  143. package/.agent/skills/nodejs-best-practices/SKILL.md +21 -21
  144. package/.agent/skills/observability/SKILL.md +21 -21
  145. package/.agent/skills/opentelemetry-observability/SKILL.md +20 -19
  146. package/.agent/skills/page-transition-animation/SKILL.md +21 -21
  147. package/.agent/skills/parallel-agents/SKILL.md +21 -21
  148. package/.agent/skills/performance-profiling/SKILL.md +21 -21
  149. package/.agent/skills/plan-writing/SKILL.md +21 -21
  150. package/.agent/skills/platform-engineer/SKILL.md +20 -20
  151. package/.agent/skills/platform-engineering-opentofu/SKILL.md +20 -19
  152. package/.agent/skills/playwright-ai-e2e/SKILL.md +21 -20
  153. package/.agent/skills/playwright-best-practices/SKILL.md +21 -21
  154. package/.agent/skills/polish/SKILL.md +21 -21
  155. package/.agent/skills/powershell-windows/SKILL.md +20 -20
  156. package/.agent/skills/pricing-page/SKILL.md +21 -21
  157. package/.agent/skills/product-aware-heuristics/SKILL.md +21 -21
  158. package/.agent/skills/progressive-blur/SKILL.md +21 -21
  159. package/.agent/skills/project-idioms/SKILL.md +21 -21
  160. package/.agent/skills/property-based-testing/SKILL.md +21 -20
  161. package/.agent/skills/python-patterns/SKILL.md +21 -21
  162. package/.agent/skills/python-pro/SKILL.md +21 -21
  163. package/.agent/skills/quieter/SKILL.md +21 -21
  164. package/.agent/skills/react-doctor/SKILL.md +21 -21
  165. package/.agent/skills/react-specialist/SKILL.md +21 -21
  166. package/.agent/skills/readme-builder/SKILL.md +21 -21
  167. package/.agent/skills/realtime-patterns/SKILL.md +21 -21
  168. package/.agent/skills/red-team-tactics/SKILL.md +21 -21
  169. package/.agent/skills/redesign-skill/SKILL.md +21 -21
  170. package/.agent/skills/review-animations/SKILL.md +21 -21
  171. package/.agent/skills/rust-pro/SKILL.md +21 -21
  172. package/.agent/skills/seo-fundamentals/SKILL.md +21 -21
  173. package/.agent/skills/server-management/SKILL.md +20 -20
  174. package/.agent/skills/shadcn-ui-expert/SKILL.md +21 -21
  175. package/.agent/skills/shape/SKILL.md +21 -21
  176. package/.agent/skills/skill-creator/SKILL.md +28 -21
  177. package/.agent/skills/soft-skill/SKILL.md +21 -21
  178. package/.agent/skills/sounds-on-the-web/SKILL.md +21 -21
  179. package/.agent/skills/sql-pro/SKILL.md +21 -21
  180. package/.agent/skills/supabase-postgres-best-practices/SKILL.md +21 -21
  181. package/.agent/skills/svg-animation/SKILL.md +21 -21
  182. package/.agent/skills/swiftui-expert/SKILL.md +21 -21
  183. package/.agent/skills/swiss-design/SKILL.md +21 -21
  184. package/.agent/skills/system-design-pro/SKILL.md +21 -21
  185. package/.agent/skills/systematic-debugging/SKILL.md +22 -21
  186. package/.agent/skills/systematic-debugging/condition-based-waiting.md +14 -9
  187. package/.agent/skills/systematic-debugging/defense-in-depth.md +9 -3
  188. package/.agent/skills/systematic-debugging/root-cause-tracing.md +14 -0
  189. package/.agent/skills/tailwind-patterns/SKILL.md +21 -21
  190. package/.agent/skills/taste-skill/SKILL.md +21 -21
  191. package/.agent/skills/tdd-workflow/SKILL.md +28 -27
  192. package/.agent/skills/test-result-analyzer/SKILL.md +21 -21
  193. package/.agent/skills/testing-patterns/SKILL.md +21 -21
  194. package/.agent/skills/thermo-nuclear-code-quality-review/SKILL.md +21 -21
  195. package/.agent/skills/thinking-protocol/SKILL.md +21 -20
  196. package/.agent/skills/to-spring-or-not-to-spring/SKILL.md +21 -21
  197. package/.agent/skills/transitions-dev/SKILL.md +21 -21
  198. package/.agent/skills/trend-researcher/SKILL.md +21 -21
  199. package/.agent/skills/typescript-advanced/SKILL.md +21 -21
  200. package/.agent/skills/typeset/SKILL.md +21 -21
  201. package/.agent/skills/ui-reasoning-engine/SKILL.md +21 -21
  202. package/.agent/skills/ui-skill-packs/SKILL.md +21 -21
  203. package/.agent/skills/ui-skills-root/SKILL.md +21 -21
  204. package/.agent/skills/ui-ux-pro-max/SKILL.md +21 -21
  205. package/.agent/skills/ui-ux-researcher/SKILL.md +21 -21
  206. package/.agent/skills/vector-search-pgvector/SKILL.md +21 -20
  207. package/.agent/skills/verification-before-completion/SKILL.md +40 -36
  208. package/.agent/skills/vue-expert/SKILL.md +21 -21
  209. package/.agent/skills/vulnerability-scanner/SKILL.md +21 -21
  210. package/.agent/skills/web-accessibility-auditor/SKILL.md +21 -21
  211. package/.agent/skills/web-design-guidelines/SKILL.md +21 -21
  212. package/.agent/skills/web-quality-audit/SKILL.md +21 -21
  213. package/.agent/skills/webapp-testing/SKILL.md +21 -21
  214. package/.agent/skills/webgpu-performance/SKILL.md +21 -21
  215. package/.agent/skills/whimsy-injector/SKILL.md +21 -21
  216. package/.agent/skills/workflow-optimizer/SKILL.md +21 -21
  217. package/.agent/skills/zero-trust-passkeys/SKILL.md +21 -20
  218. package/.agent/templates/DESIGN.md +312 -290
  219. package/.agent/templates/sdd/task-reviewer-prompt.md +2 -2
  220. package/.agent/workflows/audit-live.md +4 -3
  221. package/.agent/workflows/brainstorm.md +1 -0
  222. package/.agent/workflows/context.md +9 -7
  223. package/.agent/workflows/minimal.md +3 -2
  224. package/.agent/workflows/plan.md +1 -1
  225. package/.agent/workflows/sdd.md +15 -0
  226. package/.agent/workflows/skill-enhancement-engine.md +11 -11
  227. package/.agent/workflows/super-prompt.md +25 -24
  228. package/.agents/skills/12-principles-of-animation/SKILL.md +21 -21
  229. package/.agents/skills/60fps-animation/SKILL.md +24 -22
  230. package/.agents/skills/accessible-animation/SKILL.md +29 -31
  231. package/.agents/skills/adapt/SKILL.md +21 -21
  232. package/.agents/skills/advanced-rag-pipelines/SKILL.md +21 -21
  233. package/.agents/skills/agent-organizer/SKILL.md +21 -21
  234. package/.agents/skills/agentic-patterns/SKILL.md +21 -21
  235. package/.agents/skills/agentic-workflows-2026/SKILL.md +21 -20
  236. package/.agents/skills/ai-app-hardening/SKILL.md +21 -20
  237. package/.agents/skills/ai-prompt-injection-defense/SKILL.md +21 -21
  238. package/.agents/skills/animation-on-scroll/SKILL.md +36 -32
  239. package/.agents/skills/animation-systems/SKILL.md +35 -35
  240. package/.agents/skills/antfu-conventions/SKILL.md +21 -21
  241. package/.agents/skills/api-patterns/SKILL.md +21 -21
  242. package/.agents/skills/api-security-auditor/SKILL.md +21 -21
  243. package/.agents/skills/app-builder/SKILL.md +21 -21
  244. package/.agents/skills/appflow-wireframe/SKILL.md +21 -23
  245. package/.agents/skills/apple-design/SKILL.md +21 -21
  246. package/.agents/skills/architecture/SKILL.md +21 -21
  247. package/.agents/skills/audit-and-fix/SKILL.md +21 -21
  248. package/.agents/skills/authentication-best-practices/SKILL.md +21 -21
  249. package/.agents/skills/backend-security-expert/SKILL.md +21 -21
  250. package/.agents/skills/baseline-ui/SKILL.md +21 -21
  251. package/.agents/skills/bash-linux/SKILL.md +20 -20
  252. package/.agents/skills/behavioral-modes/SKILL.md +21 -21
  253. package/.agents/skills/better-colors/SKILL.md +21 -21
  254. package/.agents/skills/better-typography/SKILL.md +21 -20
  255. package/.agents/skills/better-ui/SKILL.md +38 -26
  256. package/.agents/skills/bolder/SKILL.md +21 -21
  257. package/.agents/skills/brainstorming/SKILL.md +21 -20
  258. package/.agents/skills/browser-audit/SKILL.md +35 -28
  259. package/.agents/skills/browser-native-ai/SKILL.md +21 -21
  260. package/.agents/skills/build-primitive/SKILL.md +21 -21
  261. package/.agents/skills/building-native-ui/SKILL.md +21 -21
  262. package/.agents/skills/cicd-pro/SKILL.md +20 -20
  263. package/.agents/skills/clarify/SKILL.md +21 -21
  264. package/.agents/skills/clean-code/SKILL.md +21 -21
  265. package/.agents/skills/cloud-architect/SKILL.md +20 -20
  266. package/.agents/skills/cobejs/SKILL.md +21 -21
  267. package/.agents/skills/code-review-checklist/SKILL.md +21 -21
  268. package/.agents/skills/codebase-design/SKILL.md +21 -21
  269. package/.agents/skills/colorize/SKILL.md +21 -21
  270. package/.agents/skills/compact-landing/SKILL.md +21 -21
  271. package/.agents/skills/company-logos/SKILL.md +21 -21
  272. package/.agents/skills/config-validator/SKILL.md +21 -21
  273. package/.agents/skills/containerization-pro/SKILL.md +20 -20
  274. package/.agents/skills/context-engineering-pro/SKILL.md +21 -20
  275. package/.agents/skills/create-design-md/SKILL.md +21 -21
  276. package/.agents/skills/critique/SKILL.md +21 -21
  277. package/.agents/skills/csharp-developer/SKILL.md +21 -21
  278. package/.agents/skills/data-validation-schemas/SKILL.md +21 -21
  279. package/.agents/skills/database-design/SKILL.md +21 -21
  280. package/.agents/skills/delight/SKILL.md +21 -21
  281. package/.agents/skills/deployment-procedures/SKILL.md +20 -20
  282. package/.agents/skills/design-lab/SKILL.md +22 -22
  283. package/.agents/skills/devops-engineer/SKILL.md +20 -20
  284. package/.agents/skills/devops-incident-responder/SKILL.md +20 -20
  285. package/.agents/skills/diagnosing-bugs/SKILL.md +22 -22
  286. package/.agents/skills/distill/SKILL.md +21 -21
  287. package/.agents/skills/documentation-templates/SKILL.md +21 -21
  288. package/.agents/skills/domain-modeling/SKILL.md +21 -21
  289. package/.agents/skills/duckdb-analytical-sql/SKILL.md +21 -20
  290. package/.agents/skills/edge-ai-mobile/SKILL.md +21 -20
  291. package/.agents/skills/edge-computing/SKILL.md +21 -21
  292. package/.agents/skills/emil-design-eng/SKILL.md +21 -21
  293. package/.agents/skills/error-resilience/SKILL.md +21 -21
  294. package/.agents/skills/expo-router-v4/SKILL.md +21 -20
  295. package/.agents/skills/extract-design-system/SKILL.md +21 -21
  296. package/.agents/skills/fabel-protocol/SKILL.md +21 -21
  297. package/.agents/skills/fixing-accessibility/SKILL.md +21 -21
  298. package/.agents/skills/fixing-metadata/SKILL.md +21 -21
  299. package/.agents/skills/fixing-motion-performance/SKILL.md +21 -21
  300. package/.agents/skills/framer-motion-expert/SKILL.md +21 -21
  301. package/.agents/skills/frontend-design/SKILL.md +21 -21
  302. package/.agents/skills/frontend-security-expert/SKILL.md +21 -21
  303. package/.agents/skills/game-design-expert/SKILL.md +21 -21
  304. package/.agents/skills/game-engineering-expert/SKILL.md +21 -21
  305. package/.agents/skills/generative-ui-expert/SKILL.md +21 -21
  306. package/.agents/skills/geo-fundamentals/SKILL.md +21 -21
  307. package/.agents/skills/git-pro/SKILL.md +21 -21
  308. package/.agents/skills/github-operations/SKILL.md +21 -21
  309. package/.agents/skills/gpt-taste/SKILL.md +21 -21
  310. package/.agents/skills/gsap-core/SKILL.md +21 -21
  311. package/.agents/skills/gsap-frameworks/SKILL.md +21 -21
  312. package/.agents/skills/gsap-performance/SKILL.md +21 -21
  313. package/.agents/skills/gsap-plugins/SKILL.md +21 -21
  314. package/.agents/skills/gsap-react/SKILL.md +21 -21
  315. package/.agents/skills/gsap-scrolltrigger/SKILL.md +21 -21
  316. package/.agents/skills/gsap-timeline/SKILL.md +21 -21
  317. package/.agents/skills/gsap-utils/SKILL.md +21 -21
  318. package/.agents/skills/harden/SKILL.md +21 -21
  319. package/.agents/skills/harness-protocol/SKILL.md +21 -21
  320. package/.agents/skills/i18n-localization/SKILL.md +21 -21
  321. package/.agents/skills/impeccable/SKILL.md +21 -21
  322. package/.agents/skills/improve-codebase-architecture/SKILL.md +21 -21
  323. package/.agents/skills/improve-ui/SKILL.md +21 -21
  324. package/.agents/skills/intelligent-routing/SKILL.md +21 -20
  325. package/.agents/skills/knowledge-graph/SKILL.md +21 -21
  326. package/.agents/skills/landing-page/SKILL.md +21 -21
  327. package/.agents/skills/lint-and-validate/SKILL.md +21 -21
  328. package/.agents/skills/llm-engineering/SKILL.md +21 -21
  329. package/.agents/skills/local-first/SKILL.md +21 -21
  330. package/.agents/skills/local-first-architecture/SKILL.md +21 -21
  331. package/.agents/skills/lottie-animation/SKILL.md +21 -21
  332. package/.agents/skills/marquee-loop/SKILL.md +21 -21
  333. package/.agents/skills/masked-reveal/SKILL.md +21 -21
  334. package/.agents/skills/mcp-builder/SKILL.md +21 -21
  335. package/.agents/skills/micro-interaction/SKILL.md +39 -32
  336. package/.agents/skills/mobile-design/SKILL.md +21 -21
  337. package/.agents/skills/monorepo-management/SKILL.md +21 -21
  338. package/.agents/skills/morphing-icons/SKILL.md +21 -21
  339. package/.agents/skills/motion-engineering/SKILL.md +21 -21
  340. package/.agents/skills/nextjs-react-expert/SKILL.md +21 -21
  341. package/.agents/skills/nodejs-best-practices/SKILL.md +21 -21
  342. package/.agents/skills/observability/SKILL.md +21 -21
  343. package/.agents/skills/opentelemetry-observability/SKILL.md +20 -19
  344. package/.agents/skills/page-transition-animation/SKILL.md +21 -21
  345. package/.agents/skills/parallel-agents/SKILL.md +21 -21
  346. package/.agents/skills/performance-profiling/SKILL.md +21 -21
  347. package/.agents/skills/plan-writing/SKILL.md +21 -21
  348. package/.agents/skills/platform-engineer/SKILL.md +20 -20
  349. package/.agents/skills/platform-engineering-opentofu/SKILL.md +20 -19
  350. package/.agents/skills/playwright-ai-e2e/SKILL.md +21 -20
  351. package/.agents/skills/playwright-best-practices/SKILL.md +21 -21
  352. package/.agents/skills/polish/SKILL.md +21 -21
  353. package/.agents/skills/powershell-windows/SKILL.md +20 -20
  354. package/.agents/skills/pricing-page/SKILL.md +21 -21
  355. package/.agents/skills/product-aware-heuristics/SKILL.md +21 -21
  356. package/.agents/skills/progressive-blur/SKILL.md +21 -21
  357. package/.agents/skills/project-idioms/SKILL.md +21 -21
  358. package/.agents/skills/property-based-testing/SKILL.md +21 -20
  359. package/.agents/skills/python-patterns/SKILL.md +21 -21
  360. package/.agents/skills/python-pro/SKILL.md +21 -21
  361. package/.agents/skills/quieter/SKILL.md +21 -21
  362. package/.agents/skills/react-doctor/SKILL.md +21 -21
  363. package/.agents/skills/react-specialist/SKILL.md +21 -21
  364. package/.agents/skills/readme-builder/SKILL.md +21 -21
  365. package/.agents/skills/realtime-patterns/SKILL.md +21 -21
  366. package/.agents/skills/red-team-tactics/SKILL.md +21 -21
  367. package/.agents/skills/redesign-skill/SKILL.md +21 -21
  368. package/.agents/skills/review-animations/SKILL.md +21 -21
  369. package/.agents/skills/rust-pro/SKILL.md +21 -21
  370. package/.agents/skills/seo-fundamentals/SKILL.md +21 -21
  371. package/.agents/skills/server-management/SKILL.md +20 -20
  372. package/.agents/skills/shadcn-ui-expert/SKILL.md +21 -21
  373. package/.agents/skills/shape/SKILL.md +21 -21
  374. package/.agents/skills/skill-creator/SKILL.md +28 -21
  375. package/.agents/skills/soft-skill/SKILL.md +21 -21
  376. package/.agents/skills/sounds-on-the-web/SKILL.md +21 -21
  377. package/.agents/skills/sql-pro/SKILL.md +21 -21
  378. package/.agents/skills/supabase-postgres-best-practices/SKILL.md +21 -21
  379. package/.agents/skills/svg-animation/SKILL.md +21 -21
  380. package/.agents/skills/swiftui-expert/SKILL.md +21 -21
  381. package/.agents/skills/swiss-design/SKILL.md +21 -21
  382. package/.agents/skills/system-design-pro/SKILL.md +21 -21
  383. package/.agents/skills/systematic-debugging/SKILL.md +22 -21
  384. package/.agents/skills/systematic-debugging/condition-based-waiting.md +14 -9
  385. package/.agents/skills/systematic-debugging/defense-in-depth.md +9 -3
  386. package/.agents/skills/systematic-debugging/root-cause-tracing.md +14 -0
  387. package/.agents/skills/tailwind-patterns/SKILL.md +21 -21
  388. package/.agents/skills/taste-skill/SKILL.md +21 -21
  389. package/.agents/skills/tdd-workflow/SKILL.md +28 -27
  390. package/.agents/skills/test-result-analyzer/SKILL.md +21 -21
  391. package/.agents/skills/testing-patterns/SKILL.md +21 -21
  392. package/.agents/skills/thermo-nuclear-code-quality-review/SKILL.md +21 -21
  393. package/.agents/skills/thinking-protocol/SKILL.md +21 -20
  394. package/.agents/skills/to-spring-or-not-to-spring/SKILL.md +21 -21
  395. package/.agents/skills/transitions-dev/SKILL.md +21 -21
  396. package/.agents/skills/trend-researcher/SKILL.md +21 -21
  397. package/.agents/skills/typescript-advanced/SKILL.md +21 -21
  398. package/.agents/skills/typeset/SKILL.md +21 -21
  399. package/.agents/skills/ui-reasoning-engine/SKILL.md +21 -21
  400. package/.agents/skills/ui-skill-packs/SKILL.md +21 -21
  401. package/.agents/skills/ui-skills-root/SKILL.md +21 -21
  402. package/.agents/skills/ui-ux-pro-max/SKILL.md +21 -21
  403. package/.agents/skills/ui-ux-researcher/SKILL.md +21 -21
  404. package/.agents/skills/vector-search-pgvector/SKILL.md +21 -20
  405. package/.agents/skills/verification-before-completion/SKILL.md +40 -36
  406. package/.agents/skills/vue-expert/SKILL.md +21 -21
  407. package/.agents/skills/vulnerability-scanner/SKILL.md +21 -21
  408. package/.agents/skills/web-accessibility-auditor/SKILL.md +21 -21
  409. package/.agents/skills/web-design-guidelines/SKILL.md +21 -21
  410. package/.agents/skills/web-quality-audit/SKILL.md +21 -21
  411. package/.agents/skills/webapp-testing/SKILL.md +21 -21
  412. package/.agents/skills/webgpu-performance/SKILL.md +21 -21
  413. package/.agents/skills/whimsy-injector/SKILL.md +21 -21
  414. package/.agents/skills/workflow-optimizer/SKILL.md +21 -21
  415. package/.agents/skills/zero-trust-passkeys/SKILL.md +21 -20
  416. package/.codex-plugin/plugin.json +1 -5
  417. package/.kimi-plugin/plugin.json +1 -5
  418. package/.opencode/INSTALL.md +1 -0
  419. package/.opencode/plugins/tribunal.js +15 -6
  420. package/.pi/extensions/tribunal.ts +26 -29
  421. package/AGENTS.md +15 -13
  422. package/CLAUDE.md +3 -1
  423. package/README.md +542 -535
  424. package/bin/adapter-install.js +263 -263
  425. package/bin/mcp-server.js +17 -12
  426. package/bin/wrapper.js +12 -1
  427. package/dist/tui/banner.js +77 -77
  428. package/gemini-extension.json +1 -1
  429. package/package.json +176 -176
  430. package/plugin.json +1 -1
  431. package/scripts/apply-version.js +57 -0
  432. package/scripts/audit_skill_sdo.js +6 -4
  433. package/scripts/context_compiler.js +207 -83
  434. package/scripts/modernize_skills.js +25 -11
  435. package/scripts/package-cores.js +4 -1
  436. package/scripts/skill_enhancement_engine.js +211 -50
  437. package/scripts/telemetry_gc.js +154 -0
  438. package/skills/12-principles-of-animation/SKILL.md +21 -21
  439. package/skills/60fps-animation/SKILL.md +24 -22
  440. package/skills/accessible-animation/SKILL.md +29 -31
  441. package/skills/adapt/SKILL.md +21 -21
  442. package/skills/advanced-rag-pipelines/SKILL.md +21 -21
  443. package/skills/agent-organizer/SKILL.md +21 -21
  444. package/skills/agentic-patterns/SKILL.md +21 -21
  445. package/skills/agentic-workflows-2026/SKILL.md +21 -20
  446. package/skills/ai-app-hardening/SKILL.md +21 -20
  447. package/skills/ai-prompt-injection-defense/SKILL.md +21 -21
  448. package/skills/animation-on-scroll/SKILL.md +36 -32
  449. package/skills/animation-systems/SKILL.md +35 -35
  450. package/skills/antfu-conventions/SKILL.md +21 -21
  451. package/skills/api-patterns/SKILL.md +21 -21
  452. package/skills/api-security-auditor/SKILL.md +21 -21
  453. package/skills/app-builder/SKILL.md +21 -21
  454. package/skills/appflow-wireframe/SKILL.md +21 -23
  455. package/skills/apple-design/SKILL.md +21 -21
  456. package/skills/architecture/SKILL.md +21 -21
  457. package/skills/audit-and-fix/SKILL.md +21 -21
  458. package/skills/authentication-best-practices/SKILL.md +21 -21
  459. package/skills/backend-security-expert/SKILL.md +21 -21
  460. package/skills/baseline-ui/SKILL.md +21 -21
  461. package/skills/bash-linux/SKILL.md +20 -20
  462. package/skills/behavioral-modes/SKILL.md +21 -21
  463. package/skills/better-colors/SKILL.md +21 -21
  464. package/skills/better-typography/SKILL.md +21 -20
  465. package/skills/better-ui/SKILL.md +38 -26
  466. package/skills/bolder/SKILL.md +21 -21
  467. package/skills/brainstorming/SKILL.md +21 -20
  468. package/skills/browser-audit/SKILL.md +35 -28
  469. package/skills/browser-native-ai/SKILL.md +21 -21
  470. package/skills/build-primitive/SKILL.md +21 -21
  471. package/skills/building-native-ui/SKILL.md +21 -21
  472. package/skills/cicd-pro/SKILL.md +20 -20
  473. package/skills/clarify/SKILL.md +21 -21
  474. package/skills/clean-code/SKILL.md +21 -21
  475. package/skills/cloud-architect/SKILL.md +20 -20
  476. package/skills/cobejs/SKILL.md +21 -21
  477. package/skills/code-review-checklist/SKILL.md +21 -21
  478. package/skills/codebase-design/SKILL.md +21 -21
  479. package/skills/colorize/SKILL.md +21 -21
  480. package/skills/compact-landing/SKILL.md +21 -21
  481. package/skills/company-logos/SKILL.md +21 -21
  482. package/skills/config-validator/SKILL.md +21 -21
  483. package/skills/containerization-pro/SKILL.md +20 -20
  484. package/skills/context-engineering-pro/SKILL.md +21 -20
  485. package/skills/create-design-md/SKILL.md +21 -21
  486. package/skills/critique/SKILL.md +21 -21
  487. package/skills/csharp-developer/SKILL.md +21 -21
  488. package/skills/data-validation-schemas/SKILL.md +21 -21
  489. package/skills/database-design/SKILL.md +21 -21
  490. package/skills/delight/SKILL.md +21 -21
  491. package/skills/deployment-procedures/SKILL.md +20 -20
  492. package/skills/design-lab/SKILL.md +22 -22
  493. package/skills/devops-engineer/SKILL.md +20 -20
  494. package/skills/devops-incident-responder/SKILL.md +20 -20
  495. package/skills/diagnosing-bugs/SKILL.md +22 -22
  496. package/skills/distill/SKILL.md +21 -21
  497. package/skills/documentation-templates/SKILL.md +21 -21
  498. package/skills/domain-modeling/SKILL.md +21 -21
  499. package/skills/duckdb-analytical-sql/SKILL.md +21 -20
  500. package/skills/edge-ai-mobile/SKILL.md +21 -20
  501. package/skills/edge-computing/SKILL.md +21 -21
  502. package/skills/emil-design-eng/SKILL.md +21 -21
  503. package/skills/error-resilience/SKILL.md +21 -21
  504. package/skills/expo-router-v4/SKILL.md +21 -20
  505. package/skills/extract-design-system/SKILL.md +21 -21
  506. package/skills/fabel-protocol/SKILL.md +21 -21
  507. package/skills/fixing-accessibility/SKILL.md +21 -21
  508. package/skills/fixing-metadata/SKILL.md +21 -21
  509. package/skills/fixing-motion-performance/SKILL.md +21 -21
  510. package/skills/framer-motion-expert/SKILL.md +21 -21
  511. package/skills/frontend-design/SKILL.md +21 -21
  512. package/skills/frontend-security-expert/SKILL.md +21 -21
  513. package/skills/game-design-expert/SKILL.md +21 -21
  514. package/skills/game-engineering-expert/SKILL.md +21 -21
  515. package/skills/generative-ui-expert/SKILL.md +21 -21
  516. package/skills/geo-fundamentals/SKILL.md +21 -21
  517. package/skills/git-pro/SKILL.md +21 -21
  518. package/skills/github-operations/SKILL.md +21 -21
  519. package/skills/gpt-taste/SKILL.md +21 -21
  520. package/skills/gsap-core/SKILL.md +21 -21
  521. package/skills/gsap-frameworks/SKILL.md +21 -21
  522. package/skills/gsap-performance/SKILL.md +21 -21
  523. package/skills/gsap-plugins/SKILL.md +21 -21
  524. package/skills/gsap-react/SKILL.md +21 -21
  525. package/skills/gsap-scrolltrigger/SKILL.md +21 -21
  526. package/skills/gsap-timeline/SKILL.md +21 -21
  527. package/skills/gsap-utils/SKILL.md +21 -21
  528. package/skills/harden/SKILL.md +21 -21
  529. package/skills/harness-protocol/SKILL.md +21 -21
  530. package/skills/i18n-localization/SKILL.md +21 -21
  531. package/skills/impeccable/SKILL.md +21 -21
  532. package/skills/improve-codebase-architecture/SKILL.md +21 -21
  533. package/skills/improve-ui/SKILL.md +21 -21
  534. package/skills/intelligent-routing/SKILL.md +21 -20
  535. package/skills/knowledge-graph/SKILL.md +21 -21
  536. package/skills/landing-page/SKILL.md +21 -21
  537. package/skills/lint-and-validate/SKILL.md +21 -21
  538. package/skills/llm-engineering/SKILL.md +21 -21
  539. package/skills/local-first/SKILL.md +21 -21
  540. package/skills/local-first-architecture/SKILL.md +21 -21
  541. package/skills/lottie-animation/SKILL.md +21 -21
  542. package/skills/marquee-loop/SKILL.md +21 -21
  543. package/skills/masked-reveal/SKILL.md +21 -21
  544. package/skills/mcp-builder/SKILL.md +21 -21
  545. package/skills/micro-interaction/SKILL.md +39 -32
  546. package/skills/mobile-design/SKILL.md +21 -21
  547. package/skills/monorepo-management/SKILL.md +21 -21
  548. package/skills/morphing-icons/SKILL.md +21 -21
  549. package/skills/motion-engineering/SKILL.md +21 -21
  550. package/skills/nextjs-react-expert/SKILL.md +21 -21
  551. package/skills/nodejs-best-practices/SKILL.md +21 -21
  552. package/skills/observability/SKILL.md +21 -21
  553. package/skills/opentelemetry-observability/SKILL.md +20 -19
  554. package/skills/page-transition-animation/SKILL.md +21 -21
  555. package/skills/parallel-agents/SKILL.md +21 -21
  556. package/skills/performance-profiling/SKILL.md +21 -21
  557. package/skills/plan-writing/SKILL.md +21 -21
  558. package/skills/platform-engineer/SKILL.md +20 -20
  559. package/skills/platform-engineering-opentofu/SKILL.md +20 -19
  560. package/skills/playwright-ai-e2e/SKILL.md +21 -20
  561. package/skills/playwright-best-practices/SKILL.md +21 -21
  562. package/skills/polish/SKILL.md +21 -21
  563. package/skills/powershell-windows/SKILL.md +20 -20
  564. package/skills/pricing-page/SKILL.md +21 -21
  565. package/skills/product-aware-heuristics/SKILL.md +21 -21
  566. package/skills/progressive-blur/SKILL.md +21 -21
  567. package/skills/project-idioms/SKILL.md +21 -21
  568. package/skills/property-based-testing/SKILL.md +21 -20
  569. package/skills/python-patterns/SKILL.md +21 -21
  570. package/skills/python-pro/SKILL.md +21 -21
  571. package/skills/quieter/SKILL.md +21 -21
  572. package/skills/react-doctor/SKILL.md +21 -21
  573. package/skills/react-specialist/SKILL.md +21 -21
  574. package/skills/readme-builder/SKILL.md +21 -21
  575. package/skills/realtime-patterns/SKILL.md +21 -21
  576. package/skills/red-team-tactics/SKILL.md +21 -21
  577. package/skills/redesign-skill/SKILL.md +21 -21
  578. package/skills/review-animations/SKILL.md +21 -21
  579. package/skills/rust-pro/SKILL.md +21 -21
  580. package/skills/seo-fundamentals/SKILL.md +21 -21
  581. package/skills/server-management/SKILL.md +20 -20
  582. package/skills/shadcn-ui-expert/SKILL.md +21 -21
  583. package/skills/shape/SKILL.md +21 -21
  584. package/skills/skill-creator/SKILL.md +28 -21
  585. package/skills/soft-skill/SKILL.md +21 -21
  586. package/skills/sounds-on-the-web/SKILL.md +21 -21
  587. package/skills/sql-pro/SKILL.md +21 -21
  588. package/skills/supabase-postgres-best-practices/SKILL.md +21 -21
  589. package/skills/svg-animation/SKILL.md +21 -21
  590. package/skills/swiftui-expert/SKILL.md +21 -21
  591. package/skills/swiss-design/SKILL.md +21 -21
  592. package/skills/system-design-pro/SKILL.md +21 -21
  593. package/skills/systematic-debugging/SKILL.md +22 -21
  594. package/skills/systematic-debugging/condition-based-waiting.md +14 -9
  595. package/skills/systematic-debugging/defense-in-depth.md +9 -3
  596. package/skills/systematic-debugging/root-cause-tracing.md +14 -0
  597. package/skills/tailwind-patterns/SKILL.md +21 -21
  598. package/skills/taste-skill/SKILL.md +21 -21
  599. package/skills/tdd-workflow/SKILL.md +28 -27
  600. package/skills/test-result-analyzer/SKILL.md +21 -21
  601. package/skills/testing-patterns/SKILL.md +21 -21
  602. package/skills/thermo-nuclear-code-quality-review/SKILL.md +21 -21
  603. package/skills/thinking-protocol/SKILL.md +21 -20
  604. package/skills/to-spring-or-not-to-spring/SKILL.md +21 -21
  605. package/skills/transitions-dev/SKILL.md +21 -21
  606. package/skills/trend-researcher/SKILL.md +21 -21
  607. package/skills/typescript-advanced/SKILL.md +21 -21
  608. package/skills/typeset/SKILL.md +21 -21
  609. package/skills/ui-reasoning-engine/SKILL.md +21 -21
  610. package/skills/ui-skill-packs/SKILL.md +21 -21
  611. package/skills/ui-skills-root/SKILL.md +21 -21
  612. package/skills/ui-ux-pro-max/SKILL.md +21 -21
  613. package/skills/ui-ux-researcher/SKILL.md +21 -21
  614. package/skills/vector-search-pgvector/SKILL.md +21 -20
  615. package/skills/verification-before-completion/SKILL.md +40 -36
  616. package/skills/vue-expert/SKILL.md +21 -21
  617. package/skills/vulnerability-scanner/SKILL.md +21 -21
  618. package/skills/web-accessibility-auditor/SKILL.md +21 -21
  619. package/skills/web-design-guidelines/SKILL.md +21 -21
  620. package/skills/web-quality-audit/SKILL.md +21 -21
  621. package/skills/webapp-testing/SKILL.md +21 -21
  622. package/skills/webgpu-performance/SKILL.md +21 -21
  623. package/skills/whimsy-injector/SKILL.md +21 -21
  624. package/skills/workflow-optimizer/SKILL.md +21 -21
  625. package/skills/zero-trust-passkeys/SKILL.md +21 -20
@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `harden` domain, inspec
34
34
 
35
35
  Execute all non-trivial tasks through this 7-pass cognitive loop:
36
36
 
37
- | Pass | Phase | Core Action |
38
- |:---|:---|:---|
39
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
37
+ | Pass | Phase | Core Action |
38
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
39
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
45
45
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
46
46
 
47
47
  ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
50
50
 
51
51
  ---
52
52
 
53
-
54
53
  ---
55
54
 
56
55
  ## 5 Resilience Domains
@@ -88,23 +87,23 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
88
87
 
89
88
  ## 🚨 Edge-Case & Failure Mode Matrix
90
89
 
91
- | Scenario | Risk | Mitigation Strategy |
92
- |:---|:---|:---|
93
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
94
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
95
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
96
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
97
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
90
+ | Scenario | Risk | Mitigation Strategy |
91
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
92
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
93
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
94
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
95
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
96
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
98
97
 
99
98
  ---
100
99
 
101
100
  ## 🤖 LLM-Specific Traps Table
102
101
 
103
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
104
- |:---|:---|:---|
105
- | **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
106
- | **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
107
- | **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
102
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
103
+ | :------------------------------ | :----------------------------------------------------------------- | :---------------------------------------------------------------------------- |
104
+ | **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
105
+ | **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
106
+ | **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
108
107
 
109
108
  ---
110
109
 
@@ -126,5 +125,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
126
125
  ### 🛑 Verification-Before-Completion (VBC) Protocol
127
126
 
128
127
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
128
+
129
129
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
130
130
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
@@ -35,14 +35,14 @@ Before generating, refactoring, or reviewing code in the `harness-protocol` doma
35
35
 
36
36
  Execute all non-trivial tasks through this 7-pass cognitive loop:
37
37
 
38
- | Pass | Phase | Core Action |
39
- |:---|:---|:---|
40
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
41
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
42
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
43
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
44
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
45
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
38
+ | Pass | Phase | Core Action |
39
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
40
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
41
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
42
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
43
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
44
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
45
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
46
46
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
47
47
 
48
48
  ---
@@ -51,7 +51,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
51
51
 
52
52
  ---
53
53
 
54
-
55
54
  ## Rules
56
55
 
57
56
  1. Each session must start with `tk marathon init "spec"`
@@ -73,23 +72,23 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
73
72
 
74
73
  ## 🚨 Edge-Case & Failure Mode Matrix
75
74
 
76
- | Scenario | Risk | Mitigation Strategy |
77
- |:---|:---|:---|
78
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
79
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
80
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
81
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
82
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
75
+ | Scenario | Risk | Mitigation Strategy |
76
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
77
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
78
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
79
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
80
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
81
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
83
82
 
84
83
  ---
85
84
 
86
85
  ## 🤖 LLM-Specific Traps Table
87
86
 
88
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
89
- |:---|:---|:---|
90
- | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
91
- | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
92
- | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
87
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
88
+ | :--------------------------------- | :------------------------------------------------------------------------ | :----------------------------------------------------------------------- |
89
+ | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
90
+ | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
91
+ | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
93
92
 
94
93
  ---
95
94
 
@@ -111,5 +110,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
111
110
  ### 🛑 Verification-Before-Completion (VBC) Protocol
112
111
 
113
112
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
113
+
114
114
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
115
115
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `i18n-localization` dom
34
34
 
35
35
  Execute all non-trivial tasks through this 7-pass cognitive loop:
36
36
 
37
- | Pass | Phase | Core Action |
38
- |:---|:---|:---|
39
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
37
+ | Pass | Phase | Core Action |
38
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
39
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
45
45
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
46
46
 
47
47
  ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
50
50
 
51
51
  ---
52
52
 
53
-
54
53
  ## Hallucination Traps (Read First)
55
54
 
56
55
  - ❌ Concatenating translated strings (`'Hello ' + name`) -> ✅ Use interpolation: `t('greeting', { name })` to handle word order differences
@@ -167,23 +166,23 @@ In Next.js Middleware:
167
166
 
168
167
  ## 🚨 Edge-Case & Failure Mode Matrix
169
168
 
170
- | Scenario | Risk | Mitigation Strategy |
171
- |:---|:---|:---|
172
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
173
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
174
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
175
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
176
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
169
+ | Scenario | Risk | Mitigation Strategy |
170
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
171
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
172
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
173
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
174
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
175
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
177
176
 
178
177
  ---
179
178
 
180
179
  ## 🤖 LLM-Specific Traps Table
181
180
 
182
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
183
- |:---|:---|:---|
184
- | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
185
- | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
186
- | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
181
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
182
+ | :--------------------------------- | :------------------------------------------------------------------------ | :----------------------------------------------------------------------- |
183
+ | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
184
+ | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
185
+ | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
187
186
 
188
187
  ---
189
188
 
@@ -205,5 +204,6 @@ In Next.js Middleware:
205
204
  ### 🛑 Verification-Before-Completion (VBC) Protocol
206
205
 
207
206
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
207
+
208
208
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
209
209
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `impeccable` domain, in
34
34
 
35
35
  Execute all non-trivial tasks through this 7-pass cognitive loop:
36
36
 
37
- | Pass | Phase | Core Action |
38
- |:---|:---|:---|
39
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
37
+ | Pass | Phase | Core Action |
38
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
39
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
45
45
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
46
46
 
47
47
  ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
50
50
 
51
51
  ---
52
52
 
53
-
54
53
  ---
55
54
 
56
55
  ## Core Pillars of Impeccable UI
@@ -85,23 +84,23 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
85
84
 
86
85
  ## 🚨 Edge-Case & Failure Mode Matrix
87
86
 
88
- | Scenario | Risk | Mitigation Strategy |
89
- |:---|:---|:---|
90
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
91
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
92
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
93
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
94
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
87
+ | Scenario | Risk | Mitigation Strategy |
88
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
89
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
90
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
91
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
92
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
93
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
95
94
 
96
95
  ---
97
96
 
98
97
  ## 🤖 LLM-Specific Traps Table
99
98
 
100
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
101
- |:---|:---|:---|
102
- | **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
103
- | **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
104
- | **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
99
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
100
+ | :------------------------------ | :----------------------------------------------------------------- | :---------------------------------------------------------------------------- |
101
+ | **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
102
+ | **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
103
+ | **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
105
104
 
106
105
  ---
107
106
 
@@ -123,5 +122,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
123
122
  ### 🛑 Verification-Before-Completion (VBC) Protocol
124
123
 
125
124
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
125
+
126
126
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
127
127
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `improve-codebase-archi
34
34
 
35
35
  Execute all non-trivial tasks through this 7-pass cognitive loop:
36
36
 
37
- | Pass | Phase | Core Action |
38
- |:---|:---|:---|
39
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
37
+ | Pass | Phase | Core Action |
38
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
39
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
45
45
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
46
46
 
47
47
  ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
50
50
 
51
51
  ---
52
52
 
53
-
54
53
  ---
55
54
 
56
55
  ## 4 Audit Steps
@@ -81,23 +80,23 @@ Output audit findings in a clear prioritized Markdown table:
81
80
 
82
81
  ## 🚨 Edge-Case & Failure Mode Matrix
83
82
 
84
- | Scenario | Risk | Mitigation Strategy |
85
- |:---|:---|:---|
86
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
87
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
88
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
89
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
90
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
83
+ | Scenario | Risk | Mitigation Strategy |
84
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
85
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
86
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
87
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
88
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
89
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
91
90
 
92
91
  ---
93
92
 
94
93
  ## 🤖 LLM-Specific Traps Table
95
94
 
96
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
97
- |:---|:---|:---|
98
- | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
99
- | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
100
- | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
95
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
96
+ | :--------------------------------- | :------------------------------------------------------------------------ | :----------------------------------------------------------------------- |
97
+ | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
98
+ | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
99
+ | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
101
100
 
102
101
  ---
103
102
 
@@ -119,5 +118,6 @@ Output audit findings in a clear prioritized Markdown table:
119
118
  ### 🛑 Verification-Before-Completion (VBC) Protocol
120
119
 
121
120
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
121
+
122
122
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
123
123
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
@@ -34,14 +34,14 @@ Before generating, refactoring, or reviewing code in the `improve-ui` domain, in
34
34
 
35
35
  Execute all non-trivial tasks through this 7-pass cognitive loop:
36
36
 
37
- | Pass | Phase | Core Action |
38
- |:---|:---|:---|
39
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
37
+ | Pass | Phase | Core Action |
38
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
39
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
40
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
41
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
42
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
43
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
44
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
45
45
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
46
46
 
47
47
  ---
@@ -50,7 +50,6 @@ Execute all non-trivial tasks through this 7-pass cognitive loop:
50
50
 
51
51
  ---
52
52
 
53
-
54
53
  ---
55
54
 
56
55
  ## 1. Operating Rules & Boundaries
@@ -103,23 +102,23 @@ Write a self-contained plan specifying:
103
102
 
104
103
  ## 🚨 Edge-Case & Failure Mode Matrix
105
104
 
106
- | Scenario | Risk | Mitigation Strategy |
107
- |:---|:---|:---|
108
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
109
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
110
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
111
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
112
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
105
+ | Scenario | Risk | Mitigation Strategy |
106
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
107
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
108
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
109
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
110
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
111
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
113
112
 
114
113
  ---
115
114
 
116
115
  ## 🤖 LLM-Specific Traps Table
117
116
 
118
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
119
- |:---|:---|:---|
120
- | **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
121
- | **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
122
- | **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
117
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
118
+ | :------------------------------ | :----------------------------------------------------------------- | :---------------------------------------------------------------------------- |
119
+ | **Uncontrolled Re-render Loop** | Mutating state inside render bodies or omitting hook dependencies | Wrap effects with explicit deps and isolate reactive derivations in useMemo |
120
+ | **Accessibility Neglect** | Interactive <div> without role="button", tabIndex, or onKeyDown | Use semantic <button> or provide ARIA role, keyboard handlers, and focus ring |
121
+ | **Layout Shift Flash** | Images/dynamic content without aspect-ratio or explicit dimensions | Enforce aspect-ratio or skeleton placeholders to guarantee zero CLS |
123
122
 
124
123
  ---
125
124
 
@@ -141,5 +140,6 @@ Write a self-contained plan specifying:
141
140
  ### 🛑 Verification-Before-Completion (VBC) Protocol
142
141
 
143
142
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
143
+
144
144
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
145
145
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.
@@ -35,14 +35,14 @@ Before generating, refactoring, or reviewing code in the `intelligent-routing` d
35
35
 
36
36
  Execute all non-trivial tasks through this 7-pass cognitive loop:
37
37
 
38
- | Pass | Phase | Core Action |
39
- |:---|:---|:---|
40
- | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
41
- | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
42
- | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
43
- | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
44
- | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
45
- | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
38
+ | Pass | Phase | Core Action |
39
+ | :--------- | :--------------- | :------------------------------------------------------------------------------------------- |
40
+ | **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. |
41
+ | **Pass 2** | **Plan** | Decompose the task into smallest logical steps; map dependencies and required tool calls. |
42
+ | **Pass 3** | **Execute** | Implement the solution with production-grade craft, zero placeholders, and strict typing. |
43
+ | **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. |
44
+ | **Pass 5** | **Attack** | Perform an adversarial review searching for edge-case failures, race conditions, and traps. |
45
+ | **Pass 6** | **Improve** | Eliminate discovered friction, optimize performance, and harden error boundaries. |
46
46
  | **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. |
47
47
 
48
48
  ---
@@ -241,23 +241,23 @@ This is idempotent — running it multiple times produces the same output. The i
241
241
 
242
242
  ## 🚨 Edge-Case & Failure Mode Matrix
243
243
 
244
- | Scenario | Risk | Mitigation Strategy |
245
- |:---|:---|:---|
246
- | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
247
- | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
248
- | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
249
- | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
250
- | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
244
+ | Scenario | Risk | Mitigation Strategy |
245
+ | :------------------------------------- | :--------------------------------------------------- | :------------------------------------------------------------------------------ |
246
+ | **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
247
+ | **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
248
+ | **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
249
+ | **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
250
+ | **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
251
251
 
252
252
  ---
253
253
 
254
254
  ## 🤖 LLM-Specific Traps Table
255
255
 
256
- | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
257
- |:---|:---|:---|
258
- | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
259
- | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
260
- | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
256
+ | Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
257
+ | :--------------------------------- | :------------------------------------------------------------------------ | :----------------------------------------------------------------------- |
258
+ | **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
259
+ | **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
260
+ | **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |
261
261
 
262
262
  ---
263
263
 
@@ -279,5 +279,6 @@ This is idempotent — running it multiple times produces the same output. The i
279
279
  ### 🛑 Verification-Before-Completion (VBC) Protocol
280
280
 
281
281
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
282
+
282
283
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
283
284
  - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.