tribunal-kit 5.8.5 → 6.0.0

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 (298) hide show
  1. package/.agent/ARCHITECTURE.md +219 -215
  2. package/.agent/agents/accessibility-reviewer.md +66 -151
  3. package/.agent/agents/ai-code-reviewer.md +22 -2
  4. package/.agent/agents/anti-pattern-reviewer.md +99 -0
  5. package/.agent/agents/api-architect.md +19 -2
  6. package/.agent/agents/backend-specialist.md +25 -3
  7. package/.agent/agents/cloud-engineer.md +21 -0
  8. package/.agent/agents/code-archaeologist.md +20 -3
  9. package/.agent/agents/complexity-reviewer.md +22 -2
  10. package/.agent/agents/database-architect.md +24 -3
  11. package/.agent/agents/db-latency-auditor.md +22 -2
  12. package/.agent/agents/debugger.md +19 -3
  13. package/.agent/agents/dependency-reviewer.md +19 -2
  14. package/.agent/agents/devops-engineer.md +24 -3
  15. package/.agent/agents/documentation-writer.md +21 -3
  16. package/.agent/agents/explorer-agent.md +21 -3
  17. package/.agent/agents/frontend-reviewer.md +19 -3
  18. package/.agent/agents/frontend-specialist.md +72 -224
  19. package/.agent/agents/game-developer.md +22 -3
  20. package/.agent/agents/interaction-reviewer.md +118 -0
  21. package/.agent/agents/logic-reviewer.md +18 -3
  22. package/.agent/agents/minimalist-reviewer.md +98 -0
  23. package/.agent/agents/mobile-developer.md +21 -3
  24. package/.agent/agents/mobile-reviewer.md +22 -2
  25. package/.agent/agents/orchestrator.md +19 -3
  26. package/.agent/agents/penetration-tester.md +22 -3
  27. package/.agent/agents/performance-optimizer.md +21 -3
  28. package/.agent/agents/performance-reviewer.md +2 -0
  29. package/.agent/agents/precedence-reviewer.md +19 -5
  30. package/.agent/agents/product-manager.md +20 -3
  31. package/.agent/agents/product-owner.md +22 -1
  32. package/.agent/agents/product-reviewer.md +98 -0
  33. package/.agent/agents/project-planner.md +19 -3
  34. package/.agent/agents/qa-automation-engineer.md +24 -3
  35. package/.agent/agents/resilience-reviewer.md +21 -2
  36. package/.agent/agents/schema-reviewer.md +21 -2
  37. package/.agent/agents/security-auditor.md +7 -1
  38. package/.agent/agents/seo-specialist.md +18 -3
  39. package/.agent/agents/sql-reviewer.md +22 -2
  40. package/.agent/agents/supervisor-agent.md +22 -3
  41. package/.agent/agents/swarm-worker-registry.md +7 -0
  42. package/.agent/agents/system-architect.md +19 -0
  43. package/.agent/agents/test-coverage-reviewer.md +22 -2
  44. package/.agent/agents/test-engineer.md +21 -2
  45. package/.agent/agents/throughput-optimizer.md +22 -2
  46. package/.agent/agents/type-safety-reviewer.md +21 -2
  47. package/.agent/agents/ui-ux-auditor.md +44 -242
  48. package/.agent/agents/ui-visual-auditor.md +99 -0
  49. package/.agent/agents/ux-reviewer.md +104 -0
  50. package/.agent/agents/visual-reviewer.md +98 -0
  51. package/.agent/agents/vitals-reviewer.md +23 -2
  52. package/.agent/history/README.md +53 -0
  53. package/.agent/history/case-law/cases/template-case.json +19 -0
  54. package/.agent/history/integrity_manifest.json +63 -33
  55. package/.agent/history/memory/.memory.idx +517 -1
  56. package/.agent/history/memory/MEMORY.md +35 -1
  57. package/.agent/routing_index.json +272 -690
  58. package/.agent/rules/GEMINI.md +10 -12
  59. package/.agent/rules/GEMINI_PLANNER.md +84 -0
  60. package/.agent/scripts/case_law_manager.js +2 -0
  61. package/.agent/scripts/context_broker.js +152 -0
  62. package/.agent/scripts/guardrail_engine.js +59 -4
  63. package/.agent/scripts/impact_classifier.js +167 -0
  64. package/.agent/scripts/minimal_change_engine.js +437 -0
  65. package/.agent/scripts/pipeline_engine.js +856 -0
  66. package/.agent/scripts/socratic_gate_policy.js +60 -0
  67. package/.agent/scripts/token_budget_broker.js +52 -0
  68. package/.agent/scripts/verify_all.js +13 -0
  69. package/.agent/scripts/visual_audit.js +92 -0
  70. package/.agent/skills/12-principles-of-animation/SKILL.md +19 -10
  71. package/.agent/skills/60fps-animation/SKILL.md +19 -10
  72. package/.agent/skills/accessible-animation/SKILL.md +19 -10
  73. package/.agent/skills/adapt/SKILL.md +19 -10
  74. package/.agent/skills/advanced-rag-pipelines/SKILL.md +21 -3
  75. package/.agent/skills/agent-organizer/SKILL.md +21 -7
  76. package/.agent/skills/agentic-patterns/SKILL.md +19 -7
  77. package/.agent/skills/ai-prompt-injection-defense/SKILL.md +21 -7
  78. package/.agent/skills/animation-on-scroll/SKILL.md +19 -10
  79. package/.agent/skills/animation-systems/SKILL.md +19 -10
  80. package/.agent/skills/antfu-conventions/SKILL.md +21 -10
  81. package/.agent/skills/api-patterns/SKILL.md +21 -7
  82. package/.agent/skills/api-security-auditor/SKILL.md +21 -7
  83. package/.agent/skills/app-builder/SKILL.md +21 -7
  84. package/.agent/skills/apple-design/SKILL.md +19 -10
  85. package/.agent/skills/architecture/SKILL.md +21 -7
  86. package/.agent/skills/audit-and-fix/SKILL.md +19 -10
  87. package/.agent/skills/authentication-best-practices/SKILL.md +21 -7
  88. package/.agent/skills/backend-security-expert/SKILL.md +21 -7
  89. package/.agent/skills/baseline-ui/SKILL.md +19 -10
  90. package/.agent/skills/bash-linux/SKILL.md +21 -7
  91. package/.agent/skills/behavioral-modes/SKILL.md +19 -7
  92. package/.agent/skills/better-colors/SKILL.md +19 -10
  93. package/.agent/skills/better-ui/SKILL.md +19 -10
  94. package/.agent/skills/bolder/SKILL.md +19 -10
  95. package/.agent/skills/brainstorming/SKILL.md +17 -7
  96. package/.agent/skills/browser-native-ai/SKILL.md +19 -3
  97. package/.agent/skills/build-primitive/SKILL.md +19 -10
  98. package/.agent/skills/building-native-ui/SKILL.md +21 -7
  99. package/.agent/skills/cicd-pro/SKILL.md +21 -10
  100. package/.agent/skills/clarify/SKILL.md +19 -10
  101. package/.agent/skills/clean-code/SKILL.md +21 -7
  102. package/.agent/skills/cloud-architect/SKILL.md +21 -10
  103. package/.agent/skills/cobejs/SKILL.md +19 -10
  104. package/.agent/skills/code-review-checklist/SKILL.md +21 -7
  105. package/.agent/skills/codebase-design/SKILL.md +21 -10
  106. package/.agent/skills/colorize/SKILL.md +19 -10
  107. package/.agent/skills/compact-landing/SKILL.md +19 -10
  108. package/.agent/skills/company-logos/SKILL.md +19 -10
  109. package/.agent/skills/config-validator/SKILL.md +21 -7
  110. package/.agent/skills/containerization-pro/SKILL.md +21 -10
  111. package/.agent/skills/create-design-md/SKILL.md +19 -10
  112. package/.agent/skills/critique/SKILL.md +19 -10
  113. package/.agent/skills/csharp-developer/SKILL.md +21 -7
  114. package/.agent/skills/data-validation-schemas/SKILL.md +21 -7
  115. package/.agent/skills/database-design/SKILL.md +21 -7
  116. package/.agent/skills/delight/SKILL.md +19 -10
  117. package/.agent/skills/deployment-procedures/SKILL.md +21 -7
  118. package/.agent/skills/design-lab/SKILL.md +21 -10
  119. package/.agent/skills/devops-engineer/SKILL.md +21 -7
  120. package/.agent/skills/devops-incident-responder/SKILL.md +21 -7
  121. package/.agent/skills/diagnosing-bugs/SKILL.md +21 -10
  122. package/.agent/skills/distill/SKILL.md +19 -10
  123. package/.agent/skills/documentation-templates/SKILL.md +21 -7
  124. package/.agent/skills/domain-modeling/SKILL.md +21 -10
  125. package/.agent/skills/edge-computing/SKILL.md +21 -7
  126. package/.agent/skills/emil-design-eng/SKILL.md +19 -10
  127. package/.agent/skills/error-resilience/SKILL.md +21 -7
  128. package/.agent/skills/extract-design-system/SKILL.md +21 -7
  129. package/.agent/skills/fabel-protocol/SKILL.md +19 -2
  130. package/.agent/skills/fixing-accessibility/SKILL.md +19 -10
  131. package/.agent/skills/fixing-metadata/SKILL.md +19 -10
  132. package/.agent/skills/fixing-motion-performance/SKILL.md +19 -10
  133. package/.agent/skills/framer-motion-expert/SKILL.md +19 -6
  134. package/.agent/skills/frontend-design/SKILL.md +64 -201
  135. package/.agent/skills/frontend-security-expert/SKILL.md +21 -7
  136. package/.agent/skills/game-design-expert/SKILL.md +21 -7
  137. package/.agent/skills/game-engineering-expert/SKILL.md +21 -7
  138. package/.agent/skills/generative-ui-expert/SKILL.md +19 -3
  139. package/.agent/skills/geo-fundamentals/SKILL.md +21 -7
  140. package/.agent/skills/git-pro/SKILL.md +21 -10
  141. package/.agent/skills/github-operations/SKILL.md +21 -7
  142. package/.agent/skills/gpt-taste/SKILL.md +19 -10
  143. package/.agent/skills/gsap-core/SKILL.md +21 -4
  144. package/.agent/skills/gsap-frameworks/SKILL.md +21 -4
  145. package/.agent/skills/gsap-performance/SKILL.md +20 -5
  146. package/.agent/skills/gsap-plugins/SKILL.md +20 -5
  147. package/.agent/skills/gsap-react/SKILL.md +20 -5
  148. package/.agent/skills/gsap-scrolltrigger/SKILL.md +21 -4
  149. package/.agent/skills/gsap-timeline/SKILL.md +20 -5
  150. package/.agent/skills/gsap-utils/SKILL.md +20 -5
  151. package/.agent/skills/harden/SKILL.md +19 -10
  152. package/.agent/skills/harness-protocol/SKILL.md +20 -4
  153. package/.agent/skills/i18n-localization/SKILL.md +21 -7
  154. package/.agent/skills/impeccable/SKILL.md +19 -10
  155. package/.agent/skills/improve-codebase-architecture/SKILL.md +21 -10
  156. package/.agent/skills/improve-ui/SKILL.md +19 -10
  157. package/.agent/skills/intelligent-routing/SKILL.md +19 -7
  158. package/.agent/skills/knowledge-graph/SKILL.md +20 -4
  159. package/.agent/skills/landing-page/SKILL.md +20 -10
  160. package/.agent/skills/lint-and-validate/SKILL.md +21 -7
  161. package/.agent/skills/llm-engineering/SKILL.md +21 -7
  162. package/.agent/skills/local-first/SKILL.md +21 -7
  163. package/.agent/skills/local-first-architecture/SKILL.md +19 -10
  164. package/.agent/skills/lottie-animation/SKILL.md +19 -10
  165. package/.agent/skills/marquee-loop/SKILL.md +19 -10
  166. package/.agent/skills/masked-reveal/SKILL.md +19 -10
  167. package/.agent/skills/mcp-builder/SKILL.md +21 -7
  168. package/.agent/skills/micro-interaction/SKILL.md +19 -10
  169. package/.agent/skills/mobile-design/SKILL.md +21 -6
  170. package/.agent/skills/monorepo-management/SKILL.md +21 -7
  171. package/.agent/skills/morphing-icons/SKILL.md +19 -10
  172. package/.agent/skills/motion-engineering/SKILL.md +20 -7
  173. package/.agent/skills/nextjs-react-expert/SKILL.md +19 -7
  174. package/.agent/skills/nodejs-best-practices/SKILL.md +21 -7
  175. package/.agent/skills/observability/SKILL.md +21 -7
  176. package/.agent/skills/page-transition-animation/SKILL.md +19 -10
  177. package/.agent/skills/parallel-agents/SKILL.md +23 -7
  178. package/.agent/skills/performance-profiling/SKILL.md +21 -7
  179. package/.agent/skills/plan-writing/SKILL.md +21 -7
  180. package/.agent/skills/platform-engineer/SKILL.md +21 -7
  181. package/.agent/skills/playwright-best-practices/SKILL.md +21 -7
  182. package/.agent/skills/polish/SKILL.md +19 -10
  183. package/.agent/skills/powershell-windows/SKILL.md +21 -7
  184. package/.agent/skills/pricing-page/SKILL.md +19 -10
  185. package/.agent/skills/product-aware-heuristics/SKILL.md +358 -0
  186. package/.agent/skills/progressive-blur/SKILL.md +19 -10
  187. package/.agent/skills/project-idioms/SKILL.md +20 -8
  188. package/.agent/skills/python-patterns/SKILL.md +21 -7
  189. package/.agent/skills/python-pro/SKILL.md +21 -6
  190. package/.agent/skills/quieter/SKILL.md +19 -10
  191. package/.agent/skills/react-doctor/SKILL.md +19 -10
  192. package/.agent/skills/react-specialist/SKILL.md +19 -6
  193. package/.agent/skills/readme-builder/SKILL.md +21 -7
  194. package/.agent/skills/realtime-patterns/SKILL.md +21 -7
  195. package/.agent/skills/red-team-tactics/SKILL.md +21 -7
  196. package/.agent/skills/redesign-skill/SKILL.md +19 -10
  197. package/.agent/skills/review-animations/SKILL.md +21 -10
  198. package/.agent/skills/rust-pro/SKILL.md +21 -7
  199. package/.agent/skills/seo-fundamentals/SKILL.md +21 -7
  200. package/.agent/skills/server-management/SKILL.md +21 -7
  201. package/.agent/skills/shadcn-ui-expert/SKILL.md +21 -7
  202. package/.agent/skills/shape/SKILL.md +19 -10
  203. package/.agent/skills/skill-creator/SKILL.md +21 -7
  204. package/.agent/skills/soft-skill/SKILL.md +19 -10
  205. package/.agent/skills/sounds-on-the-web/SKILL.md +19 -10
  206. package/.agent/skills/sql-pro/SKILL.md +21 -7
  207. package/.agent/skills/supabase-postgres-best-practices/SKILL.md +21 -7
  208. package/.agent/skills/svg-animation/SKILL.md +19 -10
  209. package/.agent/skills/swiftui-expert/SKILL.md +21 -7
  210. package/.agent/skills/swiss-design/SKILL.md +19 -10
  211. package/.agent/skills/system-design-pro/SKILL.md +21 -9
  212. package/.agent/skills/systematic-debugging/SKILL.md +21 -7
  213. package/.agent/skills/tailwind-patterns/SKILL.md +21 -7
  214. package/.agent/skills/taste-skill/SKILL.md +19 -10
  215. package/.agent/skills/tdd-workflow/SKILL.md +21 -10
  216. package/.agent/skills/test-result-analyzer/SKILL.md +18 -6
  217. package/.agent/skills/testing-patterns/SKILL.md +21 -7
  218. package/.agent/skills/thermo-nuclear-code-quality-review/SKILL.md +21 -10
  219. package/.agent/skills/thinking-protocol/SKILL.md +20 -8
  220. package/.agent/skills/to-spring-or-not-to-spring/SKILL.md +19 -10
  221. package/.agent/skills/transitions-dev/SKILL.md +19 -10
  222. package/.agent/skills/trend-researcher/SKILL.md +17 -6
  223. package/.agent/skills/typescript-advanced/SKILL.md +21 -7
  224. package/.agent/skills/typeset/SKILL.md +19 -10
  225. package/.agent/skills/ui-reasoning-engine/SKILL.md +154 -0
  226. package/.agent/skills/ui-skill-packs/SKILL.md +77 -0
  227. package/.agent/skills/ui-skills-root/SKILL.md +21 -9
  228. package/.agent/skills/ui-ux-pro-max/SKILL.md +62 -583
  229. package/.agent/skills/ui-ux-researcher/SKILL.md +17 -6
  230. package/.agent/skills/vue-expert/SKILL.md +19 -6
  231. package/.agent/skills/vulnerability-scanner/SKILL.md +21 -7
  232. package/.agent/skills/web-accessibility-auditor/SKILL.md +21 -7
  233. package/.agent/skills/web-design-guidelines/SKILL.md +32 -206
  234. package/.agent/skills/web-quality-audit/SKILL.md +19 -10
  235. package/.agent/skills/webapp-testing/SKILL.md +21 -7
  236. package/.agent/skills/webgpu-performance/SKILL.md +19 -3
  237. package/.agent/skills/whimsy-injector/SKILL.md +20 -10
  238. package/.agent/skills/workflow-optimizer/SKILL.md +16 -6
  239. package/.agent/templates/DESIGN.md +292 -0
  240. package/.agent/templates/design-tokens.json +137 -0
  241. package/.agent/workflows/acf.md +13 -6
  242. package/.agent/workflows/api-tester.md +15 -8
  243. package/.agent/workflows/audit.md +19 -8
  244. package/.agent/workflows/brainstorm.md +14 -9
  245. package/.agent/workflows/changelog.md +14 -8
  246. package/.agent/workflows/create.md +16 -8
  247. package/.agent/workflows/debug.md +15 -10
  248. package/.agent/workflows/deploy.md +16 -8
  249. package/.agent/workflows/enhance.md +15 -10
  250. package/.agent/workflows/fix.md +15 -8
  251. package/.agent/workflows/generate.md +17 -11
  252. package/.agent/workflows/marathon.md +15 -8
  253. package/.agent/workflows/migrate.md +16 -8
  254. package/.agent/workflows/minimal.md +94 -0
  255. package/.agent/workflows/orchestrate.md +15 -8
  256. package/.agent/workflows/performance-benchmarker.md +15 -8
  257. package/.agent/workflows/pipeline.md +155 -0
  258. package/.agent/workflows/plan.md +14 -10
  259. package/.agent/workflows/preview.md +14 -7
  260. package/.agent/workflows/refactor.md +16 -8
  261. package/.agent/workflows/review-ai.md +15 -7
  262. package/.agent/workflows/review.md +15 -7
  263. package/.agent/workflows/session.md +14 -7
  264. package/.agent/workflows/status.md +13 -7
  265. package/.agent/workflows/strengthen-skills.md +15 -6
  266. package/.agent/workflows/super-prompt.md +19 -10
  267. package/.agent/workflows/swarm.md +15 -7
  268. package/.agent/workflows/test.md +15 -8
  269. package/.agent/workflows/tribunal-backend.md +16 -9
  270. package/.agent/workflows/tribunal-database.md +15 -8
  271. package/.agent/workflows/tribunal-frontend.md +26 -11
  272. package/.agent/workflows/tribunal-full.md +29 -14
  273. package/.agent/workflows/tribunal-mobile.md +15 -8
  274. package/.agent/workflows/tribunal-performance.md +15 -8
  275. package/.agent/workflows/tribunal-speed.md +16 -9
  276. package/.agent/workflows/tribunal-ui.md +82 -0
  277. package/.agent/workflows/ui-ux-pro-max.md +51 -107
  278. package/CONTRIBUTING.md +2 -2
  279. package/README.md +5 -5
  280. package/bin/mcp-server.js +81 -31
  281. package/bin/wrapper.js +17 -6
  282. package/dist/cli.js +9 -1
  283. package/dist/commands/compile.js +7 -0
  284. package/dist/commands/context.js +8 -3
  285. package/dist/commands/graph.js +8 -2
  286. package/dist/commands/init.js +13 -2
  287. package/dist/commands/memory.js +119 -68
  288. package/dist/commands/minimal.js +71 -0
  289. package/dist/commands/optimize.js +15 -5
  290. package/dist/esm/index.mjs +26 -32
  291. package/dist/utils/fs.js +10 -4
  292. package/dist/utils/helpers.js +10 -1
  293. package/dist/utils/version.js +9 -2
  294. package/mcp_config.json +10 -1
  295. package/package.json +17 -14
  296. package/scripts/benchmark.js +16 -0
  297. package/scripts/sync-version.js +1 -1
  298. package/scripts/visual_audit.js +126 -0
@@ -1,12 +1,29 @@
1
1
  ---
2
2
  name: fabel-protocol
3
3
  description: Distilled Fabel-5 cognitive intelligence protocol. Injects epistemic reasoning, coding discipline, design evaluation cascades, and orchestration patterns into any AI model. Load this skill to make any model think, reason, code, and design like Fabel-5. Activates for complex builds, code generation, design tasks, and multi-agent orchestration.
4
- version: 1.0.0
5
- last-updated: 2026-07-07
4
+ version: 3.0.0
5
+ last-updated: 2026-07-30
6
+ skills:
7
+ - agentic-patterns
8
+ - thinking-protocol
9
+ - knowledge-graph
10
+ tools: Read, Grep, Glob, Bash, Edit, Write
11
+ scripts-binding:
12
+ - .agent/scripts/checklist.js
13
+ - .agent/scripts/verify_all.js
6
14
  ---
7
15
 
8
16
  # Fabel Protocol — Cognitive Intelligence Engine
9
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before executing reasoning loops, you MUST inspect:
23
+ 1. `package.json` / dependency manifests → Verify exact framework version boundaries (React 19 vs 18, Next.js 15 vs 14)
24
+ 2. Epistemic Confidence Checklist (Section 1) → Categorize implementation confidence L1 to L5
25
+ 3. High-Risk Hallucination Heatmap (Section 7) → Tag uncertain ORM/SDK method calls with `// VERIFY: [reason]` tags
26
+
10
27
  > Distilled from the Fabel-5 system prompt (191KB → 2,000 tokens). Makes any model reason like Fabel-5.
11
28
 
12
29
  ---
@@ -1,20 +1,29 @@
1
1
  ---
2
2
  name: fixing-accessibility
3
3
  description: Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.
4
- version: 1.0.0
5
- last-updated: 2026-07-22
6
- applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
7
- routing:
8
- domain: UI Craft & Accessibility
9
- tier: pro
10
- co-requires: [audit-and-fix, web-accessibility-auditor]
11
- trigger-signals:
12
- strong: [fixing-accessibility, accessibility audit, WCAG 2.2, aria-label, keyboard navigation, focus trap, color contrast]
13
- weak: [a11y, focus ring, screen reader]
4
+ version: 3.0.0
5
+ last-updated: 2026-07-30
6
+ skills:
7
+ - audit-and-fix
8
+ - build-primitive
9
+ - baseline-ui
10
+ tools: Read, Grep, Glob, Bash, Edit, Write
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
14
14
  ---
15
15
 
16
16
  # Fixing Accessibility — WCAG 2.2 AA Audit & Remediation
17
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before remediating HTML accessibility defects, you MUST inspect:
23
+ 1. Priority Matrix (Section 22) → Ensure accessible names on icon buttons (P1) and native HTML keyboard controls (P2) before styling
24
+ 2. Focus Ring Policy (Section 29) → Ban `outline: none` without providing explicit `:focus-visible` replacement (`2px` ring + offset)
25
+ 3. Form Error Association (Section 32) → Attach `aria-invalid="true"` and `aria-describedby` pointing to error text IDs
26
+
18
27
  Guidelines for detecting, prioritizing, and fixing accessibility defects across web interfaces.
19
28
 
20
29
  ---
@@ -1,20 +1,29 @@
1
1
  ---
2
2
  name: fixing-metadata
3
3
  description: Audit and fix page metadata including page titles, meta descriptions, Open Graph, Twitter cards, canonical URLs, and JSON-LD structured data.
4
- version: 1.0.0
5
- last-updated: 2026-07-22
6
- applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
7
- routing:
8
- domain: Technical SEO & Metadata Optimization
9
- tier: pro
10
- co-requires: [seo-fundamentals, web-quality-audit]
11
- trigger-signals:
12
- strong: [fixing-metadata, Open Graph tags, Twitter card metadata, canonical URL, JSON-LD structured data, meta description fix]
13
- weak: [fix metadata, SEO tags]
4
+ version: 3.0.0
5
+ last-updated: 2026-07-30
6
+ skills:
7
+ - nextjs-react-expert
8
+ - baseline-ui
9
+ - compact-landing
10
+ tools: Read, Grep, Glob, Bash, Edit, Write
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
14
14
  ---
15
15
 
16
16
  # Fixing Metadata — Technical SEO & Open Graph Tags
17
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before engineering metadata or Open Graph tags, you MUST inspect:
23
+ 1. Title & Meta Description Caps (Section 24) → Restrict title tags to 50–60 chars and meta descriptions to 140–155 chars
24
+ 2. Absolute Image URL Rule (Section 74) → Enforce full absolute HTTPS URLs (`https://domain.com/og.jpg`) for `og:image` and `twitter:image`
25
+ 3. Twitter Card Type (Section 39) → Always specify `<meta name="twitter:card" content="summary_large_image" />` for prominent social previews
26
+
18
27
  Audit, generate, and fix page metadata for rich social previews, search engine indexing, and structured data.
19
28
 
20
29
  ---
@@ -1,20 +1,29 @@
1
1
  ---
2
2
  name: fixing-motion-performance
3
3
  description: Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.
4
- version: 1.0.0
5
- last-updated: 2026-07-22
6
- applies-to-model: gemini-3-6-flash, claude-3-7-sonnet
7
- routing:
8
- domain: UI Motion & Performance
9
- tier: pro
10
- co-requires: [60fps-animation, gsap-performance]
11
- trigger-signals:
12
- strong: [fixing-motion-performance, layout thrashing, compositor properties, scroll jank, animation stutter, GPU acceleration, will-change]
13
- weak: [jank, slow animation, stutter]
4
+ version: 3.0.0
5
+ last-updated: 2026-07-30
6
+ skills:
7
+ - 60fps-animation
8
+ - motion-engineering
9
+ - gsap-performance
10
+ tools: Read, Grep, Glob, Bash, Edit, Write
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
14
14
  ---
15
15
 
16
16
  # Fixing Motion Performance — 60/120fps Jank-Free Animation
17
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before auditing or fixing animation performance, you MUST inspect:
23
+ 1. Browser Rendering Pipeline (Section 22) → Restrict properties to Composite-only (`transform`, `opacity`) and eliminate Layout/Paint animators
24
+ 2. Layout Thrashing (Section 33) → Batch all DOM reads (`offsetHeight`, `getBoundingClientRect`) before executing DOM writes (`style.height = ...`)
25
+ 3. `will-change` VRAM management (Section 53) → Remove `will-change` hints upon animation completion
26
+
18
27
  Guidelines for auditing and resolving web animation jank, layout thrashing, and GPU rendering bottlenecks.
19
28
 
20
29
  ---
@@ -1,16 +1,29 @@
1
1
  ---
2
2
  name: framer-motion-expert
3
3
  description: Framer Motion 12+ for React. Declarative animations, layout transitions, gestures, scroll-linked motion, AnimatePresence, useAnimate, LazyMotion. Use when building component animations, page transitions, shared layout animations, or gesture-driven UI.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 3.1.0
6
- last-updated: 2026-04-06
7
- routing:
8
- domain: general
9
- tier: basic
4
+ tools: Read, Grep, Glob, Bash, Edit, Write
5
+ version: 3.0.0
6
+ last-updated: 2026-07-30
7
+ skills:
8
+ - motion-engineering
9
+ - 60fps-animation
10
+ - accessible-animation
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
10
14
  ---
11
15
 
12
16
  # Framer Motion 12+ — Dense Reference
13
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before writing Framer Motion code in React, you MUST inspect:
23
+ 1. `package.json` / Next.js Client Boundaries → Add `"use client"` directive on Next.js App Router files containing `motion.X`
24
+ 2. AnimatePresence & layoutId Rules (Section 117) → Enforce `mode="wait"` and ensure every `<AnimatePresence>` child has a unique `key`
25
+ 3. Bundle Optimization (Section 182) → Use `<LazyMotion features={domAnimation}>` with `m.div` for lightweight production bundles
26
+
14
27
  ## Hallucination Traps (Read First)
15
28
 
16
29
  - ❌ `<Motion>` (capital M) → ✅ `motion.div` (lowercase dot notation)
@@ -1,249 +1,112 @@
1
1
  ---
2
2
  name: frontend-design
3
- description: Design thinking for web UI. Micro-interactions, visual hierarchy, typography scaling, HSL color palettes, spacing systems, and CSS-first UI logic. Avoid generic AI aesthetics.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 3.1.0
6
- last-updated: 2026-04-06
7
- applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
8
- routing:
9
- domain: general
10
- tier: basic
3
+ description: Design engineering principles for React/Next.js. Relative color syntax (OKLCH), spatial grid math, fluid container queries, and contrast validation.
4
+ version: 3.0.0
5
+ last-updated: 2026-07-30
6
+ skills:
7
+ - baseline-ui
8
+ - better-colors
9
+ - better-ui
10
+ tools: Read, Grep, Glob, Bash, Edit, Write
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
11
14
  ---
12
15
 
13
- # Frontend Design — Dense Reference
16
+ # Frontend Design — Technical Spacing & Color Science
14
17
 
15
- ## Hallucination Traps (Read First)
18
+ ---
16
19
 
17
- - Purple gradient backgrounds (`from-purple-500 to-blue-500`) → ✅ The worst AI UI cliché. Use high-contrast solid colors, grain, or sophisticated HSL mono-palettes.
18
- - ❌ Hardcoded pixels (`font-size: 14px`) → ✅ Use `rem` for accessibility and scaling (`1rem = 16px`).
19
- - ❌ Gray text (`#888`) on white → ✅ Fails WCAG contrast. Text must be `4.5:1` ratio.
20
- - ❌ Generic sans-serif → ✅ Inter, Geist, Roboto Mono, or system-ui. Typography is 80% of design.
21
- - ❌ "Bento Box" grids for everything → ✅ Overused pattern. Use directional flow or asymmetric layouts.
22
- - ❌ Symmetrical layouts out of laziness → ✅ Tension and blank space (negative space) drive premium feel.
23
- - ❌ Infinite scrolling without context → ✅ Provide clear footers or logical pagination markers.
24
- - ❌ Over-animating everything (`all elements fade in`) → ✅ Animate state changes (hover, focus, submit), not static entry layout unless scrollytelling.
20
+ ## Mandatory Pre-Flight Context Inspection
25
21
 
26
- ---
22
+ Before implementing front-end designs or CSS layout systems, you MUST inspect:
23
+ 1. Relative Color Syntax (Section 16) → Derive hover/active states dynamically with `oklch(from var(--color-primary) calc(l - 0.08) c h)`
24
+ 2. Nested Radius Math (Section 54) → Enforce `outer_radius = inner_radius + padding_inner` for nested card containers
25
+ 3. APCA Contrast Thresholds (Section 81) → Ensure Lc > 75 for body text, Lc > 60 for headings, and Lc > 45 for borders and labels
27
26
 
28
- ## 1. Modern Color Systems (OKLCH & HSL)
27
+ This skill guides the implementation of responsive layout systems, color science, and spatial tokens.
29
28
 
30
- Never use raw flat HEX colors. Use OKLCH (perceptually uniform) or HSL to build scalable, harmonic themes.
29
+ ---
31
30
 
31
+ ## 1. Relative Color Syntax & OKLCH Theme Tokens
32
+
33
+ Perceptually uniform color science ensures stable contrast. Use CSS **Relative Color Syntax** to derive state colors dynamically:
32
34
  ```css
33
35
  :root {
34
- /* OKLCH perceptual uniformity: lightness (0-100%), chroma (0-0.37), hue (0-360) */
35
- --brand-primary: oklch(62% 0.21 275);
36
- --brand-hover: oklch(from var(--brand-primary) calc(l - 0.1) c h); /* Relative Color Syntax */
36
+ /* base color values */
37
+ --color-primary: oklch(62% 0.21 250); /* Brand electric blue */
38
+
39
+ /* Deriving hover states dynamically: reduce lightness, preserve chroma and hue */
40
+ --color-primary-hover: oklch(from var(--color-primary) calc(l - 0.08) c h);
41
+ --color-primary-active: oklch(from var(--color-primary) calc(l - 0.12) c h);
37
42
 
38
- --bg-base: oklch(98% 0.005 240);
43
+ /* Backgrounds */
39
44
  --bg-surface: oklch(100% 0 0);
40
- --text-main: oklch(20% 0.02 240);
41
- --text-muted: oklch(50% 0.02 240);
45
+ --text-main: oklch(20% 0.02 250);
42
46
  }
43
47
 
44
- /* Light/Dark mode via native light-dark() function or OLED media query */
45
- :root {
46
- color-scheme: light dark;
47
- --bg-surface: light-dark(oklch(100% 0 0), oklch(15% 0.01 240));
48
- --text-main: light-dark(oklch(20% 0.02 240), oklch(95% 0.01 240));
48
+ [data-theme="dark"] {
49
+ --bg-surface: oklch(14% 0.008 250);
50
+ --text-main: oklch(93% 0.003 250);
49
51
  }
50
52
  ```
51
53
 
52
54
  ---
53
55
 
54
- ## 2. Spatial Systems & Container Queries
55
-
56
- Design relies on structural rhythm and component-level adaptability.
57
-
58
- - **Base Spacing Grid (8px)**: Micro `4px`, `8px` | Component `16px`, `24px` | Section `48px`, `64px`, `96px`
59
- - **Nested Border Radius Formula**: `outer_radius = inner_radius + padding`
60
- - **Fluid Typography**: Use `clamp()` and `cqi` container units over macro media queries.
56
+ ## 2. Spatial Grid Math & Radius Tokens
61
57
 
58
+ Enforce an 8px spatial grid calculated mathematically to ensure alignment precision:
62
59
  ```css
63
- /* Container Queries for Portable Components */
64
- .card-container {
65
- container-type: inline-size;
66
- container-name: card;
67
- }
68
-
69
- @container card (min-width: 400px) {
70
- .card-body {
71
- display: grid;
72
- grid-template-columns: 1fr 2fr;
73
- gap: 1.5cqi;
74
- }
75
- }
76
-
77
- /* Typographic Balance */
78
- h1, h2, h3 {
79
- font-size: clamp(2rem, 4vw + 1rem, 4rem);
80
- letter-spacing: -0.02em;
81
- text-wrap: balance; /* Prevents awkward multiline headline breaks */
82
- }
83
-
84
- p {
85
- font-size: 1rem;
86
- max-width: 65ch;
87
- text-wrap: pretty; /* Eliminates typographical orphans in body text */
60
+ :root {
61
+ --base-grid: 8px;
62
+
63
+ --space-xs: calc(var(--base-grid) * 0.5); /* 4px - icon gaps */
64
+ --space-sm: calc(var(--base-grid) * 1); /* 8px - tag paddings */
65
+ --space-md: calc(var(--base-grid) * 2); /* 16px - inputs */
66
+ --space-lg: calc(var(--base-grid) * 3); /* 24px - card padding */
67
+ --space-xl: calc(var(--base-grid) * 4); /* 32px - section gaps */
88
68
  }
89
69
  ```
90
70
 
91
- ---
92
-
93
- ## 3. Interaction & Entry Motion (@starting-style)
94
-
95
- A premium UI reacts to user actions instantly and provides smooth DOM mount transitions.
96
-
97
- ```css
98
- /* Physical press feedback */
99
- .btn {
100
- transition: transform 0.15s cubic-bezier(0.2, 0.8, 0.4, 1), box-shadow 0.15s ease;
101
- }
102
- .btn:active {
103
- transform: scale(0.97);
104
- }
105
-
106
- /* Entry/Exit Animations for DOM Elements (@starting-style) */
107
- .toast {
108
- display: none;
109
- opacity: 0;
110
- transform: translateY(8px);
111
- transition: opacity 0.25s ease, transform 0.25s ease, display 0.25s allow-discrete;
112
- }
113
- .toast.is-open {
114
- display: flex;
115
- opacity: 1;
116
- transform: translateY(0);
117
- }
118
- @starting-style {
119
- .toast.is-open {
120
- opacity: 0;
121
- transform: translateY(8px);
122
- }
123
- }
124
- ```
71
+ ### Nested Radius Formula
72
+ Ensure component inner borders track correctly:
73
+ `outer_radius = inner_radius + padding_inner`
74
+ If container padding is `16px` and inner content radius is `8px`, then container outer radius must be exactly `24px` (`8px + 16px`).
125
75
 
126
76
  ---
127
77
 
128
- ## 4. Modern Glassmorphism & Multi-Layer Depth
129
-
130
- Avoid flat 1px borders and muddy single shadows. Use multi-layered elevation.
78
+ ## 3. Responsive Layouts & Container Queries
131
79
 
80
+ Avoid viewport-level media queries for self-contained components. Use container queries to make components portable:
132
81
  ```css
133
- .card {
134
- background: light-dark(rgba(255, 255, 255, 0.8), rgba(20, 20, 25, 0.8));
135
- backdrop-filter: blur(16px);
136
- -webkit-backdrop-filter: blur(16px);
137
- border: 1px solid light-dark(rgba(0, 0, 0, 0.08), rgba(255, 255, 255, 0.12));
138
- border-radius: 16px;
139
- box-shadow:
140
- 0 1px 2px oklch(0% 0 0 / 0.05),
141
- 0 4px 12px oklch(0% 0 0 / 0.08);
82
+ .component-wrapper {
83
+ container-type: inline-size;
84
+ container-name: component;
142
85
  }
143
- ```
144
-
145
- ---
146
86
 
147
- ## 5. Accessibility (WCAG 2.2 AA Standards)
148
-
149
- Design is broken if it excludes users.
150
- - ✅ **SC 2.5.8 Target Size**: Interactive controls must be at least `24x24px` CSS pixels (min `44x44px` for touch targets).
151
- - ✅ **SC 2.4.11 Focus Not Obscured**: Focused elements must never be completely hidden by sticky headers/footers.
152
- - ✅ **SC 2.4.13 Focus Appearance**: Visible focus rings must achieve `3:1` contrast ratio with a minimum 2px perimeter offset.
153
- - ✅ **Color Alone**: Never rely solely on color to convey state (pair error alerts with icons).
154
-
155
- ```css
156
- button:focus-visible, a:focus-visible {
157
- outline: 2px solid var(--brand-primary);
158
- outline-offset: 3px;
87
+ @container component (min-width: 450px) {
88
+ .inner-layout {
89
+ display: grid;
90
+ grid-template-columns: repeat(2, 1fr);
91
+ gap: var(--space-md);
92
+ }
159
93
  }
160
94
  ```
161
95
 
162
96
  ---
163
97
 
164
- AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
98
+ ## 4. APCA Contrast Guidelines
165
99
 
166
- 1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
167
- 2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
168
- 3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
169
- 4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
170
- 5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
100
+ Ensure that typography meets the APCA Lc guidelines:
101
+ * Lc > 75 for body text elements.
102
+ * Lc > 60 for large titles and headings.
103
+ * Lc > 45 for secondary input labels and border guides.
171
104
 
172
105
  ---
173
106
 
174
- **Slash command: `/review` or `/tribunal-full`**
175
- **Active reviewers: `logic-reviewer` · `security-auditor`**
176
-
177
- ### ❌ Forbidden AI Tropes
178
-
179
- 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
180
- 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
181
- 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
182
-
183
- Review these questions before confirming output:
184
-
185
- ```
186
- ✅ Did I rely ONLY on real, verified tools and methods?
187
- ✅ Is this solution appropriately scoped to the user's constraints?
188
- ✅ Did I handle potential failure modes and edge cases?
189
- ✅ Have I avoided generic boilerplate that doesn't add value?
190
- ```
191
-
192
- ### 🛑 Verification-Before-Completion (VBC) Protocol
193
-
194
- **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
195
-
196
- - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
197
- - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
198
-
199
107
  ## Pre-Flight Checklist
200
-
201
108
  - [ ] Have I reviewed the user's specific constraints and requests?
202
109
  - [ ] Have I checked the environment for relevant existing implementations?
203
110
 
204
111
  ## VBC Protocol (Verification-Before-Completion)
205
-
206
112
  You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
207
-
208
- ---
209
-
210
- ## 🤖 LLM-Specific Traps
211
-
212
- AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
213
-
214
- 1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
215
- 2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
216
- 3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
217
- 4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
218
- 5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
219
-
220
- ---
221
-
222
- ## 🏛️ Tribunal Integration (Anti-Hallucination)
223
-
224
- **Slash command: `/review` or `/tribunal-full`**
225
- **Active reviewers: `logic-reviewer` · `security-auditor`**
226
-
227
- ### ❌ Forbidden AI Tropes
228
-
229
- 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
230
- 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
231
- 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
232
-
233
- ### ✅ Pre-Flight Self-Audit
234
-
235
- Review these questions before confirming output:
236
-
237
- ```
238
- ✅ Did I rely ONLY on real, verified tools and methods?
239
- ✅ Is this solution appropriately scoped to the user's constraints?
240
- ✅ Did I handle potential failure modes and edge cases?
241
- ✅ Have I avoided generic boilerplate that doesn't add value?
242
- ```
243
-
244
- ### 🛑 Verification-Before-Completion (VBC) Protocol
245
-
246
- **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
247
-
248
- - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
249
- - ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing tests, compile success, or equivalent proof) that your output works as intended.
@@ -1,17 +1,31 @@
1
1
  ---
2
2
  name: frontend-security-expert
3
3
  description: Frontend security auditing for modern meta-frameworks. Focuses on React/Next.js UI paradigms, hydration poisoning, third-party script supply chain, local storage security, and XSS prevention in modern environments.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 1.0.0
6
- last-updated: 2026-05-22
7
- applies-to-model: gemini-3-1-pro, claude-3-7-sonnet
8
- routing:
9
- domain: general
10
- tier: basic
4
+ tools: Read, Grep, Glob, Bash, Edit, Write
5
+ version: 3.0.0
6
+ last-updated: 2026-07-30
7
+ skills:
8
+ - backend-security-expert
9
+ - api-security-auditor
10
+ - vulnerability-scanner
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
11
14
  ---
12
15
 
13
16
  # Frontend Security Expert — Modern Meta-Frameworks
14
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before auditing or writing client-side code, you MUST inspect:
23
+ 1. XSS Sanitize Rules (Section 28) → Require DOMPurify for any `dangerouslySetInnerHTML` and audit dynamic `javascript:` URIs
24
+ 2. HttpOnly Auth Token Storage (Section 34) → Ban storing JWTs or auth tokens in `localStorage` or `sessionStorage`; use `HttpOnly`, `Secure`, `SameSite` cookies
25
+ 3. PostMessage Origin Verification (Section 46) → Never use `targetOrigin: '*'` and always validate `event.origin` on receiving handlers
26
+
27
+ # Frontend Security Expert — Modern Meta-Frameworks
28
+
15
29
  ## Hallucination Traps (Read First)
16
30
 
17
31
  - ❌ Focusing on generic OWASP top 10 (SQLi, IDOR) → ✅ This is the _frontend_ skill. Focus strictly on client-side boundaries, SSR hydration, and DOM.
@@ -1,15 +1,29 @@
1
1
  ---
2
2
  name: game-design-expert
3
3
  description: Game Design, UX, and Flow State mastery. Replaces fragmented legacy skills. Core gameplay loop design, 3Cs (Character, Camera, Controls), input buffering, coyote time, juice (game feel), telemetry tracking, narrative alignment, and audio spatialization integration. Use when crafting player experience, progression arcs, or systemic balance.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 2.0.0
6
- last-updated: 2026-04-02
7
- applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
- routing:
9
- domain: general
10
- tier: basic
4
+ tools: Read, Grep, Glob, Bash, Edit, Write
5
+ version: 3.0.0
6
+ last-updated: 2026-07-30
7
+ skills:
8
+ - game-engineering-expert
9
+ - 12-principles-of-animation
10
+ - sounds-on-the-web
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
11
14
  ---
12
15
 
16
+ # Game Design Expert — Player Experience & Flow Mastery
17
+
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before designing gameplay systems or controller feel, you MUST inspect:
23
+ 1. 3Cs Foundation (Character, Camera, Controls) (Section 25) → Implement input buffering (~150ms) and coyote time (~100ms) before designing enemy AI or progression
24
+ 2. Macro Gameplay Loop Validation (Section 42) → Ensure upgrading systems directly alter action and combat feel to prevent player churn
25
+ 3. Juicing & Hitstop Feel (Section 58) → Incorporate screen shake, hitstop (3 freeze frames), particle explosions, and squash-and-stretch for impact feedback
26
+
13
27
  ## Hallucination Traps (Read First)
14
28
 
15
29
  - ❌ Designing reward systems without testing for compulsion loops -> ✅ Playtesting must verify engagement without addiction patterns
@@ -1,15 +1,29 @@
1
1
  ---
2
2
  name: game-engineering-expert
3
3
  description: Game Engineering and Systems Architecture mastery. Replaces fragmented legacy skills. Entity Component Systems (ECS), Unity (C#) / Godot (GDScript) integration, physics calculations, deterministic engine state, WebGL memory management, multiplayer sync architectures (deterministic lockstep vs traditional authoritative), spatial partitioning, and rendering pipelines.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 2.0.0
6
- last-updated: 2026-04-02
7
- applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
- routing:
9
- domain: general
10
- tier: basic
4
+ tools: Read, Grep, Glob, Bash, Edit, Write
5
+ version: 3.0.0
6
+ last-updated: 2026-07-30
7
+ skills:
8
+ - game-design-expert
9
+ - csharp-developer
10
+ - 60fps-animation
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
11
14
  ---
12
15
 
16
+ # Game Engineering Expert — Performance & State Mastery
17
+
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before engineering game state loops or physics engines, you MUST inspect:
23
+ 1. Clamped DeltaTime Rule (Section 25) → Clamp `deltaTime` (max 0.05s) to prevent physics explosions on frame rate drops
24
+ 2. Garbage Collection & Object Pooling (Section 50) → Pre-allocate and pool game objects; ban `Instantiate()` or dynamic memory allocations in frame update loops
25
+ 3. FixedUpdate vs Update Separation (Section 43) → Put all physics logic in `FixedUpdate()`; use `Update()` strictly for visual interpolation and input collection
26
+
13
27
  ## Hallucination Traps (Read First)
14
28
 
15
29
  - ❌ Using deltaTime without clamping -> ✅ Unclamped deltaTime causes physics explosions on frame spikes; clamp to max 0.05s
@@ -1,13 +1,29 @@
1
1
  ---
2
2
  name: generative-ui-expert
3
3
  description: Generative UI mastery. Vercel AI SDK 3.0+, React Server Components (RSC) + LLMs, streaming UI elements, structured tool calling (Zod schemas), and managing client-side AI state via useChat/useObject.
4
- routing:
5
- domain: general
6
- tier: basic
4
+ tools: Read, Grep, Glob, Bash, Edit, Write
5
+ version: 3.0.0
6
+ last-updated: 2026-07-30
7
+ skills:
8
+ - nextjs-react-expert
9
+ - react-specialist
10
+ - browser-native-ai
11
+ scripts-binding:
12
+ - .agent/scripts/lint_runner.js
13
+ - .agent/scripts/verify_all.js
7
14
  ---
8
15
 
9
16
  # Generative UI Expert (Vercel AI SDK)
10
17
 
18
+ ---
19
+
20
+ ## Mandatory Pre-Flight Context Inspection
21
+
22
+ Before implementing Generative UI streaming pipelines, you MUST inspect:
23
+ 1. Tool Parameter Schemas (Section 87) → Validate all LLM tool parameters with Zod schemas
24
+ 2. RSC Server Action Boundaries (Section 33) → Annotate server actions with `"use server"` and yield Server Components directly from `streamUI`
25
+ 3. Intermediate Skeleton Yielding (Section 80) → Always `yield <SkeletonLoader />` before awaiting async APIs or external LLM tool calls
26
+
11
27
  You are the definitive expert in Generative UI using the Vercel AI SDK and React Server Components (RSC). Your goal is to move AI from spitting out "markdown walls of text" into rendering interactive, stateful, and dynamic UI components natively inside the chat or application stream.
12
28
 
13
29
  ## 1. Core Principles