flyee 0.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (302) hide show
  1. package/LICENSE +21 -0
  2. package/README.md +134 -0
  3. package/bin/install.js +357 -0
  4. package/bridge/bridge.py +1780 -0
  5. package/bridge/local_tracker.py +722 -0
  6. package/core/agents/backend-specialist.md +266 -0
  7. package/core/agents/code-archaeologist.md +106 -0
  8. package/core/agents/database-architect.md +226 -0
  9. package/core/agents/debugger.md +225 -0
  10. package/core/agents/devops-engineer.md +323 -0
  11. package/core/agents/documentation-writer.md +104 -0
  12. package/core/agents/explorer-agent.md +73 -0
  13. package/core/agents/frontend-specialist.md +743 -0
  14. package/core/agents/game-developer.md +162 -0
  15. package/core/agents/mobile-developer.md +377 -0
  16. package/core/agents/orchestrator.md +416 -0
  17. package/core/agents/penetration-tester.md +188 -0
  18. package/core/agents/performance-optimizer.md +187 -0
  19. package/core/agents/product-manager.md +112 -0
  20. package/core/agents/product-owner.md +95 -0
  21. package/core/agents/project-planner.md +470 -0
  22. package/core/agents/qa-automation-engineer.md +103 -0
  23. package/core/agents/security-auditor.md +170 -0
  24. package/core/agents/seo-specialist.md +111 -0
  25. package/core/agents/stitch-designer.md +190 -0
  26. package/core/agents/tdd-reviewer.md +282 -0
  27. package/core/agents/test-engineer.md +158 -0
  28. package/core/scripts/auto_preview.py +148 -0
  29. package/core/scripts/checklist.py +243 -0
  30. package/core/scripts/cost_report.py +149 -0
  31. package/core/scripts/doc-sync-check.py +461 -0
  32. package/core/scripts/parse_user_stories.py +79 -0
  33. package/core/scripts/prepare_notion_updates.py +172 -0
  34. package/core/scripts/print_create_payload.py +18 -0
  35. package/core/scripts/session_manager.py +120 -0
  36. package/core/scripts/task_complete.py +127 -0
  37. package/core/scripts/verify_all.py +327 -0
  38. package/core/skills/analytics-strategy/SKILL.md +128 -0
  39. package/core/skills/api-patterns/SKILL.md +81 -0
  40. package/core/skills/api-patterns/api-style.md +42 -0
  41. package/core/skills/api-patterns/auth.md +24 -0
  42. package/core/skills/api-patterns/documentation.md +26 -0
  43. package/core/skills/api-patterns/graphql.md +41 -0
  44. package/core/skills/api-patterns/rate-limiting.md +31 -0
  45. package/core/skills/api-patterns/response.md +37 -0
  46. package/core/skills/api-patterns/rest.md +40 -0
  47. package/core/skills/api-patterns/scripts/api_validator.py +211 -0
  48. package/core/skills/api-patterns/security-testing.md +122 -0
  49. package/core/skills/api-patterns/trpc.md +41 -0
  50. package/core/skills/api-patterns/versioning.md +22 -0
  51. package/core/skills/app-builder/SKILL.md +75 -0
  52. package/core/skills/app-builder/agent-coordination.md +71 -0
  53. package/core/skills/app-builder/feature-building.md +53 -0
  54. package/core/skills/app-builder/project-detection.md +34 -0
  55. package/core/skills/app-builder/scaffolding.md +118 -0
  56. package/core/skills/app-builder/tech-stack.md +40 -0
  57. package/core/skills/app-builder/templates/SKILL.md +39 -0
  58. package/core/skills/app-builder/templates/astro-static/TEMPLATE.md +76 -0
  59. package/core/skills/app-builder/templates/chrome-extension/TEMPLATE.md +92 -0
  60. package/core/skills/app-builder/templates/cli-tool/TEMPLATE.md +88 -0
  61. package/core/skills/app-builder/templates/electron-desktop/TEMPLATE.md +88 -0
  62. package/core/skills/app-builder/templates/express-api/TEMPLATE.md +83 -0
  63. package/core/skills/app-builder/templates/flutter-app/TEMPLATE.md +90 -0
  64. package/core/skills/app-builder/templates/monorepo-turborepo/TEMPLATE.md +90 -0
  65. package/core/skills/app-builder/templates/nextjs-fullstack/TEMPLATE.md +82 -0
  66. package/core/skills/app-builder/templates/nextjs-saas/TEMPLATE.md +100 -0
  67. package/core/skills/app-builder/templates/nextjs-static/TEMPLATE.md +106 -0
  68. package/core/skills/app-builder/templates/nuxt-app/TEMPLATE.md +101 -0
  69. package/core/skills/app-builder/templates/python-fastapi/TEMPLATE.md +83 -0
  70. package/core/skills/app-builder/templates/react-native-app/TEMPLATE.md +93 -0
  71. package/core/skills/architecture/SKILL.md +55 -0
  72. package/core/skills/architecture/context-discovery.md +43 -0
  73. package/core/skills/architecture/examples.md +94 -0
  74. package/core/skills/architecture/pattern-selection.md +68 -0
  75. package/core/skills/architecture/patterns-reference.md +50 -0
  76. package/core/skills/architecture/trade-off-analysis.md +77 -0
  77. package/core/skills/atomic-design/SKILL.md +282 -0
  78. package/core/skills/atomic-design/references/classification-guide.md +132 -0
  79. package/core/skills/atomic-design/references/quality-checklist.md +60 -0
  80. package/core/skills/atomic-design/references/stacks/stack-blade.md +254 -0
  81. package/core/skills/atomic-design/references/stacks/stack-nextjs.md +272 -0
  82. package/core/skills/atomic-design/references/stacks/stack-react.md +239 -0
  83. package/core/skills/atomic-design/references/stacks/stack-vue.md +224 -0
  84. package/core/skills/bash-linux/SKILL.md +199 -0
  85. package/core/skills/behavioral-modes/SKILL.md +242 -0
  86. package/core/skills/brainstorming/SKILL.md +163 -0
  87. package/core/skills/brainstorming/dynamic-questioning.md +373 -0
  88. package/core/skills/checkpointing-patterns/SKILL.md +163 -0
  89. package/core/skills/clean-code/SKILL.md +201 -0
  90. package/core/skills/code-review-checklist/SKILL.md +109 -0
  91. package/core/skills/code-truth-validation/SKILL.md +149 -0
  92. package/core/skills/component-library-discovery/SKILL.md +154 -0
  93. package/core/skills/content-strategy/SKILL.md +222 -0
  94. package/core/skills/context-budget/SKILL.md +155 -0
  95. package/core/skills/context-gathering-patterns/SKILL.md +278 -0
  96. package/core/skills/cost-tracking/SKILL.md +206 -0
  97. package/core/skills/database-design/SKILL.md +52 -0
  98. package/core/skills/database-design/database-selection.md +43 -0
  99. package/core/skills/database-design/indexing.md +39 -0
  100. package/core/skills/database-design/migrations.md +48 -0
  101. package/core/skills/database-design/optimization.md +36 -0
  102. package/core/skills/database-design/orm-selection.md +30 -0
  103. package/core/skills/database-design/schema-design.md +56 -0
  104. package/core/skills/database-design/scripts/schema_validator.py +172 -0
  105. package/core/skills/deployment-procedures/SKILL.md +295 -0
  106. package/core/skills/design-md/README.md +34 -0
  107. package/core/skills/design-md/SKILL.md +172 -0
  108. package/core/skills/design-md/examples/DESIGN.md +154 -0
  109. package/core/skills/design-system-enforcement/SKILL.md +339 -0
  110. package/core/skills/doc.md +177 -0
  111. package/core/skills/document-registry/SKILL.md +130 -0
  112. package/core/skills/documentation-publishing/SKILL.md +174 -0
  113. package/core/skills/documentation-templates/SKILL.md +194 -0
  114. package/core/skills/enhance-prompt/README.md +34 -0
  115. package/core/skills/enhance-prompt/SKILL.md +204 -0
  116. package/core/skills/enhance-prompt/references/KEYWORDS.md +114 -0
  117. package/core/skills/frontend-design/SKILL.md +430 -0
  118. package/core/skills/frontend-design/animation-guide.md +331 -0
  119. package/core/skills/frontend-design/color-system.md +311 -0
  120. package/core/skills/frontend-design/decision-trees.md +418 -0
  121. package/core/skills/frontend-design/motion-graphics.md +306 -0
  122. package/core/skills/frontend-design/scripts/accessibility_checker.py +183 -0
  123. package/core/skills/frontend-design/scripts/ux_audit.py +722 -0
  124. package/core/skills/frontend-design/typography-system.md +345 -0
  125. package/core/skills/frontend-design/ux-psychology.md +541 -0
  126. package/core/skills/frontend-design/visual-effects.md +383 -0
  127. package/core/skills/game-development/2d-games/SKILL.md +119 -0
  128. package/core/skills/game-development/3d-games/SKILL.md +135 -0
  129. package/core/skills/game-development/SKILL.md +167 -0
  130. package/core/skills/game-development/game-art/SKILL.md +185 -0
  131. package/core/skills/game-development/game-audio/SKILL.md +190 -0
  132. package/core/skills/game-development/game-design/SKILL.md +129 -0
  133. package/core/skills/game-development/mobile-games/SKILL.md +108 -0
  134. package/core/skills/game-development/multiplayer/SKILL.md +132 -0
  135. package/core/skills/game-development/pc-games/SKILL.md +144 -0
  136. package/core/skills/game-development/vr-ar/SKILL.md +123 -0
  137. package/core/skills/game-development/web-games/SKILL.md +150 -0
  138. package/core/skills/geo-fundamentals/SKILL.md +156 -0
  139. package/core/skills/geo-fundamentals/scripts/geo_checker.py +289 -0
  140. package/core/skills/git-workflow/SKILL.md +263 -0
  141. package/core/skills/history-check-patterns/SKILL.md +125 -0
  142. package/core/skills/i18n-localization/SKILL.md +154 -0
  143. package/core/skills/i18n-localization/scripts/i18n_checker.py +241 -0
  144. package/core/skills/integration-completeness/SKILL.md +219 -0
  145. package/core/skills/intelligent-routing/SKILL.md +370 -0
  146. package/core/skills/lint-and-validate/SKILL.md +45 -0
  147. package/core/skills/lint-and-validate/scripts/lint_runner.py +173 -0
  148. package/core/skills/lint-and-validate/scripts/type_coverage.py +173 -0
  149. package/core/skills/local-verification/SKILL.md +195 -0
  150. package/core/skills/mcp-builder/SKILL.md +176 -0
  151. package/core/skills/mobile-design/SKILL.md +394 -0
  152. package/core/skills/mobile-design/decision-trees.md +516 -0
  153. package/core/skills/mobile-design/mobile-backend.md +491 -0
  154. package/core/skills/mobile-design/mobile-color-system.md +420 -0
  155. package/core/skills/mobile-design/mobile-debugging.md +122 -0
  156. package/core/skills/mobile-design/mobile-design-thinking.md +357 -0
  157. package/core/skills/mobile-design/mobile-navigation.md +458 -0
  158. package/core/skills/mobile-design/mobile-performance.md +767 -0
  159. package/core/skills/mobile-design/mobile-testing.md +356 -0
  160. package/core/skills/mobile-design/mobile-typography.md +433 -0
  161. package/core/skills/mobile-design/platform-android.md +666 -0
  162. package/core/skills/mobile-design/platform-ios.md +561 -0
  163. package/core/skills/mobile-design/scripts/mobile_audit.py +670 -0
  164. package/core/skills/mobile-design/touch-psychology.md +537 -0
  165. package/core/skills/nextjs-react-expert/1-async-eliminating-waterfalls.md +312 -0
  166. package/core/skills/nextjs-react-expert/2-bundle-bundle-size-optimization.md +240 -0
  167. package/core/skills/nextjs-react-expert/3-server-server-side-performance.md +490 -0
  168. package/core/skills/nextjs-react-expert/4-client-client-side-data-fetching.md +264 -0
  169. package/core/skills/nextjs-react-expert/5-rerender-re-render-optimization.md +581 -0
  170. package/core/skills/nextjs-react-expert/6-rendering-rendering-performance.md +432 -0
  171. package/core/skills/nextjs-react-expert/7-js-javascript-performance.md +684 -0
  172. package/core/skills/nextjs-react-expert/8-advanced-advanced-patterns.md +150 -0
  173. package/core/skills/nextjs-react-expert/SKILL.md +267 -0
  174. package/core/skills/nextjs-react-expert/scripts/convert_rules.py +222 -0
  175. package/core/skills/nextjs-react-expert/scripts/react_performance_checker.py +252 -0
  176. package/core/skills/nodejs-best-practices/SKILL.md +333 -0
  177. package/core/skills/notion-task-patterns/SKILL.md +2529 -0
  178. package/core/skills/page-specifications/SKILL.md +367 -0
  179. package/core/skills/parallel-agents/SKILL.md +175 -0
  180. package/core/skills/performance-profiling/SKILL.md +143 -0
  181. package/core/skills/performance-profiling/scripts/lighthouse_audit.py +76 -0
  182. package/core/skills/plan-writing/SKILL.md +190 -0
  183. package/core/skills/powershell-windows/SKILL.md +167 -0
  184. package/core/skills/project-foundation/SKILL.md +117 -0
  185. package/core/skills/project-setup/SKILL.md +141 -0
  186. package/core/skills/project-tracking-patterns/SKILL.md +357 -0
  187. package/core/skills/project-type-discovery/SKILL.md +239 -0
  188. package/core/skills/python-patterns/SKILL.md +441 -0
  189. package/core/skills/qa-test-generation/SKILL.md +156 -0
  190. package/core/skills/react-components/README.md +36 -0
  191. package/core/skills/react-components/SKILL.md +47 -0
  192. package/core/skills/react-components/examples/gold-standard-card.tsx +80 -0
  193. package/core/skills/react-components/package-lock.json +231 -0
  194. package/core/skills/react-components/package.json +16 -0
  195. package/core/skills/react-components/resources/architecture-checklist.md +15 -0
  196. package/core/skills/react-components/resources/component-template.tsx +37 -0
  197. package/core/skills/react-components/resources/stitch-api-reference.md +14 -0
  198. package/core/skills/react-components/resources/style-guide.json +27 -0
  199. package/core/skills/react-components/scripts/fetch-stitch.sh +30 -0
  200. package/core/skills/react-components/scripts/validate.js +68 -0
  201. package/core/skills/red-team-tactics/SKILL.md +199 -0
  202. package/core/skills/remotion/README.md +105 -0
  203. package/core/skills/remotion/SKILL.md +393 -0
  204. package/core/skills/remotion/examples/WalkthroughComposition.tsx +78 -0
  205. package/core/skills/remotion/examples/screens.json +56 -0
  206. package/core/skills/remotion/resources/composition-checklist.md +124 -0
  207. package/core/skills/remotion/resources/screen-slide-template.tsx +123 -0
  208. package/core/skills/remotion/scripts/download-stitch-asset.sh +38 -0
  209. package/core/skills/seo-fundamentals/SKILL.md +129 -0
  210. package/core/skills/seo-fundamentals/scripts/seo_checker.py +219 -0
  211. package/core/skills/server-management/SKILL.md +161 -0
  212. package/core/skills/session-resilience/SKILL.md +199 -0
  213. package/core/skills/shadcn-ui/README.md +248 -0
  214. package/core/skills/shadcn-ui/SKILL.md +326 -0
  215. package/core/skills/shadcn-ui/examples/auth-layout.tsx +177 -0
  216. package/core/skills/shadcn-ui/examples/data-table.tsx +313 -0
  217. package/core/skills/shadcn-ui/examples/form-pattern.tsx +177 -0
  218. package/core/skills/shadcn-ui/resources/component-catalog.md +481 -0
  219. package/core/skills/shadcn-ui/resources/customization-guide.md +516 -0
  220. package/core/skills/shadcn-ui/resources/migration-guide.md +463 -0
  221. package/core/skills/shadcn-ui/resources/setup-guide.md +412 -0
  222. package/core/skills/shadcn-ui/scripts/verify-setup.sh +134 -0
  223. package/core/skills/state-machine/SKILL.md +264 -0
  224. package/core/skills/stitch-loop/README.md +54 -0
  225. package/core/skills/stitch-loop/SKILL.md +203 -0
  226. package/core/skills/stitch-loop/examples/SITE.md +73 -0
  227. package/core/skills/stitch-loop/examples/next-prompt.md +25 -0
  228. package/core/skills/stitch-loop/resources/baton-schema.md +61 -0
  229. package/core/skills/stitch-loop/resources/site-template.md +104 -0
  230. package/core/skills/systematic-debugging/SKILL.md +109 -0
  231. package/core/skills/tailwind-patterns/SKILL.md +284 -0
  232. package/core/skills/tdd-validation/SKILL.md +243 -0
  233. package/core/skills/tdd-workflow/SKILL.md +284 -0
  234. package/core/skills/testing-patterns/SKILL.md +196 -0
  235. package/core/skills/testing-patterns/scripts/test_runner.py +219 -0
  236. package/core/skills/ui-ux-discovery/SKILL.md +329 -0
  237. package/core/skills/ui-validation/SKILL.md +190 -0
  238. package/core/skills/ui-validation/scripts/ui_antipattern_check.py +317 -0
  239. package/core/skills/verification-gate/SKILL.md +205 -0
  240. package/core/skills/vulnerability-scanner/SKILL.md +276 -0
  241. package/core/skills/vulnerability-scanner/checklists.md +121 -0
  242. package/core/skills/vulnerability-scanner/scripts/security_scan.py +458 -0
  243. package/core/skills/web-design-guidelines/SKILL.md +57 -0
  244. package/core/skills/webapp-testing/SKILL.md +187 -0
  245. package/core/skills/webapp-testing/scripts/playwright_runner.py +173 -0
  246. package/core/templates/ARCHITECTURE.template.md +407 -0
  247. package/core/templates/project-resources.example.json +71 -0
  248. package/core/workflows/atomic.md +182 -0
  249. package/core/workflows/brainstorm.md +134 -0
  250. package/core/workflows/check-task.md +242 -0
  251. package/core/workflows/copy-collect.md +306 -0
  252. package/core/workflows/create-agent.md +33 -0
  253. package/core/workflows/create-skill.md +39 -0
  254. package/core/workflows/create-workflow.md +33 -0
  255. package/core/workflows/create.md +92 -0
  256. package/core/workflows/debug.md +186 -0
  257. package/core/workflows/demand.md +443 -0
  258. package/core/workflows/deploy.md +260 -0
  259. package/core/workflows/discovery.md +267 -0
  260. package/core/workflows/document.md +272 -0
  261. package/core/workflows/ds-components.md +296 -0
  262. package/core/workflows/ds-init.md +58 -0
  263. package/core/workflows/ds-refactor.md +245 -0
  264. package/core/workflows/ds-references.md +197 -0
  265. package/core/workflows/ds-styleguide.md +237 -0
  266. package/core/workflows/ds-token-diff.md +103 -0
  267. package/core/workflows/ds-tokens.md +317 -0
  268. package/core/workflows/ds-validate.md +309 -0
  269. package/core/workflows/execute.md +483 -0
  270. package/core/workflows/extract-template.md +278 -0
  271. package/core/workflows/fix-failed-tests.md +160 -0
  272. package/core/workflows/init-project.md +386 -0
  273. package/core/workflows/legacy-project.md +849 -0
  274. package/core/workflows/log.md +97 -0
  275. package/core/workflows/new-project.md +610 -0
  276. package/core/workflows/new-project.md.bak +3292 -0
  277. package/core/workflows/new-task.md +404 -0
  278. package/core/workflows/orchestrate.md +237 -0
  279. package/core/workflows/page-build.md +296 -0
  280. package/core/workflows/plan.md +89 -0
  281. package/core/workflows/prd.md +255 -0
  282. package/core/workflows/preview.md +81 -0
  283. package/core/workflows/review-page.md +304 -0
  284. package/core/workflows/status.md +86 -0
  285. package/core/workflows/stitch.md +226 -0
  286. package/core/workflows/task-complete.md +473 -0
  287. package/core/workflows/task-update.md +163 -0
  288. package/core/workflows/tdd.md +344 -0
  289. package/core/workflows/test.md +251 -0
  290. package/core/workflows/ui-ux-pro-max.md +437 -0
  291. package/core/workflows/ux-mobile-optimize.md +262 -0
  292. package/core/workflows/ux-mobile-validate.md +297 -0
  293. package/engine-files/GEMINI.md +69 -0
  294. package/package.json +47 -0
  295. package/runtime-adapters/antigravity.js +26 -0
  296. package/runtime-adapters/claude.js +57 -0
  297. package/runtime-adapters/codex.js +51 -0
  298. package/runtime-adapters/copilot.js +51 -0
  299. package/runtime-adapters/cursor.js +51 -0
  300. package/runtime-adapters/gemini-cli.js +30 -0
  301. package/runtime-adapters/opencode.js +51 -0
  302. package/runtime-adapters/windsurf.js +51 -0
@@ -0,0 +1,404 @@
1
+ ---
2
+ description: Add or update features with mandatory Analysis, Splitting, and Tracker sync (Flyee or Local). Supports dynamic database discovery.
3
+ skills: checkpointing-patterns, history-check-patterns, context-gathering-patterns, project-tracking-patterns, ui-ux-discovery, local-verification, integration-completeness, design-system-enforcement, document-registry
4
+
5
+ ---
6
+
7
+ # /new-task - Structured Improvement Workflow
8
+
9
+ $ARGUMENTS
10
+
11
+ **Flags:**
12
+
13
+ | Flag | Descrição |
14
+ |------|-----------|
15
+ | `--tdd` | Modo **TDD obrigatório** (testes antes do código) |
16
+ | `--resume` | **Retomar** de onde parou |
17
+ | `--backlog` | **Apenas registro**: Cria a task no Flyee e encerra (não inicia implementação) |
18
+ | `--skip-history` | Pular consulta de histórico (não recomendado) |
19
+
20
+ **Status lifecycle da task:**
21
+ ```
22
+ backlog → running → testing → completed
23
+ ```
24
+ - `backlog` — Task registrada, plano em elaboração (iterações)
25
+ - `running` — Plano aprovado, implementação em curso
26
+ - `testing` — Implementação concluída, aguardando validação QA
27
+ - `completed` — QA aprovado, task encerrada via `/task-complete`
28
+
29
+ ---
30
+
31
+ ## 🛑🛑🛑 MANDATORY EXECUTION PROTOCOL (READ FIRST) 🛑🛑🛑
32
+
33
+ > [!CAUTION]
34
+ > **HALT.** Você DEVE completar TODAS as etapas abaixo **ANTES** de escrever qualquer linha de código.
35
+ > Pular qualquer etapa = **VIOLAÇÃO GRAVE**. O workflow inteiro será considerado inválido.
36
+ > **NENHUMA EXCEÇÃO.** Nem urgência, nem simplicidade, nem pedido do usuário justifica pular.
37
+
38
+ ### 📋 CHECKLIST OBRIGATÓRIO (Executar em ordem, mostrar evidência)
39
+
40
+ **O agente DEVE executar cada comando e mostrar o output ao usuário:**
41
+
42
+ ```
43
+ 🛑 /new-task GOVERNANCE GATE
44
+
45
+ [ ] 0. FASE 0 — TASK CRIADA ANTES DO PLANO:
46
+ → Executei `bridge.py --create-task --status backlog`?
47
+ → task_id obtido: ___________
48
+ → task_id gravado no frontmatter do implementation_plan.md?
49
+ → Se falhou: RETRY 1x → Se falhou novamente: INFORMAR usuário e parar
50
+
51
+ [ ] 1. FLYEE DETECTION: Executei `cat flyee.json` e verifiquei se existe?
52
+ → Se não existe: INFORMAR usuário e perguntar se deseja configurar
53
+ → Se existe mas enabled:false: INFORMAR que tracking está desativado
54
+
55
+ [ ] 2. HISTORY CHECK: Consultei tasks anteriores no Flyee relacionadas à demanda?
56
+ → Tasks encontradas: ___ (ou "Nenhuma")
57
+ → Lições aplicáveis: ___ (ou "Nenhuma")
58
+
59
+ [ ] 3. CONTEXT CHECK: Verifiquei docs/INDEX.md e docs/flows/ para contexto?
60
+ → Documentação encontrada: ___ (ou "Nenhuma → perguntar ao usuário")
61
+
62
+ [ ] 4. PERSIST-PLAN ITERATIVO ATIVO:
63
+ → A cada atualização do implementation_plan.md, executei `--persist-plan`?
64
+ → task_id presente no frontmatter do .md? (se não → ERRO, não continuar)
65
+
66
+ ❌ QUALQUER ITEM DESMARCADO → NÃO INICIAR IMPLEMENTAÇÃO
67
+ ✅ TODOS MARCADOS → Prosseguir para código
68
+ ```
69
+
70
+ > [!CAUTION]
71
+ > **ANTI-SKIP RULES:**
72
+ > - ❌ "É uma task simples" → NÃO é motivo para pular. Tasks simples TAMBÉM devem ser rastreadas.
73
+ > - ❌ "O usuário pediu para ir direto" → NÃO é motivo. Informar o usuário que o gate é obrigatório.
74
+ > - ❌ "Já sei o que fazer" → NÃO é motivo. O registro no Flyee serve para rastreabilidade, não para planejamento.
75
+ > - ❌ "Vou registrar depois" → PROIBIDO. A task DEVE ser criada ANTES da implementação.
76
+
77
+ ### ⚡ ORDEM DE EXECUÇÃO OBRIGATÓRIA
78
+
79
+ ```
80
+ 0. bridge.py --create-task --status backlog → Criar task ANTES do plano
81
+ ↳ Gravar task_id no frontmatter do implementation_plan.md
82
+ 1. cat flyee.json → Detectar Flyee
83
+ 2. Flyee API: search tasks relacionadas → History check
84
+ 3. Verificar docs/INDEX.md + docs/flows/ → Context check
85
+ 4. Escrever implementation_plan.md → Planejamento
86
+ ↳ bridge.py --persist-plan <path> --task-id <id> → Persiste v1
87
+ ↳ A cada iteração do plano → --persist-plan novamente (SHA256 dedup)
88
+ 5. Usuário aprova plano:
89
+ ↳ bridge.py --update-task <id> --status running
90
+ ↳ bridge.py --update-task <id> --description "<escopo final aprovado>"
91
+ 6. ════════════════════════════════════════════
92
+ ↓↓↓ SOMENTE APÓS 0-5 COMPLETOS ↓↓↓
93
+ 7. Implementar código
94
+ 8. bridge.py --update-task <id> --status testing → Aguarda QA
95
+ 9. /task-complete → Fechar task
96
+ ```
97
+
98
+ > [!CAUTION]
99
+ > **ANTI-BYPASS:** Se `implementation_plan.md` não tiver `task_id` no frontmatter ao executar `--persist-plan`, o bridge retorna **exit(1)** com mensagem de erro. O agente **DEVE** parar e resolver — não ignorar silenciosamente.
100
+
101
+ > [!CAUTION]
102
+ > **SE O AGENTE CHEGAR AO PASSO 6 SEM TER EXECUTADO 1-4:**
103
+ > O agente DEVE parar IMEDIATAMENTE, voltar, e executar os passos faltantes.
104
+ > Código escrito sem task rastreada = trabalho perdido.
105
+
106
+ ---
107
+
108
+ ## 🎯 PROPÓSITO
109
+
110
+ Workflow para melhorias e correções que exige **Análise Prévia** e **Registro no Tracker** (Flyee ou Local).
111
+ Totalmente dinâmico: adapta-se ao projeto atual buscando o contexto correto.
112
+
113
+ > [!IMPORTANT]
114
+ > **Tracker-aware:** Lê `PROJECT-PROGRESS.md` → `Tracker de Tasks` para determinar
115
+ > se cria tasks via Flyee API ou em `docs/TASKS.md`.
116
+
117
+ ---
118
+
119
+ ## 💾 SISTEMA DE CHECKPOINTING
120
+
121
+ > **Skill:** `project-tracking-patterns`
122
+ >
123
+ > O workflow mantém estado em dois lugares:
124
+ > - Arquivo local: `docs/NEW-TASK-PROGRESS.md`
125
+ > - Tracker remoto: Flyee Task
126
+ >
127
+ > **Retomada:** Ao executar `/new-task --resume`, o agente carrega o arquivo de progresso, busca a task no Flyee e continua da fase pendente.
128
+
129
+ ---
130
+
131
+ ## 🚫 FLUXO: PRE-CHECK → HISTORY → DISCOVER → ANALYSE → TRACK → EXECUTE → VERIFY
132
+
133
+ > [!CAUTION]
134
+ > **REGRA DE OURO:** NUNCA use IDs fixos. Sempre busque o contexto do projeto atual.
135
+ > **Cada transição de fase exige que a fase anterior tenha sido COMPLETADA com evidência.**
136
+
137
+ ---
138
+
139
+ ### 🚨 Fase -2: PRE-START CHECK (Gate de Finalização)
140
+
141
+ > [!CAUTION]
142
+ > **REGRA BLOQUEANTE:** Esta é a PRIMEIRA ação ao iniciar o workflow.
143
+ > Verificar se há tasks "Em andamento" antes de criar/iniciar nova.
144
+
145
+ **Ações OBRIGATÓRIAS (executar e mostrar output):**
146
+
147
+ 1. **Detectar Flyee:**
148
+ ```bash
149
+ cat flyee.json 2>/dev/null || echo "⚠️ flyee.json não encontrado"
150
+ ```
151
+ → Se não existe: **PARAR** e perguntar ao usuário se deseja configurar.
152
+
153
+ 2. **Verificar tasks abertas:**
154
+ ```bash
155
+ python3 .agent/flyee-bridge/bridge.py --search-context "status em andamento"
156
+ ```
157
+ → Se houver tasks em andamento: Perguntar se deseja finalizar primeiro.
158
+ → Se usuário quiser finalizar: Executar `/task-complete` antes de prosseguir.
159
+
160
+ **Gate de Saída Fase -2:**
161
+ ```
162
+ [ ] flyee.json verificado (mostrar output)
163
+ [ ] Tasks em andamento verificadas
164
+ ❌ Se desmarcado → NÃO prosseguir para Fase -1
165
+ ```
166
+
167
+ ---
168
+
169
+ ### 🕵️ Fase -1: HISTORY CHECK (Aprender com o passado)
170
+
171
+ > **Skill:** `history-check-patterns`
172
+ >
173
+ > **Objetivo:** Consultar histórico de tarefas relacionadas à demanda para evitar repetir erros e adotar padrões já definidos.
174
+ > **Ação:** Executar a busca de histórico descrita no skill.
175
+
176
+ **Gate de Saída Fase -1:**
177
+ ```
178
+ [ ] History check executado (mostrar output ou "Nenhum histórico")
179
+ [ ] Lições identificadas e anotadas
180
+ ❌ Se desmarcado → NÃO prosseguir para Fase 0
181
+ ```
182
+
183
+ ---
184
+
185
+ - Atualizar doc na "Documentação Técnica" (se existir)
186
+ - Atualizar guia no "Manual do Usuário" (se existir)
187
+
188
+ ---
189
+
190
+ ### 🧠 Fase 1: ANÁLISE TÉCNICA (Offline/Mental)
191
+
192
+ **Trigger:** Database identificado e validado.
193
+
194
+ **1. Análise de Complexidade:**
195
+ - O pedido toca em múltiplos contextos?
196
+ - Tempo estimado > 2h?
197
+
198
+ **2. Estratégia de Particionamento (Split):**
199
+ - **SIMPLES:** 1 Task.
200
+ - **COMPLEXA:** Múltiplas sub-tasks.
201
+
202
+ **3. Estimativa:**
203
+ - Defina a estimativa para cada task (P/M/G ou Pontos).
204
+
205
+ **Gate de Saída Fase 1:**
206
+ ```
207
+ [ ] Complexidade avaliada
208
+ [ ] Estratégia de split definida
209
+ [ ] Estimativa definida
210
+ ❌ Se desmarcado → NÃO prosseguir para Fase 2
211
+ ```
212
+
213
+ ---
214
+
215
+ ### 🌱 Fase 0: TASK REGISTRATION (Antes do Plano)
216
+
217
+ > [!CAUTION]
218
+ > **BLOQUEADOR ABSOLUTO:** Task DEVE ser criada no Flyee ANTES de escrever qualquer linha do plano.
219
+
220
+ ```bash
221
+ # Criar task em status backlog (intenção registrada, plano ainda não aprovado)
222
+ python3 .agent/flyee-bridge/bridge.py \
223
+ --create-task \
224
+ --name "{nome da demanda}" \
225
+ --type implement_feature \
226
+ --status backlog \
227
+ --description "Intent placeholder — plano em elaboração" \
228
+ --priority normal
229
+ # → Salva o task_id retornado no frontmatter do implementation_plan.md
230
+ ```
231
+
232
+ **Frontmatter obrigatório em `implementation_plan.md`:**
233
+ ```yaml
234
+ ---
235
+ task_id: <uuid retornado acima>
236
+ task_name: <nome>
237
+ flyee_status: backlog
238
+ iteration: 0
239
+ ---
240
+ ```
241
+
242
+ > [!IMPORTANT]
243
+ > **STOP GATE (`--backlog` flag):** Se `--backlog` foi utilizado, **ENCERRA AQUI**. Informe o link da task ao usuário. Task permanece em `backlog`.
244
+
245
+ **Gate de Saída Fase 0:**
246
+ ```
247
+ [ ] Task criada com --status backlog (ID obtido)
248
+ [ ] task_id gravado no frontmatter do implementation_plan.md
249
+ [ ] Se --backlog: encerrou aqui
250
+ ❌ task_id ausente → NÃO escrever plano
251
+ ```
252
+
253
+ ---
254
+
255
+ ### 📝 Fase 2: PLANNING + PERSIST ITERATIVO
256
+
257
+ > [!CAUTION]
258
+ > **REGRA:** `--persist-plan` roda a **cada iteração** do plano — não só na aprovação.
259
+ > SHA256 dedup garante que versões idênticas não geram duplicatas.
260
+
261
+ ```bash
262
+ # A cada atualização do implementation_plan.md:
263
+ python3 .agent/flyee-bridge/bridge.py \
264
+ --persist-plan "implementation_plan.md" \
265
+ --task-id <id do frontmatter>
266
+ # → bridge lê task_id do frontmatter automaticamente se não informado via flag
267
+ # → se task_id AUSENTE no frontmatter → exit(1) com erro explícito
268
+ # → se conteúdo idêntico ao anterior (mesmo SHA256) → skipped (não cria nova versão)
269
+ # → se conteúdo diferente → cria nova versão, incrementa iteration no frontmatter
270
+
271
+ # Ao APROVAR o plano (usuário confirma):
272
+ python3 .agent/flyee-bridge/bridge.py --update-task <id> --status running
273
+ python3 .agent/flyee-bridge/bridge.py --update-task <id> --description "<escopo real aprovado>"
274
+
275
+ # Ao ABANDONAR (usuário rejeita definitivamente):
276
+ # Task permanece em backlog — registro de intenção explorada. Usuário arquiva manualmente.
277
+ ```
278
+
279
+ **🧩 UI Component Classification Gate (se plano contém componentes UI):**
280
+
281
+ > [!CAUTION]
282
+ > **ANTES de aprovar o plano**, o agente DEVE classificar CADA componente UI listado como `[NEW]`.
283
+ > Skill de referência: `design-system-enforcement` § Component Classification.
284
+ > Skill complementar: `plan-writing` § Principle 6.
285
+
286
+ Para cada `[NEW]` componente UI no plano, preencher:
287
+
288
+ ```markdown
289
+ ⚠️ UI COMPONENT CLASSIFICATION — Plano: {task_name}
290
+
291
+ | Componente | Conceito Visual Genérico? | Reutilizável em 2+ features? | Destino |
292
+ |------------|--------------------------|------------------------------|---------|
293
+ | {nome} | Sim/Não | Sim/Não | components/ui/ OU features/{x}/components/ |
294
+
295
+ [ ] Primitivos genéricos extraídos para components/ui/ (se aplicável)
296
+ [ ] Feature components consomem os primitivos genéricos (não recriam o visual)
297
+ ❌ Componente genérico dentro de features/ → CORRIGIR PLANO antes de aprovar
298
+ ```
299
+
300
+ > **Anti-pattern:** Plano aprovado com `[NEW] features/progress/components/SprintTimeline.tsx`
301
+ > contendo sua própria `.module.css` que constrói uma timeline visual do zero.
302
+ > O conceito "Timeline" é genérico e deveria estar em `components/ui/Timeline/`.
303
+
304
+ **Gate de Saída Fase 2:**
305
+ ```
306
+ [ ] Plano escrito com task_id no frontmatter
307
+ [ ] --persist-plan executado ao menos 1x (versão v1 criada no Flyee)
308
+ [ ] UI Component Classification preenchido (se plano tem componentes UI)
309
+ [ ] Plano aprovado → --update-task --status running executado
310
+ ❌ task_id ausente → PARAR, executar Fase 0 primeiro
311
+ ❌ Componente genérico preso em features/ → CORRIGIR PLANO
312
+ ```
313
+
314
+ ---
315
+
316
+ ### 💻 Fase 3: EXECUTION (Code)
317
+
318
+ > **Skills ativas:** `tdd-workflow`, `design-system-enforcement`, `ui-validation`
319
+
320
+ > [!CAUTION]
321
+ > **🛑 CHECKPOINT:** Verifique que as Fases -2 a 2 foram CONCLUÍDAS.
322
+ > É terminantemente proibido codar sem uma Task ID do Flyee em mãos.
323
+
324
+ **Ação:** Implementar as mudanças delegando responsabilidades aos skills especialistas:
325
+
326
+ | Sub-fase | Skill | O que |
327
+ |----------|-------|-------|
328
+ | 🔴 **3.0 Context Gather** | `context-gathering-patterns` | (Opcional) Re-ler requisitos detalhados listados na Fase 0 |
329
+ | **3.1 Lógica/Backend** | `tdd-workflow` | Implementar TDD: RED → GREEN → REFACTOR. Seguir regras Anti-Mock. |
330
+ | **3.2 UI Components** | `design-system-enforcement` | Se houver UI, extrair tokens do `docs/design/DESIGN-SYSTEM.md` e garantir Premium Styling e Responsividade. |
331
+ | **3.3 UI Check** | `ui-validation` | Se alterou UI, rodar validação automatizada de antipatterns Visuais. |
332
+
333
+ **Gate de Saída Fase 3:**
334
+ ```
335
+ [ ] Lógica implementada (Testada se --tdd)
336
+ [ ] UI aderente ao Design System (se aplicável)
337
+ ❌ Se pendente → NÃO prosseguir
338
+ ```
339
+
340
+ ---
341
+
342
+ ### ✅ Fase 4: VERIFICATION & COMPLETION (Workflow Delegation)
343
+
344
+ > **Workflow:** `/task-complete`
345
+ > **Skill:** `project-tracking-patterns`
346
+
347
+ **Ação Final:**
348
+
349
+ 1. **Document Refresh:** Busque documentações antigas impactadas e atualize (local e no Flyee).
350
+ 2. **Coverage:** Se `--tdd`, garanta mínimo de 80% coverage localmente.
351
+ 3. **Completion:** Execute `/task-complete`. ESTA É A ÚNICA FORMA AUTORIZADA DE FECHAR TASKS.
352
+
353
+ > [!CAUTION]
354
+ > 🚫 **ANTI-PATTERN PROIBIDO:** `API-patch-page` solto para fechar a Task sem comentários ou detalhes.
355
+ > ✅ **OBRIGATÓRIO:** Workflow `/task-complete` fará os 8 steps de encerramento, incluindo o Log de Execução e o tempo gasto.
356
+
357
+ **Gate Final:**
358
+ ```
359
+ [ ] `/task-complete` excutado
360
+ [ ] Documentação técnica ou guias atualizados
361
+ ```
362
+
363
+ ### ⚠️ Checklist de Finalização (OBRIGATÓRIO)
364
+
365
+ **Antes de ENCERRAR a conversa ou resposta, o agente DEVE verificar:**
366
+
367
+ - [ ] **Fase 2 executada?** Task criada no Flyee com ID registrado?
368
+ - [ ] **Fase 3 concluída?** Todas as alterações implementadas?
369
+ - [ ] **Doc Refresh executado?** Docs impactados verificados e atualizados (local + Flyee)?
370
+ - [ ] **Fase 4 executada?**
371
+ - [ ] Workflow `/task-complete` invocado para finalizar a task no sistema?
372
+
373
+ ### 🔄 Se a Execução for Longa/Interrompida
374
+
375
+ Se o agente precisar pausar ou a conversa for longa:
376
+
377
+ 1. **ANTES de parar:** Atualizar Tracker com progresso parcial
378
+ 2. **Informar usuário:** "Task {ID} em progresso - X de Y itens concluídos"
379
+ 3. **Ao retomar:** Verificar status atual no Flyee antes de continuar
380
+
381
+ ### ❌ O Que NUNCA Fazer
382
+
383
+ 1. ❌ **Encerrar conversa** sem atualizar tracker
384
+ 2. ❌ **Marcar como Concluído** sem verificar se TODOS os itens foram resolvidos
385
+ 3. ❌ **Esquecer de registrar** a task inicialmente (Fase 2)
386
+ 4. ❌ **Pular o resumo final** com descrição das alterações
387
+
388
+ ### ✅ Verificação de Conclusão Correta
389
+
390
+ Quando o usuário perguntar "verificar task" ou "checar Flyee":
391
+
392
+ 1. **Buscar task:** `API-post-search` com o nome/ID
393
+ 2. **Ler status atual:** Verificar Status e comentários
394
+ 3. **Comparar com trabalho feito:**
395
+ - Listar arquivos modificados na sessão
396
+ - Verificar se correspondem ao escopo da task
397
+ 4. **Se incompleto:** Perguntar ao usuário antes de marcar como Concluído
398
+ ```
399
+ ⚠️ A task "{nome}" tem os seguintes itens pendentes:
400
+ - [ ] {item 1}
401
+ - [ ] {item 2}
402
+
403
+ Deseja marcar como Concluído mesmo assim?
404
+ ```
@@ -0,0 +1,237 @@
1
+ ---
2
+ description: Coordinate multiple agents for complex tasks. Use for multi-perspective analysis, comprehensive reviews, or tasks requiring different domain expertise.
3
+ ---
4
+
5
+ # Multi-Agent Orchestration
6
+
7
+ You are now in **ORCHESTRATION MODE**. Your task: coordinate specialized agents to solve this complex problem.
8
+
9
+ ## Task to Orchestrate
10
+ $ARGUMENTS
11
+
12
+ ---
13
+
14
+ ## 🔴 CRITICAL: Minimum Agent Requirement
15
+
16
+ > ⚠️ **ORCHESTRATION = MINIMUM 3 DIFFERENT AGENTS**
17
+ >
18
+ > If you use fewer than 3 agents, you are NOT orchestrating - you're just delegating.
19
+ >
20
+ > **Validation before completion:**
21
+ > - Count invoked agents
22
+ > - If `agent_count < 3` → STOP and invoke more agents
23
+ > - Single agent = FAILURE of orchestration
24
+
25
+ ### Agent Selection Matrix
26
+
27
+ | Task Type | REQUIRED Agents (minimum) |
28
+ |-----------|---------------------------|
29
+ | **Web App** | frontend-specialist, backend-specialist, test-engineer |
30
+ | **API** | backend-specialist, security-auditor, test-engineer |
31
+ | **UI/Design** | frontend-specialist, seo-specialist, performance-optimizer |
32
+ | **Database** | database-architect, backend-specialist, security-auditor |
33
+ | **Full Stack** | project-planner, frontend-specialist, backend-specialist, devops-engineer |
34
+ | **Debug** | debugger, explorer-agent, test-engineer |
35
+ | **Security** | security-auditor, penetration-tester, devops-engineer |
36
+
37
+ ---
38
+
39
+ ## Pre-Flight: Mode Check
40
+
41
+ | Current Mode | Task Type | Action |
42
+ |--------------|-----------|--------|
43
+ | **plan** | Any | ✅ Proceed with planning-first approach |
44
+ | **edit** | Simple execution | ✅ Proceed directly |
45
+ | **edit** | Complex/multi-file | ⚠️ Ask: "This task requires planning. Switch to plan mode?" |
46
+ | **ask** | Any | ⚠️ Ask: "Ready to orchestrate. Switch to edit or plan mode?" |
47
+
48
+ ---
49
+
50
+ ## 🔴 STRICT 2-PHASE ORCHESTRATION
51
+
52
+ ### PHASE 1: PLANNING (Sequential - NO parallel agents)
53
+
54
+ | Step | Agent | Action |
55
+ |------|-------|--------|
56
+ | 1 | `project-planner` | Create docs/PLAN.md |
57
+ | 2 | (optional) `explorer-agent` | Codebase discovery if needed |
58
+
59
+ > 🔴 **NO OTHER AGENTS during planning!** Only project-planner and explorer-agent.
60
+
61
+ ### ⏸️ CHECKPOINT: User Approval
62
+
63
+ ```
64
+ After PLAN.md is complete, ASK:
65
+
66
+ "✅ Plan oluşturuldu: docs/PLAN.md
67
+
68
+ Onaylıyor musunuz? (Y/N)
69
+ - Y: Implementation başlatılır
70
+ - N: Planı düzeltirim"
71
+ ```
72
+
73
+ > 🔴 **DO NOT proceed to Phase 2 without explicit user approval!**
74
+
75
+ ### PHASE 2: IMPLEMENTATION (Parallel agents after approval)
76
+
77
+ | Parallel Group | Agents |
78
+ |----------------|--------|
79
+ | Foundation | `database-architect`, `security-auditor` |
80
+ | Core | `backend-specialist`, `frontend-specialist` |
81
+ | Polish | `test-engineer`, `devops-engineer` |
82
+
83
+ > ✅ After user approval, invoke multiple agents in PARALLEL.
84
+
85
+ ## Available Agents (17 total)
86
+
87
+ | Agent | Domain | Use When |
88
+ |-------|--------|----------|
89
+ | `project-planner` | Planning | Task breakdown, PLAN.md |
90
+ | `explorer-agent` | Discovery | Codebase mapping |
91
+ | `frontend-specialist` | UI/UX | React, Vue, CSS, HTML |
92
+ | `backend-specialist` | Server | API, Node.js, Python |
93
+ | `database-architect` | Data | SQL, NoSQL, Schema |
94
+ | `security-auditor` | Security | Vulnerabilities, Auth |
95
+ | `penetration-tester` | Security | Active testing |
96
+ | `test-engineer` | Testing | Unit, E2E, Coverage |
97
+ | `devops-engineer` | Ops | CI/CD, Docker, Deploy |
98
+ | `mobile-developer` | Mobile | React Native, Flutter |
99
+ | `performance-optimizer` | Speed | Lighthouse, Profiling |
100
+ | `seo-specialist` | SEO | Meta, Schema, Rankings |
101
+ | `documentation-writer` | Docs | README, API docs |
102
+ | `debugger` | Debug | Error analysis |
103
+ | `game-developer` | Games | Unity, Godot |
104
+ | `orchestrator` | Meta | Coordination |
105
+
106
+ ---
107
+
108
+ ## Orchestration Protocol
109
+
110
+ ### Step 1: Analyze Task Domains
111
+ Identify ALL domains this task touches:
112
+ ```
113
+ □ Security → security-auditor, penetration-tester
114
+ □ Backend/API → backend-specialist
115
+ □ Frontend/UI → frontend-specialist
116
+ □ Database → database-architect
117
+ □ Testing → test-engineer
118
+ □ DevOps → devops-engineer
119
+ □ Mobile → mobile-developer
120
+ □ Performance → performance-optimizer
121
+ □ SEO → seo-specialist
122
+ □ Planning → project-planner
123
+ ```
124
+
125
+ ### Step 2: Phase Detection
126
+
127
+ | If Plan Exists | Action |
128
+ |----------------|--------|
129
+ | NO `docs/PLAN.md` | → Go to PHASE 1 (planning only) |
130
+ | YES `docs/PLAN.md` + user approved | → Go to PHASE 2 (implementation) |
131
+
132
+ ### Step 3: Execute Based on Phase
133
+
134
+ **PHASE 1 (Planning):**
135
+ ```
136
+ Use the project-planner agent to create PLAN.md
137
+ → STOP after plan is created
138
+ → ASK user for approval
139
+ ```
140
+
141
+ **PHASE 2 (Implementation - after approval):**
142
+ ```
143
+ Invoke agents in PARALLEL:
144
+ Use the frontend-specialist agent to [task]
145
+ Use the backend-specialist agent to [task]
146
+ Use the test-engineer agent to [task]
147
+ ```
148
+
149
+ **🔴 CRITICAL: Context Passing (MANDATORY)**
150
+
151
+ When invoking ANY subagent, you MUST include:
152
+
153
+ 1. **Original User Request:** Full text of what user asked
154
+ 2. **Decisions Made:** All user answers to Socratic questions
155
+ 3. **Previous Agent Work:** Summary of what previous agents did
156
+ 4. **Current Plan State:** If plan files exist in workspace, include them
157
+
158
+ **Example with FULL context:**
159
+ ```
160
+ Use the project-planner agent to create PLAN.md:
161
+
162
+ **CONTEXT:**
163
+ - User Request: "Öğrenciler için sosyal platform, mock data ile"
164
+ - Decisions: Tech=Vue 3, Layout=Grid Widget, Auth=Mock, Design=Genç Dinamik
165
+ - Previous Work: Orchestrator asked 6 questions, user chose all options
166
+ - Current Plan: playful-roaming-dream.md exists in workspace with initial structure
167
+
168
+ **TASK:** Create detailed PLAN.md based on ABOVE decisions. Do NOT infer from folder name.
169
+ ```
170
+
171
+ > ⚠️ **VIOLATION:** Invoking subagent without full context = subagent will make wrong assumptions!
172
+
173
+
174
+ ### Step 4: Verification (MANDATORY)
175
+ The LAST agent must run appropriate verification scripts:
176
+ ```bash
177
+ python .agent/skills/vulnerability-scanner/scripts/security_scan.py .
178
+ python .agent/skills/lint-and-validate/scripts/lint_runner.py .
179
+ ```
180
+
181
+ ### Step 5: Synthesize Results
182
+ Combine all agent outputs into unified report.
183
+
184
+ ---
185
+
186
+ ## Output Format
187
+
188
+ ```markdown
189
+ ## 🎼 Orchestration Report
190
+
191
+ ### Task
192
+ [Original task summary]
193
+
194
+ ### Mode
195
+ [Current Antigravity Agent mode: plan/edit/ask]
196
+
197
+ ### Agents Invoked (MINIMUM 3)
198
+ | # | Agent | Focus Area | Status |
199
+ |---|-------|------------|--------|
200
+ | 1 | project-planner | Task breakdown | ✅ |
201
+ | 2 | frontend-specialist | UI implementation | ✅ |
202
+ | 3 | test-engineer | Verification scripts | ✅ |
203
+
204
+ ### Verification Scripts Executed
205
+ - [x] security_scan.py → Pass/Fail
206
+ - [x] lint_runner.py → Pass/Fail
207
+
208
+ ### Key Findings
209
+ 1. **[Agent 1]**: Finding
210
+ 2. **[Agent 2]**: Finding
211
+ 3. **[Agent 3]**: Finding
212
+
213
+ ### Deliverables
214
+ - [ ] PLAN.md created
215
+ - [ ] Code implemented
216
+ - [ ] Tests passing
217
+ - [ ] Scripts verified
218
+
219
+ ### Summary
220
+ [One paragraph synthesis of all agent work]
221
+ ```
222
+
223
+ ---
224
+
225
+ ## 🔴 EXIT GATE
226
+
227
+ Before completing orchestration, verify:
228
+
229
+ 1. ✅ **Agent Count:** `invoked_agents >= 3`
230
+ 2. ✅ **Scripts Executed:** At least `security_scan.py` ran
231
+ 3. ✅ **Report Generated:** Orchestration Report with all agents listed
232
+
233
+ > **If any check fails → DO NOT mark orchestration complete. Invoke more agents or run scripts.**
234
+
235
+ ---
236
+
237
+ **Begin orchestration now. Select 3+ agents, execute sequentially, run verification scripts, synthesize results.**