tribunal-kit 4.5.1 → 4.6.0

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 (211) hide show
  1. package/.agent/.shared/ui-ux-pro-max/README.md +4 -4
  2. package/.agent/ARCHITECTURE.md +279 -277
  3. package/.agent/GEMINI.md +127 -121
  4. package/.agent/agents/accessibility-reviewer.md +187 -187
  5. package/.agent/agents/ai-code-reviewer.md +199 -199
  6. package/.agent/agents/api-architect.md +71 -66
  7. package/.agent/agents/backend-specialist.md +219 -215
  8. package/.agent/agents/cloud-engineer.md +98 -0
  9. package/.agent/agents/code-archaeologist.md +168 -161
  10. package/.agent/agents/database-architect.md +184 -184
  11. package/.agent/agents/db-latency-auditor.md +213 -216
  12. package/.agent/agents/debugger.md +198 -191
  13. package/.agent/agents/dependency-reviewer.md +106 -103
  14. package/.agent/agents/devops-engineer.md +218 -218
  15. package/.agent/agents/documentation-writer.md +209 -201
  16. package/.agent/agents/explorer-agent.md +167 -160
  17. package/.agent/agents/frontend-reviewer.md +162 -160
  18. package/.agent/agents/frontend-specialist.md +257 -248
  19. package/.agent/agents/game-developer.md +48 -48
  20. package/.agent/agents/logic-reviewer.md +118 -116
  21. package/.agent/agents/mobile-developer.md +197 -200
  22. package/.agent/agents/mobile-reviewer.md +159 -162
  23. package/.agent/agents/orchestrator.md +187 -181
  24. package/.agent/agents/penetration-tester.md +160 -157
  25. package/.agent/agents/performance-optimizer.md +183 -183
  26. package/.agent/agents/performance-reviewer.md +178 -178
  27. package/.agent/agents/precedence-reviewer.md +251 -250
  28. package/.agent/agents/product-manager.md +149 -142
  29. package/.agent/agents/product-owner.md +81 -80
  30. package/.agent/agents/project-planner.md +152 -142
  31. package/.agent/agents/qa-automation-engineer.md +216 -225
  32. package/.agent/agents/resilience-reviewer.md +88 -88
  33. package/.agent/agents/schema-reviewer.md +67 -67
  34. package/.agent/agents/security-auditor.md +180 -174
  35. package/.agent/agents/seo-specialist.md +188 -193
  36. package/.agent/agents/sql-reviewer.md +159 -161
  37. package/.agent/agents/supervisor-agent.md +173 -184
  38. package/.agent/agents/swarm-worker-contracts.md +170 -166
  39. package/.agent/agents/swarm-worker-registry.md +92 -92
  40. package/.agent/agents/system-architect.md +85 -0
  41. package/.agent/agents/test-coverage-reviewer.md +158 -160
  42. package/.agent/agents/test-engineer.md +118 -118
  43. package/.agent/agents/throughput-optimizer.md +291 -299
  44. package/.agent/agents/type-safety-reviewer.md +182 -175
  45. package/.agent/agents/ui-ux-auditor.md +300 -292
  46. package/.agent/agents/vitals-reviewer.md +223 -223
  47. package/.agent/mcp_config.json +37 -40
  48. package/.agent/patterns/generator.md +11 -9
  49. package/.agent/patterns/inversion.md +14 -12
  50. package/.agent/patterns/pipeline.md +11 -9
  51. package/.agent/patterns/reviewer.md +15 -13
  52. package/.agent/patterns/tool-wrapper.md +11 -9
  53. package/.agent/routing_index.json +654 -0
  54. package/.agent/rules/GEMINI.md +358 -352
  55. package/.agent/scripts/compile_router.py +112 -0
  56. package/.agent/scripts/migrate_skills_frontmatter.py +64 -0
  57. package/.agent/scripts/strengthen_skills.js +1 -1
  58. package/.agent/skills/advanced-rag-pipelines/SKILL.md +56 -0
  59. package/.agent/skills/agent-organizer/SKILL.md +156 -150
  60. package/.agent/skills/agentic-patterns/SKILL.md +313 -315
  61. package/.agent/skills/ai-prompt-injection-defense/SKILL.md +190 -184
  62. package/.agent/skills/api-patterns/SKILL.md +253 -247
  63. package/.agent/skills/api-security-auditor/SKILL.md +195 -193
  64. package/.agent/skills/app-builder/SKILL.md +573 -572
  65. package/.agent/skills/app-builder/templates/SKILL.md +108 -115
  66. package/.agent/skills/app-builder/templates/astro-static/TEMPLATE.md +76 -76
  67. package/.agent/skills/app-builder/templates/chrome-extension/TEMPLATE.md +92 -92
  68. package/.agent/skills/app-builder/templates/cli-tool/TEMPLATE.md +88 -88
  69. package/.agent/skills/app-builder/templates/electron-desktop/TEMPLATE.md +88 -88
  70. package/.agent/skills/app-builder/templates/express-api/TEMPLATE.md +83 -83
  71. package/.agent/skills/app-builder/templates/flutter-app/TEMPLATE.md +90 -90
  72. package/.agent/skills/app-builder/templates/monorepo-turborepo/TEMPLATE.md +90 -90
  73. package/.agent/skills/app-builder/templates/nextjs-fullstack/TEMPLATE.md +126 -122
  74. package/.agent/skills/app-builder/templates/nextjs-saas/TEMPLATE.md +127 -122
  75. package/.agent/skills/app-builder/templates/nextjs-static/TEMPLATE.md +172 -169
  76. package/.agent/skills/app-builder/templates/nuxt-app/TEMPLATE.md +139 -134
  77. package/.agent/skills/app-builder/templates/python-fastapi/TEMPLATE.md +83 -83
  78. package/.agent/skills/app-builder/templates/react-native-app/TEMPLATE.md +122 -119
  79. package/.agent/skills/appflow-wireframe/SKILL.md +146 -145
  80. package/.agent/skills/architecture/SKILL.md +226 -219
  81. package/.agent/skills/authentication-best-practices/SKILL.md +197 -189
  82. package/.agent/skills/backend-security-expert/SKILL.md +16 -2
  83. package/.agent/skills/bash-linux/SKILL.md +179 -179
  84. package/.agent/skills/behavioral-modes/SKILL.md +239 -223
  85. package/.agent/skills/brainstorming/SKILL.md +498 -486
  86. package/.agent/skills/browser-native-ai/SKILL.md +57 -4
  87. package/.agent/skills/building-native-ui/SKILL.md +202 -202
  88. package/.agent/skills/cicd-pro/SKILL.md +442 -0
  89. package/.agent/skills/clean-code/SKILL.md +400 -381
  90. package/.agent/skills/cloud-architect/SKILL.md +439 -0
  91. package/.agent/skills/code-review-checklist/SKILL.md +203 -194
  92. package/.agent/skills/config-validator/SKILL.md +165 -165
  93. package/.agent/skills/containerization-pro/SKILL.md +452 -0
  94. package/.agent/skills/csharp-developer/SKILL.md +518 -518
  95. package/.agent/skills/data-validation-schemas/SKILL.md +333 -328
  96. package/.agent/skills/database-design/SKILL.md +247 -240
  97. package/.agent/skills/deployment-procedures/SKILL.md +172 -169
  98. package/.agent/skills/devops-engineer/SKILL.md +345 -345
  99. package/.agent/skills/devops-incident-responder/SKILL.md +143 -137
  100. package/.agent/skills/doc.md +209 -177
  101. package/.agent/skills/documentation-templates/SKILL.md +291 -279
  102. package/.agent/skills/edge-computing/SKILL.md +183 -181
  103. package/.agent/skills/error-resilience/SKILL.md +411 -428
  104. package/.agent/skills/extract-design-system/SKILL.md +160 -158
  105. package/.agent/skills/framer-motion-expert/SKILL.md +253 -244
  106. package/.agent/skills/frontend-design/SKILL.md +208 -201
  107. package/.agent/skills/frontend-security-expert/SKILL.md +16 -3
  108. package/.agent/skills/game-design-expert/SKILL.md +132 -129
  109. package/.agent/skills/game-engineering-expert/SKILL.md +148 -146
  110. package/.agent/skills/generative-ui-expert/SKILL.md +57 -1
  111. package/.agent/skills/geo-fundamentals/SKILL.md +148 -147
  112. package/.agent/skills/git-pro/SKILL.md +435 -0
  113. package/.agent/skills/github-operations/SKILL.md +335 -329
  114. package/.agent/skills/gsap-core/SKILL.md +319 -308
  115. package/.agent/skills/gsap-frameworks/SKILL.md +213 -207
  116. package/.agent/skills/gsap-performance/SKILL.md +139 -133
  117. package/.agent/skills/gsap-plugins/SKILL.md +486 -480
  118. package/.agent/skills/gsap-react/SKILL.md +202 -189
  119. package/.agent/skills/gsap-scrolltrigger/SKILL.md +357 -350
  120. package/.agent/skills/gsap-timeline/SKILL.md +165 -161
  121. package/.agent/skills/gsap-utils/SKILL.md +344 -338
  122. package/.agent/skills/harness-protocol/SKILL.md +48 -0
  123. package/.agent/skills/i18n-localization/SKILL.md +174 -163
  124. package/.agent/skills/intelligent-routing/SKILL.md +202 -246
  125. package/.agent/skills/knowledge-graph/SKILL.md +60 -52
  126. package/.agent/skills/lint-and-validate/SKILL.md +261 -261
  127. package/.agent/skills/llm-engineering/SKILL.md +400 -394
  128. package/.agent/skills/local-first/SKILL.md +178 -178
  129. package/.agent/skills/mcp-builder/SKILL.md +143 -142
  130. package/.agent/skills/mobile-design/SKILL.md +272 -263
  131. package/.agent/skills/monorepo-management/SKILL.md +335 -334
  132. package/.agent/skills/motion-engineering/SKILL.md +266 -234
  133. package/.agent/skills/nextjs-react-expert/SKILL.md +236 -234
  134. package/.agent/skills/nodejs-best-practices/SKILL.md +547 -548
  135. package/.agent/skills/observability/SKILL.md +343 -343
  136. package/.agent/skills/parallel-agents/SKILL.md +143 -146
  137. package/.agent/skills/performance-profiling/SKILL.md +259 -267
  138. package/.agent/skills/plan-writing/SKILL.md +150 -142
  139. package/.agent/skills/platform-engineer/SKILL.md +148 -147
  140. package/.agent/skills/playwright-best-practices/SKILL.md +188 -187
  141. package/.agent/skills/powershell-windows/SKILL.md +162 -162
  142. package/.agent/skills/project-idioms/SKILL.md +137 -137
  143. package/.agent/skills/python-patterns/SKILL.md +260 -259
  144. package/.agent/skills/python-pro/SKILL.md +324 -323
  145. package/.agent/skills/react-specialist/SKILL.md +305 -277
  146. package/.agent/skills/readme-builder/SKILL.md +310 -300
  147. package/.agent/skills/realtime-patterns/SKILL.md +323 -319
  148. package/.agent/skills/red-team-tactics/SKILL.md +231 -218
  149. package/.agent/skills/rust-pro/SKILL.md +671 -673
  150. package/.agent/skills/seo-fundamentals/SKILL.md +179 -179
  151. package/.agent/skills/server-management/SKILL.md +218 -214
  152. package/.agent/skills/shadcn-ui-expert/SKILL.md +231 -231
  153. package/.agent/skills/skill-creator/SKILL.md +87 -86
  154. package/.agent/skills/sql-pro/SKILL.md +629 -629
  155. package/.agent/skills/supabase-postgres-best-practices/SKILL.md +97 -97
  156. package/.agent/skills/swiftui-expert/SKILL.md +204 -201
  157. package/.agent/skills/system-design-pro/SKILL.md +345 -0
  158. package/.agent/skills/systematic-debugging/SKILL.md +153 -142
  159. package/.agent/skills/tailwind-patterns/SKILL.md +610 -566
  160. package/.agent/skills/tdd-workflow/SKILL.md +169 -161
  161. package/.agent/skills/test-result-analyzer/SKILL.md +313 -309
  162. package/.agent/skills/testing-patterns/SKILL.md +566 -579
  163. package/.agent/skills/trend-researcher/SKILL.md +243 -237
  164. package/.agent/skills/typescript-advanced/SKILL.md +336 -335
  165. package/.agent/skills/ui-ux-pro-max/SKILL.md +590 -562
  166. package/.agent/skills/ui-ux-researcher/SKILL.md +244 -244
  167. package/.agent/skills/vue-expert/SKILL.md +294 -275
  168. package/.agent/skills/vulnerability-scanner/SKILL.md +416 -404
  169. package/.agent/skills/web-accessibility-auditor/SKILL.md +219 -218
  170. package/.agent/skills/web-design-guidelines/SKILL.md +192 -186
  171. package/.agent/skills/webapp-testing/SKILL.md +167 -169
  172. package/.agent/skills/webgpu-performance/SKILL.md +56 -2
  173. package/.agent/skills/whimsy-injector/SKILL.md +346 -325
  174. package/.agent/skills/workflow-optimizer/SKILL.md +231 -229
  175. package/.agent/workflows/acf.md +141 -0
  176. package/.agent/workflows/api-tester.md +176 -151
  177. package/.agent/workflows/audit.md +150 -127
  178. package/.agent/workflows/brainstorm.md +134 -110
  179. package/.agent/workflows/changelog.md +140 -112
  180. package/.agent/workflows/create.md +168 -124
  181. package/.agent/workflows/debug.md +190 -165
  182. package/.agent/workflows/deploy.md +201 -180
  183. package/.agent/workflows/enhance.md +154 -128
  184. package/.agent/workflows/fix.md +136 -114
  185. package/.agent/workflows/generate.md +198 -183
  186. package/.agent/workflows/marathon.md +37 -11
  187. package/.agent/workflows/migrate.md +184 -160
  188. package/.agent/workflows/orchestrate.md +192 -168
  189. package/.agent/workflows/performance-benchmarker.md +135 -114
  190. package/.agent/workflows/plan.md +196 -173
  191. package/.agent/workflows/preview.md +103 -80
  192. package/.agent/workflows/refactor.md +192 -161
  193. package/.agent/workflows/review-ai.md +125 -101
  194. package/.agent/workflows/review.md +141 -116
  195. package/.agent/workflows/session.md +122 -94
  196. package/.agent/workflows/status.md +101 -79
  197. package/.agent/workflows/strengthen-skills.md +164 -138
  198. package/.agent/workflows/super-prompt.md +24 -0
  199. package/.agent/workflows/swarm.md +193 -179
  200. package/.agent/workflows/test.md +211 -189
  201. package/.agent/workflows/tribunal-backend.md +136 -105
  202. package/.agent/workflows/tribunal-database.md +122 -95
  203. package/.agent/workflows/tribunal-frontend.md +221 -96
  204. package/.agent/workflows/tribunal-full.md +129 -100
  205. package/.agent/workflows/tribunal-mobile.md +122 -95
  206. package/.agent/workflows/tribunal-performance.md +136 -110
  207. package/.agent/workflows/tribunal-speed.md +209 -183
  208. package/.agent/workflows/ui-ux-pro-max.md +145 -122
  209. package/README.md +107 -55
  210. package/mcp_config.json +1 -3
  211. package/package.json +94 -94
@@ -1,576 +1,575 @@
1
- ---
2
- name: app-builder
3
- description: Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
4
- allowed-tools: Read, Write, Edit, Glob, Grep
5
- version: 3.1.0
6
- last-updated: 2026-04-06
7
- applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
- ---
9
-
10
- ## Hallucination Traps (Read First)
11
- - ❌ Generating entire applications in one shot -> ✅ Build one module at a time, verify each
12
- - ❌ Choosing a tech stack without asking the user -> ✅ Always ask about existing preferences, team skills, and deployment target
13
- - Hardcoding API keys or secrets during scaffolding -> ✅ Use .env.example with placeholder values from day one
14
-
15
- ---
16
-
17
-
18
- # App Builder — Application Orchestrator
19
-
20
- ---
21
-
22
- ## When This Skill Activates
23
-
24
- Activate when the user request involves:
25
- - Creating a new application from scratch
26
- - Building a major feature that spans frontend + backend + database
27
- - Bootstrapping a project structure for a new stack
28
-
29
- ---
30
-
31
- ## Orchestration Flow
32
-
33
- ```
34
- 1. CLARIFY → Understand what and who for
35
- 2. DECIDE → Choose the stack
36
- 3. PLAN → Break into ordered, dependency-aware tasks
37
- 4. COORDINATE → Run specialists in the right sequence
38
- 5. INTEGRATE Verify boundaries are consistent
39
- 6. PREVIEW Start the dev server
40
- ```
41
-
42
- ---
43
-
44
- ## Phase 1 — Clarification
45
-
46
- Before selecting a stack or writing a line of code, ask:
47
-
48
- ```
49
- 1. What is the core thing this app does? (not features — the primary purpose)
50
- 2. Who uses it? (internal tool, public-facing, B2B, mobile users?)
51
- 3. What constraints matter most? (time to ship, cost, performance, existing stack?)
52
- 4. What already exists that this integrates with?
53
- ```
54
-
55
- Wait for answers. Stack decisions depend on these answers.
56
-
57
- ---
58
-
59
- ## Phase 2 Stack Selection
60
-
61
- |App Type|Frontend|Backend|Database|
62
- |Content / marketing site|Next.js|Next.js API routes|PostgreSQL (if dynamic)|
63
- |SaaS web app|Next.js|Next.js API routes / Fastify|PostgreSQL + Redis|
64
- |Mobile app (cross-platform)|React Native (Expo)|Node.js API|PostgreSQL|
65
- |Internal dashboard / admin|Next.js|Next.js API routes|Existing|
66
- |Real-time (chat, collaboration)|Next.js|Fastify + WebSockets|PostgreSQL + Redis|
67
- |Data-heavy API|—|FastAPI (Python)|PostgreSQL|
68
- |AI assistant / RAG app|Next.js (streaming)|Fastify + LLM SDK|PostgreSQL + pgvector|
69
- |Edge-global, latency-critical|Next.js|Hono (Cloudflare Workers)|Turso / Cloudflare KV|
70
-
71
- **If unclear:** Next.js + PostgreSQL covers 80% of use cases and is the safest default for web apps.
72
-
73
- ---
74
-
75
- ## AI-Native App Orchestration
76
-
77
- For RAG apps and AI assistants, the build order changes:
78
-
79
- ```
80
- Step 1: vector-database-architect
81
- Design the embedding schema and chunking strategy
82
- → Output: schema with vector column + indexing strategy
83
-
84
- Step 2: ingest-pipeline (backend-specialist)
85
- Build document ingestion: load chunk → embed → store
86
- → Output: ingest API endpoint
87
-
88
- Step 3: retrieval-api (backend-specialist, uses Steps 1+2)
89
- → Build: embed query vector search rerankprompt assembly
90
- → Output: /api/generate endpoint with SSE streaming
91
-
92
- Step 4: streaming-frontend (frontend-specialist, uses Step 3)
93
- → Build: EventSource consumerstreaming text UIloading states
94
- → Output: AI chat or search interface
95
- ```
96
-
97
- **Never wire the frontend to the LLM directly** always proxy through your backend to keep API keys server-side.
98
-
99
- ---
100
-
101
- ## Phase 3Project Structure
102
-
103
- **Web (Next.js):**
104
-
105
- ```
106
- app/
107
- (auth)/ Auth pages — login, register
108
- (app)/ Protected app routes
109
- api/ API routes
110
- components/
111
- ui/ Primitive components (button, input, modal)
112
- features/ Feature-specific components
113
- lib/
114
- db/ Database client and utilities
115
- auth/ Auth helpers
116
- utils/ Shared utilities
117
- ```
118
-
119
- **API-only (Node.js / Fastify):**
120
-
121
- ```
122
- src/
123
- routes/ Route definitions (thin)
124
- handlers/ Request handling and response formatting
125
- services/ Business logic
126
- repositories/ Database access
127
- lib/ Shared utilities
128
- ```
129
-
130
- ---
131
-
132
- ## Phase 4 — Agent Coordination
133
-
134
- Build in dependency order:
135
-
136
- ```
137
- Step 1: database-architect
138
- Design and document the schema
139
- → Output: SQL schema, type definitions
140
-
141
- Step 2: backend-specialist (uses schema from Step 1)
142
- Build API routes
143
- → Output: API endpoint spec (URL, method, request, response shapes)
144
-
145
- Step 3: frontend-specialist (uses API spec from Step 2)
146
- → Build UI components
147
- Connect to real API contracts
148
- → Output: Working pages
149
-
150
- Step 4: test-engineer (uses all of the above)
151
- Create integration and E2E tests
152
- → Output: Test suite
153
- ```
154
-
155
- **Never run Step 2 against a guessed schema. Never run Step 3 against a guessed API.**
156
-
157
- ---
158
-
159
- ## Phase 5 Integration Verification
160
-
161
- Before presenting to the user, verify consistency:
162
-
163
- - API endpoints the frontend calls → exist on the backend
164
- - Database column names the backend queries → exist in the schema
165
- - TypeScript types match across package boundaries
166
- - Environment variables referenced in code → are in `.env.example`
167
-
168
- ---
169
-
170
- ## Phase 6 Preview Launch
171
-
172
- After integration verification, start the dev server:
173
-
174
- ```bash
175
- # Check for dev script
176
- python .agent/scripts/auto_preview.py start
177
-
178
- # Or manually
179
- npm run dev
180
- ```
181
-
182
- Report the URL to the user.
183
-
184
- ---
185
-
186
- ## Template Index
187
-
188
- |Template|Path|When to Use|
189
- |Next.js Full-Stack|`templates/nextjs-app/`|Web app with API routes|
190
- |React Native|`templates/react-native-app/`|Cross-platform mobile|
191
- |API Only|`templates/api-only/`|Backend service, no UI|
192
-
193
- ---
194
-
195
- ---
196
-
197
- ## Agent Coordination
198
-
199
- How App Builder orchestrates specialist agents.
200
-
201
- ### Agent Pipeline
202
-
203
- ```
204
- ┌─────────────────────────────────────────────────────────────┐
205
- │ APP BUILDER (Orchestrator) │
206
- └─────────────────────────────────────────────────────────────┘
207
-
208
-
209
- ┌─────────────────────────────────────────────────────────────┐
210
- │ PROJECT PLANNER │
211
- • Task breakdown │
212
- │ • Dependency graph │
213
- │ • File structure planning │
214
- Create {task-slug}.md in project root (MANDATORY)
215
- └─────────────────────────────────────────────────────────────┘
216
-
217
-
218
- ┌─────────────────────────────────────────────────────────────┐
219
- │ CHECKPOINT: PLAN VERIFICATION │
220
- 🔴 VERIFY: Does {task-slug}.md exist in project root? │
221
- │ 🔴 If NO → STOP → Create plan file first │
222
- │ 🔴 If YES → Proceed to specialist agents │
223
- └─────────────────────────────────────────────────────────────┘
224
-
225
- ┌───────────────────┼───────────────────┐
226
- ▼ ▼ ▼
227
- ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
228
- DATABASE │ │ BACKEND │ │ FRONTEND │
229
- │ ARCHITECT │ │ SPECIALIST │ │ SPECIALIST │
230
- │ │ │ │ │ │
231
- Schema design │ │ • API routes │ │ • Components │
232
- • Migrations │ │ • Controllers │ │ • Pages
233
- • Seed data │ │ • Middleware │ │ • Styling
234
- └─────────────────┘ └─────────────────┘ └─────────────────┘
235
-
236
- └───────────────────┼───────────────────┘
237
-
238
- ┌─────────────────────────────────────────────────────────────┐
239
- PARALLEL PHASE (Optional)
240
- │ • Security Auditor → Vulnerability check │
241
- │ • Test Engineer → Unit tests │
242
- │ • Performance Optimizer → Bundle analysis │
243
- └─────────────────────────────────────────────────────────────┘
244
-
245
-
246
- ┌─────────────────────────────────────────────────────────────┐
247
- │ DEVOPS ENGINEER │
248
- • Environment setup │
249
- │ • Preview deployment │
250
- │ • Health check │
251
- └─────────────────────────────────────────────────────────────┘
252
- ```
253
-
254
- ### Execution Order
255
-
256
- |Phase|Agent(s)|Parallel?|Prerequisite|CHECKPOINT|
257
- |-------|----------|-----------|--------------|------------|
258
- |0|Socratic Gate|❌|-|✅ Ask 3 questions|
259
- |1|Project Planner|❌|Questions answered|✅ **PLAN.md created**|
260
- |1.5|**PLAN VERIFICATION**|❌|PLAN.md exists|✅ **File exists in root**|
261
- |2|Database Architect|❌|Plan ready|Schema defined|
262
- |3|Backend Specialist|❌|Schema ready|API routes created|
263
- |4|Frontend Specialist|✅|API ready (partial)|UI components ready|
264
- |5|Security Auditor, Test Engineer|✅|Code ready|Tests & audit pass|
265
- |6|DevOps Engineer|❌|All code ready|Deployment ready|
266
-
267
- > 🔴 **CRITICAL:** Phase 1.5 is MANDATORY. No specialist agents proceed without PLAN.md verification.
268
-
269
- ---
270
-
271
- ## Feature Building
272
-
273
- How to analyze and implement new features.
274
-
275
- ### Feature Analysis
276
-
277
- ```
278
- Request: "add payment system"
279
-
280
- Analysis:
281
- ├── Required Changes:
282
- │ ├── Database: orders, payments tables
283
- │ ├── Backend: /api/checkout, /api/webhooks/stripe
284
- │ ├── Frontend: CheckoutForm, PaymentSuccess
285
- │ └── Config: Stripe API keys
286
-
287
- ├── Dependencies:
288
- │ ├── stripe package
289
- │ └── Existing user authentication
290
-
291
- └── Estimated Time: 15-20 minutes
292
- ```
293
-
294
- ### Iterative Enhancement Process
295
-
296
- ```
297
- 1. Analyze existing project
298
- 2. Create change plan
299
- 3. Present plan to user
300
- 4. Get approval
301
- 5. Apply changes
302
- 6. Test
303
- 7. Show preview
304
- ```
305
-
306
- ### Error Handling
307
-
308
- |Error Type|Solution Strategy|
309
- |------------|-------------------|
310
- |TypeScript Error|Fix type, add missing import|
311
- |Missing Dependency|Run npm install|
312
- |Port Conflict|Suggest alternative port|
313
- |Database Error|Check migration, validate connection|
314
-
315
- ### Recovery Strategy
316
-
317
- ```
318
- 1. Detect error
319
- 2. Try automatic fix
320
- 3. If failed, report to user
321
- 4. Suggest alternative
322
- 5. Rollback if necessary
323
- ```
324
-
325
- ---
326
-
327
- ## Project Type Detection
328
-
329
- Analyze user requests to determine project type and template.
330
-
331
- ### Keyword Matrix
332
-
333
- |Keywords|Project Type|Template|
334
- |----------|--------------|----------|
335
- |blog, post, article|Blog|astro-static|
336
- |e-commerce, product, cart, payment|E-commerce|nextjs-saas|
337
- |dashboard, panel, management|Admin Dashboard|nextjs-fullstack|
338
- |api, backend, service, rest|API Service|express-api|
339
- |python, fastapi, django|Python API|python-fastapi|
340
- |mobile, android, ios, react native|Mobile App (RN)|react-native-app|
341
- |flutter, dart|Mobile App (Flutter)|flutter-app|
342
- |portfolio, personal, cv|Portfolio|nextjs-static|
343
- |crm, customer, sales|CRM|nextjs-fullstack|
344
- |saas, subscription, stripe|SaaS|nextjs-saas|
345
- |landing, promotional, marketing|Landing Page|nextjs-static|
346
- |docs, documentation|Documentation|astro-static|
347
- |extension, plugin, chrome|Browser Extension|chrome-extension|
348
- |desktop, electron|Desktop App|electron-desktop|
349
- |cli, command line, terminal|CLI Tool|cli-tool|
350
- |monorepo, workspace|Monorepo|monorepo-turborepo|
351
-
352
- ### Detection Process
353
-
354
- ```
355
- 1. Tokenize user request
356
- 2. Extract keywords
357
- 3. Determine project type
358
- 4. Detect missing information → forward to conversation-manager
359
- 5. Suggest tech stack
360
- ```
361
-
362
- ---
363
-
364
- ## Project Scaffolding
365
-
366
- ---
367
-
368
- ### Next.js Full-Stack Structure (2025 Optimized)
369
-
370
- ```
371
- project-name/
372
- ├── src/
373
- │ ├── app/ # Routes only (thin layer)
374
- │ │ ├── layout.tsx
375
- │ │ ├── page.tsx
376
- │ │ ├── globals.css
377
- ├── (auth)/ # Route group - auth pages
378
- │ │ ├── login/page.tsx
379
- │ │ │ └── register/page.tsx
380
- │ │ ├── (dashboard)/ # Route group - dashboard layout
381
- │ │ ├── layout.tsx
382
- │ │ │ └── page.tsx
383
- │ │ └── api/
384
- │ │ └── [resource]/route.ts
385
- │ │
386
- ├── features/ # Feature-based modules
387
- │ │ ├── auth/
388
- │ │ │ ├── components/
389
- │ │ │ ├── hooks/
390
- │ │ ├── actions.ts # Server Actions
391
- │ │ ├── queries.ts # Data fetching
392
- │ │ │ └── types.ts
393
- │ │ ├── products/
394
- │ │ │ ├── components/
395
- │ │ │ ├── actions.ts
396
- │ │ │ └── queries.ts
397
- │ │ └── cart/
398
- │ │ └── ...
399
- │ │
400
- ├── shared/ # Shared utilities
401
- │ │ ├── components/ui/ # Reusable UI components
402
- │ │ ├── lib/ # Utils, helpers
403
- │ │ └── hooks/ # Global hooks
404
-
405
- └── server/ # Server-only code
406
- ├── db/ # Database client (Prisma)
407
- ├── auth/ # Auth config
408
- └── services/ # External API integrations
409
-
410
- ├── prisma/
411
- ├── schema.prisma
412
- ├── migrations/
413
- └── seed.ts
414
-
415
- ├── public/
416
- ├── .env.example
417
- ├── .env.local
418
- ├── package.json
419
- ├── tailwind.config.ts
420
- ├── tsconfig.json
421
- └── README.md
422
- ```
423
-
424
- ---
425
-
426
- ### Structure Principles
427
-
428
- |Principle|Implementation|
429
- |-----------|----------------|
430
- |**Feature isolation**|Each feature in `features/` with its own components, hooks, actions|
431
- |**Server/Client separation**|Server-only code in `server/`, prevents accidental client imports|
432
- |**Thin routes**|`app/` only for routing, logic lives in `features/`|
433
- |**Route groups**|`(groupName)/` for layout sharing without URL impact|
434
- |**Shared code**|`shared/` for truly reusable UI and utilities|
435
-
436
- ---
437
-
438
- ### Core Files
439
-
440
- |File|Purpose|
441
- |------|---------|
442
- |`package.json`|Dependencies|
443
- |`tsconfig.json`|TypeScript + path aliases (`@/features/*`)|
444
- |`tailwind.config.ts`|Tailwind config|
445
- |`.env.example`|Environment template|
446
- |`README.md`|Project documentation|
447
- |`.gitignore`|Git ignore rules|
448
- |`prisma/schema.prisma`|Database schema|
449
-
450
- ---
451
-
452
- ### Path Aliases (tsconfig.json)
453
-
454
- ```json
455
- {
456
- "compilerOptions": {
457
- "paths": {
458
- "@/*": ["./src/*"],
459
- "@/features/*": ["./src/features/*"],
460
- "@/shared/*": ["./src/shared/*"],
461
- "@/server/*": ["./src/server/*"]
462
- }
463
- }
464
- }
465
- ```
466
-
467
- ---
468
-
469
- ### When to Use What
470
-
471
- |Need|Location|
472
- |------|----------|
473
- |New page/route|`app/(group)/page.tsx`|
474
- |Feature component|`features/[name]/components/`|
475
- |Server action|`features/[name]/actions.ts`|
476
- |Data fetching|`features/[name]/queries.ts`|
477
- |Reusable button/input|`shared/components/ui/`|
478
- |Database query|`server/db/`|
479
- |External API call|`server/services/`|
480
-
481
- ---
482
-
483
- ## Tech Stack Selection (2026)
484
-
485
- Default and alternative technology choices for web applications.
486
-
487
- ### Default Stack (Web App - 2026)
488
-
489
- ```yaml
490
- Frontend:
491
- framework: Next.js 16 (Stable)
492
- language: TypeScript 5.7+
493
- styling: Tailwind CSS v4
494
- state: React 19 Actions / Server Components
495
- bundler: Turbopack (Stable for Dev)
496
-
497
- Backend:
498
- runtime: Node.js 23
499
- framework: Next.js API Routes / Hono (for Edge)
500
- validation: Zod / TypeBox
501
-
502
- Database:
503
- primary: PostgreSQL
504
- orm: Prisma / Drizzle
505
- hosting: Supabase / Neon
506
-
507
- Auth:
508
- provider: Auth.js (v5) / Clerk
509
-
510
- Monorepo:
511
- tool: Turborepo 2.0
512
- ```
513
-
514
- ### Alternative Options
515
-
516
- |Need|Default|Alternative|
517
- |------|---------|-------------|
518
- |Real-time|-|Supabase Realtime, Socket.io|
519
- |File storage|-|Cloudinary, S3|
520
- |Payment|Stripe|LemonSqueezy, Paddle|
521
- |Email|-|Resend, SendGrid|
522
- |Search|-|Algolia, Typesense|
523
-
524
-
525
- ---
526
-
527
-
528
-
529
- AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
530
-
531
- 1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
532
- 2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
533
- 3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
534
- 4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
535
- 5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
536
-
537
- ---
538
-
539
-
540
-
541
- **Slash command: `/review` or `/tribunal-full`**
542
- **Active reviewers: `logic-reviewer` · `security-auditor`**
543
-
544
- ### ❌ Forbidden AI Tropes
545
-
546
- 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
547
- 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
548
- 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
549
-
550
-
551
-
552
- Review these questions before confirming output:
553
- ```
554
- ✅ Did I rely ONLY on real, verified tools and methods?
555
- ✅ Is this solution appropriately scoped to the user's constraints?
556
- ✅ Did I handle potential failure modes and edge cases?
557
- ✅ Have I avoided generic boilerplate that doesn't add value?
558
- ```
559
-
560
- ### 🛑 Verification-Before-Completion (VBC) Protocol
561
-
562
- **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
563
- - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
564
- - ✅ **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.
565
-
566
-
567
- ## Pre-Flight Checklist
568
- - [ ] Have I reviewed the user's specific constraints and requests?
569
- - [ ] Have I checked the environment for relevant existing implementations?
570
-
571
- ## VBC Protocol (Verification-Before-Completion)
572
- You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
1
+ ---
2
+ name: app-builder
3
+ description: Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.
4
+ allowed-tools: Read, Write, Edit, Glob, Grep
5
+ version: 3.1.0
6
+ last-updated: 2026-04-06
7
+ applies-to-model: gemini-2.5-pro, claude-3-7-sonnet
8
+ routing:
9
+ domain: general
10
+ tier: basic
11
+ ---
12
+
13
+ ## Hallucination Traps (Read First)
14
+
15
+ - ❌ Generating entire applications in one shot -> ✅ Build one module at a time, verify each
16
+ - ❌ Choosing a tech stack without asking the user -> ✅ Always ask about existing preferences, team skills, and deployment target
17
+ - ❌ Hardcoding API keys or secrets during scaffolding -> ✅ Use .env.example with placeholder values from day one
18
+
19
+ ---
20
+
21
+ # App Builder — Application Orchestrator
22
+
23
+ ---
24
+
25
+ ## When This Skill Activates
26
+
27
+ Activate when the user request involves:
28
+
29
+ - Creating a new application from scratch
30
+ - Building a major feature that spans frontend + backend + database
31
+ - Bootstrapping a project structure for a new stack
32
+
33
+ ---
34
+
35
+ ## Orchestration Flow
36
+
37
+ ```
38
+ 1. CLARIFY Understand what and who for
39
+ 2. DECIDE Choose the stack
40
+ 3. PLAN → Break into ordered, dependency-aware tasks
41
+ 4. COORDINATE → Run specialists in the right sequence
42
+ 5. INTEGRATE → Verify boundaries are consistent
43
+ 6. PREVIEW → Start the dev server
44
+ ```
45
+
46
+ ---
47
+
48
+ ## Phase 1 — Clarification
49
+
50
+ Before selecting a stack or writing a line of code, ask:
51
+
52
+ ```
53
+ 1. What is the core thing this app does? (not features — the primary purpose)
54
+ 2. Who uses it? (internal tool, public-facing, B2B, mobile users?)
55
+ 3. What constraints matter most? (time to ship, cost, performance, existing stack?)
56
+ 4. What already exists that this integrates with?
57
+ ```
58
+
59
+ Wait for answers. Stack decisions depend on these answers.
60
+
61
+ ---
62
+
63
+ ## Phase 2 Stack Selection
64
+
65
+ |App Type|Frontend|Backend|Database|
66
+ |Content / marketing site|Next.js|Next.js API routes|PostgreSQL (if dynamic)|
67
+ |SaaS web app|Next.js|Next.js API routes / Fastify|PostgreSQL + Redis|
68
+ |Mobile app (cross-platform)|React Native (Expo)|Node.js API|PostgreSQL|
69
+ |Internal dashboard / admin|Next.js|Next.js API routes|Existing|
70
+ |Real-time (chat, collaboration)|Next.js|Fastify + WebSockets|PostgreSQL + Redis|
71
+ |Data-heavy API|—|FastAPI (Python)|PostgreSQL|
72
+ |AI assistant / RAG app|Next.js (streaming)|Fastify + LLM SDK|PostgreSQL + pgvector|
73
+ |Edge-global, latency-critical|Next.js|Hono (Cloudflare Workers)|Turso / Cloudflare KV|
74
+
75
+ **If unclear:** Next.js + PostgreSQL covers 80% of use cases and is the safest default for web apps.
76
+
77
+ ---
78
+
79
+ ## AI-Native App Orchestration
80
+
81
+ For RAG apps and AI assistants, the build order changes:
82
+
83
+ ```
84
+ Step 1: vector-database-architect
85
+ Design the embedding schema and chunking strategy
86
+ → Output: schema with vector column + indexing strategy
87
+
88
+ Step 2: ingest-pipeline (backend-specialist)
89
+ → Build document ingestion: loadchunkembedstore
90
+ → Output: ingest API endpoint
91
+
92
+ Step 3: retrieval-api (backend-specialist, uses Steps 1+2)
93
+ → Build: embed queryvector search rerank prompt assembly
94
+ → Output: /api/generate endpoint with SSE streaming
95
+
96
+ Step 4: streaming-frontend (frontend-specialist, uses Step 3)
97
+ Build: EventSource consumer streaming text UI loading states
98
+ → Output: AI chat or search interface
99
+ ```
100
+
101
+ **Never wire the frontend to the LLM directly** always proxy through your backend to keep API keys server-side.
102
+
103
+ ---
104
+
105
+ ## Phase 3 — Project Structure
106
+
107
+ **Web (Next.js):**
108
+
109
+ ```
110
+ app/
111
+ (auth)/ Auth pages login, register
112
+ (app)/ Protected app routes
113
+ api/ API routes
114
+ components/
115
+ ui/ Primitive components (button, input, modal)
116
+ features/ Feature-specific components
117
+ lib/
118
+ db/ Database client and utilities
119
+ auth/ Auth helpers
120
+ utils/ Shared utilities
121
+ ```
122
+
123
+ **API-only (Node.js / Fastify):**
124
+
125
+ ```
126
+ src/
127
+ routes/ Route definitions (thin)
128
+ handlers/ Request handling and response formatting
129
+ services/ Business logic
130
+ repositories/ Database access
131
+ lib/ Shared utilities
132
+ ```
133
+
134
+ ---
135
+
136
+ ## Phase 4 — Agent Coordination
137
+
138
+ Build in dependency order:
139
+
140
+ ```
141
+ Step 1: database-architect
142
+ Design and document the schema
143
+ → Output: SQL schema, type definitions
144
+
145
+ Step 2: backend-specialist (uses schema from Step 1)
146
+ → Build API routes
147
+ Output: API endpoint spec (URL, method, request, response shapes)
148
+
149
+ Step 3: frontend-specialist (uses API spec from Step 2)
150
+ Build UI components
151
+ Connect to real API contracts
152
+ → Output: Working pages
153
+
154
+ Step 4: test-engineer (uses all of the above)
155
+ Create integration and E2E tests
156
+ → Output: Test suite
157
+ ```
158
+
159
+ **Never run Step 2 against a guessed schema. Never run Step 3 against a guessed API.**
160
+
161
+ ---
162
+
163
+ ## Phase 5 Integration Verification
164
+
165
+ Before presenting to the user, verify consistency:
166
+
167
+ - API endpoints the frontend calls → exist on the backend
168
+ - Database column names the backend queries → exist in the schema
169
+ - TypeScript types match across package boundaries
170
+ - Environment variables referenced in code → are in `.env.example`
171
+
172
+ ---
173
+
174
+ ## Phase 6 — Preview Launch
175
+
176
+ After integration verification, start the dev server:
177
+
178
+ ```bash
179
+ # Check for dev script
180
+ python .agent/scripts/auto_preview.py start
181
+
182
+ # Or manually
183
+ npm run dev
184
+ ```
185
+
186
+ Report the URL to the user.
187
+
188
+ ---
189
+
190
+ ## Template Index
191
+
192
+ |Template|Path|When to Use|
193
+ |Next.js Full-Stack|`templates/nextjs-app/`|Web app with API routes|
194
+ |React Native|`templates/react-native-app/`|Cross-platform mobile|
195
+ |API Only|`templates/api-only/`|Backend service, no UI|
196
+
197
+ ---
198
+
199
+ ---
200
+
201
+ ## Agent Coordination
202
+
203
+ How App Builder orchestrates specialist agents.
204
+
205
+ ### Agent Pipeline
206
+
207
+ ```
208
+ ┌─────────────────────────────────────────────────────────────┐
209
+ │ APP BUILDER (Orchestrator) │
210
+ └─────────────────────────────────────────────────────────────┘
211
+
212
+
213
+ ┌─────────────────────────────────────────────────────────────┐
214
+ PROJECT PLANNER
215
+ │ • Task breakdown │
216
+ • Dependency graph │
217
+ │ • File structure planning │
218
+ │ • Create {task-slug}.md in project root (MANDATORY) │
219
+ └─────────────────────────────────────────────────────────────┘
220
+
221
+
222
+ ┌─────────────────────────────────────────────────────────────┐
223
+ │ CHECKPOINT: PLAN VERIFICATION │
224
+ 🔴 VERIFY: Does {task-slug}.md exist in project root? │
225
+ │ 🔴 If NO → STOP → Create plan file first │
226
+ │ 🔴 If YES → Proceed to specialist agents │
227
+ └─────────────────────────────────────────────────────────────┘
228
+
229
+ ┌───────────────────┼───────────────────┐
230
+ ▼ ▼ ▼
231
+ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
232
+ DATABASE │ │ BACKEND │ │ FRONTEND
233
+ ARCHITECT │ │ SPECIALIST │ │ SPECIALIST
234
+ │ │ │ │ │ │
235
+ • Schema design • API routes │ │ • Components │
236
+ │ • Migrations │ │ • Controllers │ │ • Pages │
237
+ │ • Seed data │ │ • Middleware │ │ • Styling │
238
+ └─────────────────┘ └─────────────────┘ └─────────────────┘
239
+
240
+ └───────────────────┼───────────────────┘
241
+
242
+ ┌─────────────────────────────────────────────────────────────┐
243
+ │ PARALLEL PHASE (Optional) │
244
+ • Security Auditor → Vulnerability check │
245
+ │ • Test Engineer → Unit tests │
246
+ │ • Performance Optimizer → Bundle analysis │
247
+ └─────────────────────────────────────────────────────────────┘
248
+
249
+
250
+ ┌─────────────────────────────────────────────────────────────┐
251
+ │ DEVOPS ENGINEER │
252
+ │ • Environment setup │
253
+ │ • Preview deployment │
254
+ │ • Health check │
255
+ └─────────────────────────────────────────────────────────────┘
256
+ ```
257
+
258
+ ### Execution Order
259
+
260
+ | Phase | Agent(s) | Parallel? | Prerequisite | CHECKPOINT |
261
+ | ----- | ------------------------------- | --------- | ------------------- | -------------------------- |
262
+ | 0 | Socratic Gate | ❌ | - | ✅ Ask 3 questions |
263
+ | 1 | Project Planner | | Questions answered | ✅ **PLAN.md created** |
264
+ | 1.5 | **PLAN VERIFICATION** | ❌ | PLAN.md exists | **File exists in root** |
265
+ | 2 | Database Architect | | Plan ready | Schema defined |
266
+ | 3 | Backend Specialist | ❌ | Schema ready | API routes created |
267
+ | 4 | Frontend Specialist | ✅ | API ready (partial) | UI components ready |
268
+ | 5 | Security Auditor, Test Engineer | ✅ | Code ready | Tests & audit pass |
269
+ | 6 | DevOps Engineer | ❌ | All code ready | Deployment ready |
270
+
271
+ > 🔴 **CRITICAL:** Phase 1.5 is MANDATORY. No specialist agents proceed without PLAN.md verification.
272
+
273
+ ---
274
+
275
+ ## Feature Building
276
+
277
+ How to analyze and implement new features.
278
+
279
+ ### Feature Analysis
280
+
281
+ ```
282
+ Request: "add payment system"
283
+
284
+ Analysis:
285
+ ├── Required Changes:
286
+ ├── Database: orders, payments tables
287
+ ├── Backend: /api/checkout, /api/webhooks/stripe
288
+ │ ├── Frontend: CheckoutForm, PaymentSuccess
289
+ │ └── Config: Stripe API keys
290
+
291
+ ├── Dependencies:
292
+ │ ├── stripe package
293
+ │ └── Existing user authentication
294
+
295
+ └── Estimated Time: 15-20 minutes
296
+ ```
297
+
298
+ ### Iterative Enhancement Process
299
+
300
+ ```
301
+ 1. Analyze existing project
302
+ 2. Create change plan
303
+ 3. Present plan to user
304
+ 4. Get approval
305
+ 5. Apply changes
306
+ 6. Test
307
+ 7. Show preview
308
+ ```
309
+
310
+ ### Error Handling
311
+
312
+ | Error Type | Solution Strategy |
313
+ | ------------------ | ------------------------------------ |
314
+ | TypeScript Error | Fix type, add missing import |
315
+ | Missing Dependency | Run npm install |
316
+ | Port Conflict | Suggest alternative port |
317
+ | Database Error | Check migration, validate connection |
318
+
319
+ ### Recovery Strategy
320
+
321
+ ```
322
+ 1. Detect error
323
+ 2. Try automatic fix
324
+ 3. If failed, report to user
325
+ 4. Suggest alternative
326
+ 5. Rollback if necessary
327
+ ```
328
+
329
+ ---
330
+
331
+ ## Project Type Detection
332
+
333
+ Analyze user requests to determine project type and template.
334
+
335
+ ### Keyword Matrix
336
+
337
+ | Keywords | Project Type | Template |
338
+ | ---------------------------------- | -------------------- | ------------------ |
339
+ | blog, post, article | Blog | astro-static |
340
+ | e-commerce, product, cart, payment | E-commerce | nextjs-saas |
341
+ | dashboard, panel, management | Admin Dashboard | nextjs-fullstack |
342
+ | api, backend, service, rest | API Service | express-api |
343
+ | python, fastapi, django | Python API | python-fastapi |
344
+ | mobile, android, ios, react native | Mobile App (RN) | react-native-app |
345
+ | flutter, dart | Mobile App (Flutter) | flutter-app |
346
+ | portfolio, personal, cv | Portfolio | nextjs-static |
347
+ | crm, customer, sales | CRM | nextjs-fullstack |
348
+ | saas, subscription, stripe | SaaS | nextjs-saas |
349
+ | landing, promotional, marketing | Landing Page | nextjs-static |
350
+ | docs, documentation | Documentation | astro-static |
351
+ | extension, plugin, chrome | Browser Extension | chrome-extension |
352
+ | desktop, electron | Desktop App | electron-desktop |
353
+ | cli, command line, terminal | CLI Tool | cli-tool |
354
+ | monorepo, workspace | Monorepo | monorepo-turborepo |
355
+
356
+ ### Detection Process
357
+
358
+ ```
359
+ 1. Tokenize user request
360
+ 2. Extract keywords
361
+ 3. Determine project type
362
+ 4. Detect missing information → forward to conversation-manager
363
+ 5. Suggest tech stack
364
+ ```
365
+
366
+ ---
367
+
368
+ ## Project Scaffolding
369
+
370
+ ---
371
+
372
+ ### Next.js Full-Stack Structure (2025 Optimized)
373
+
374
+ ```
375
+ project-name/
376
+ ├── src/
377
+ │ ├── app/ # Routes only (thin layer)
378
+ │ │ ├── layout.tsx
379
+ │ │ ├── page.tsx
380
+ │ │ ├── globals.css
381
+ │ │ ├── (auth)/ # Route group - auth pages
382
+ │ │ │ ├── login/page.tsx
383
+ │ │ └── register/page.tsx
384
+ │ │ ├── (dashboard)/ # Route group - dashboard layout
385
+ │ │ │ ├── layout.tsx
386
+ │ │ └── page.tsx
387
+ │ │ └── api/
388
+ │ │ └── [resource]/route.ts
389
+ │ │
390
+ │ ├── features/ # Feature-based modules
391
+ │ │ ├── auth/
392
+ │ │ │ ├── components/
393
+ │ │ ├── hooks/
394
+ │ │ │ ├── actions.ts # Server Actions
395
+ │ │ │ ├── queries.ts # Data fetching
396
+ │ │ │ └── types.ts
397
+ │ │ ├── products/
398
+ │ │ │ ├── components/
399
+ │ │ │ ├── actions.ts
400
+ │ │ └── queries.ts
401
+ │ │ └── cart/
402
+ │ │ └── ...
403
+ │ │
404
+ ├── shared/ # Shared utilities
405
+ │ ├── components/ui/ # Reusable UI components
406
+ ├── lib/ # Utils, helpers
407
+ │ └── hooks/ # Global hooks
408
+
409
+ └── server/ # Server-only code
410
+ ├── db/ # Database client (Prisma)
411
+ ├── auth/ # Auth config
412
+ └── services/ # External API integrations
413
+
414
+ ├── prisma/
415
+ ├── schema.prisma
416
+ ├── migrations/
417
+ │ └── seed.ts
418
+
419
+ ├── public/
420
+ ├── .env.example
421
+ ├── .env.local
422
+ ├── package.json
423
+ ├── tailwind.config.ts
424
+ ├── tsconfig.json
425
+ └── README.md
426
+ ```
427
+
428
+ ---
429
+
430
+ ### Structure Principles
431
+
432
+ | Principle | Implementation |
433
+ | ---------------------------- | ------------------------------------------------------------------- |
434
+ | **Feature isolation** | Each feature in `features/` with its own components, hooks, actions |
435
+ | **Server/Client separation** | Server-only code in `server/`, prevents accidental client imports |
436
+ | **Thin routes** | `app/` only for routing, logic lives in `features/` |
437
+ | **Route groups** | `(groupName)/` for layout sharing without URL impact |
438
+ | **Shared code** | `shared/` for truly reusable UI and utilities |
439
+
440
+ ---
441
+
442
+ ### Core Files
443
+
444
+ | File | Purpose |
445
+ | ---------------------- | ------------------------------------------ |
446
+ | `package.json` | Dependencies |
447
+ | `tsconfig.json` | TypeScript + path aliases (`@/features/*`) |
448
+ | `tailwind.config.ts` | Tailwind config |
449
+ | `.env.example` | Environment template |
450
+ | `README.md` | Project documentation |
451
+ | `.gitignore` | Git ignore rules |
452
+ | `prisma/schema.prisma` | Database schema |
453
+
454
+ ---
455
+
456
+ ### Path Aliases (tsconfig.json)
457
+
458
+ ```json
459
+ {
460
+ "compilerOptions": {
461
+ "paths": {
462
+ "@/*": ["./src/*"],
463
+ "@/features/*": ["./src/features/*"],
464
+ "@/shared/*": ["./src/shared/*"],
465
+ "@/server/*": ["./src/server/*"]
466
+ }
467
+ }
468
+ }
469
+ ```
470
+
471
+ ---
472
+
473
+ ### When to Use What
474
+
475
+ | Need | Location |
476
+ | --------------------- | ----------------------------- |
477
+ | New page/route | `app/(group)/page.tsx` |
478
+ | Feature component | `features/[name]/components/` |
479
+ | Server action | `features/[name]/actions.ts` |
480
+ | Data fetching | `features/[name]/queries.ts` |
481
+ | Reusable button/input | `shared/components/ui/` |
482
+ | Database query | `server/db/` |
483
+ | External API call | `server/services/` |
484
+
485
+ ---
486
+
487
+ ## Tech Stack Selection (2026)
488
+
489
+ Default and alternative technology choices for web applications.
573
490
 
491
+ ### Default Stack (Web App - 2026)
492
+
493
+ ```yaml
494
+ Frontend:
495
+ framework: Next.js 16 (Stable)
496
+ language: TypeScript 5.7+
497
+ styling: Tailwind CSS v4
498
+ state: React 19 Actions / Server Components
499
+ bundler: Turbopack (Stable for Dev)
500
+
501
+ Backend:
502
+ runtime: Node.js 23
503
+ framework: Next.js API Routes / Hono (for Edge)
504
+ validation: Zod / TypeBox
505
+
506
+ Database:
507
+ primary: PostgreSQL
508
+ orm: Prisma / Drizzle
509
+ hosting: Supabase / Neon
510
+
511
+ Auth:
512
+ provider: Auth.js (v5) / Clerk
513
+
514
+ Monorepo:
515
+ tool: Turborepo 2.0
516
+ ```
517
+
518
+ ### Alternative Options
519
+
520
+ | Need | Default | Alternative |
521
+ | ------------ | ------- | ---------------------------- |
522
+ | Real-time | - | Supabase Realtime, Socket.io |
523
+ | File storage | - | Cloudinary, S3 |
524
+ | Payment | Stripe | LemonSqueezy, Paddle |
525
+ | Email | - | Resend, SendGrid |
526
+ | Search | - | Algolia, Typesense |
527
+
528
+ ---
529
+
530
+ AI coding assistants often fall into specific bad habits when dealing with this domain. These are strictly forbidden:
531
+
532
+ 1. **Over-engineering:** Proposing complex abstractions or distributed systems when a simpler approach suffices.
533
+ 2. **Hallucinated Libraries/Methods:** Using non-existent methods or packages. Always `// VERIFY` or check `package.json` / `requirements.txt`.
534
+ 3. **Skipping Edge Cases:** Writing the "happy path" and ignoring error handling, timeouts, or data validation.
535
+ 4. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
536
+ 5. **Silent Degradation:** Catching and suppressing errors without logging or re-raising.
537
+
538
+ ---
539
+
540
+ **Slash command: `/review` or `/tribunal-full`**
541
+ **Active reviewers: `logic-reviewer` · `security-auditor`**
542
+
543
+ ### ❌ Forbidden AI Tropes
544
+
545
+ 1. **Blind Assumptions:** Never make an assumption without documenting it clearly with `// VERIFY: [reason]`.
546
+ 2. **Silent Degradation:** Catching and suppressing errors without logging or handling.
547
+ 3. **Context Amnesia:** Forgetting the user's constraints and offering generic advice instead of tailored solutions.
548
+
549
+ Review these questions before confirming output:
550
+
551
+ ```
552
+ ✅ Did I rely ONLY on real, verified tools and methods?
553
+ ✅ Is this solution appropriately scoped to the user's constraints?
554
+ ✅ Did I handle potential failure modes and edge cases?
555
+ ✅ Have I avoided generic boilerplate that doesn't add value?
556
+ ```
557
+
558
+ ### 🛑 Verification-Before-Completion (VBC) Protocol
559
+
560
+ **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
561
+
562
+ - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
563
+ - ✅ **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.
564
+
565
+ ## Pre-Flight Checklist
566
+
567
+ - [ ] Have I reviewed the user's specific constraints and requests?
568
+ - [ ] Have I checked the environment for relevant existing implementations?
569
+
570
+ ## VBC Protocol (Verification-Before-Completion)
571
+
572
+ You MUST verify existing code signatures and variables before attempting to modify or call them. No hallucination is permitted.
574
573
 
575
574
  ---
576
575
 
@@ -600,6 +599,7 @@ AI coding assistants often fall into specific bad habits when dealing with this
600
599
  ### ✅ Pre-Flight Self-Audit
601
600
 
602
601
  Review these questions before confirming output:
602
+
603
603
  ```
604
604
  ✅ Did I rely ONLY on real, verified tools and methods?
605
605
  ✅ Is this solution appropriately scoped to the user's constraints?
@@ -610,5 +610,6 @@ Review these questions before confirming output:
610
610
  ### 🛑 Verification-Before-Completion (VBC) Protocol
611
611
 
612
612
  **CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
613
+
613
614
  - ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
614
615
  - ✅ **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.