ai-developer-skill-os 1.0.0

package/skills/engineering/agent-orchestrator/SKILL.md

@@ -0,0 +1,177 @@
+---
+name: agent-orchestrator
+description: >-
+  Phân tích yêu cầu, lên kế hoạch thực thi chi tiết và điều phối các tác vụ cho đúng skill. Không tự viết code.
+version: 1.0.0
+category: engineering
+tags: [orchestration, planning, workflow, task-decomposition]
+platforms: [antigravity, claude-code, kilo-code, cursor, windsurf]
+---
+
+# Agent Orchestrator
+
+> **Language rule:**
+> Use **English** for: skill names, phase labels, technical decisions, file paths.
+> Use **the user's language** for: explanations, questions, plan summaries, and feedback.
+
+> ⚠️ **CRITICAL CONSTRAINT: This skill MUST NOT write any code.**
+> Its only job is to analyze, plan, and delegate.
+> If the orchestrator starts writing implementation code — it is violating its role.
+> Immediately stop and delegate to the appropriate skill instead.
+
+---
+
+## Trigger
+
+Activate this skill when:
+- User describes a task without knowing where to start
+- User request spans multiple concerns (UI + API + state + tests)
+- Request is ambiguous and needs decomposition before action
+- User says: "help me plan", "what should I do first", "how do I approach this"
+
+---
+
+## Scope
+
+- ✅ Analyze the user's request
+- ✅ Identify which skills are needed
+- ✅ Define the correct execution order
+- ✅ Create a step-by-step plan
+- ✅ Delegate each step to the correct skill
+- ✅ Track overall progress
+
+---
+
+## Non-goals
+
+- ❌ Do NOT write implementation code
+- ❌ Do NOT modify files
+- ❌ Do NOT fix bugs directly (delegate to `bug-fix`)
+- ❌ Do NOT build UI directly (delegate to `ui-builder`)
+- ❌ Do NOT make architectural decisions unilaterally (delegate to `frontend-architecture`)
+
+---
+
+## Workflow
+
+### Phase 1 — Request Analysis
+
+Parse the user's request:
+
+1. **What** is being asked? (feature, fix, refactor, review, deploy?)
+2. **Where** does it belong? (frontend, backend, shared, infrastructure?)
+3. **What is the scope?** (single component, full feature, entire codebase?)
+4. **What is unknown?** List any ambiguities that need clarification.
+
+If critical information is missing → ask before planning.
+
+---
+
+### Phase 2 — Skill Selection
+
+Map the request to skills from the registry:
+
+| Request type | Recommended skill(s) |
+|---|---|
+| "I don't know what's wrong" | `project-audit` → `bug-fix` |
+| "Build a new page" | `frontend-architecture` → `design-system` → `ui-builder` |
+| "Add API call" | `context-manager` → `api-integration` |
+| "App is slow" | `project-audit` → `frontend-performance` |
+| "Upgrade dependencies" | `migration` |
+| "Write tests" | `frontend-testing` |
+
+Always check dependencies from `skills.json` — load dependent skills first.
+
+---
+
+### Phase 3 — Execution Plan
+
+Produce a numbered, ordered plan. Each step maps to one skill.
+
+Format:
+```
+Step 1: [skill-name] — [what it will do]
+Step 2: [skill-name] — [what it will do]
+Step 3: [skill-name] — [what it will do]
+```
+
+Mark dependencies explicitly:
+```
+Step 2 requires Step 1 to complete first.
+```
+
+---
+
+### Phase 4 — Delegation
+
+For each step in the plan:
+1. Announce which skill is being activated
+2. Pass relevant context to that skill
+3. Wait for skill output
+4. Confirm completion before moving to next step
+
+---
+
+### Phase 5 — Progress Tracking
+
+After each skill completes:
+- Mark step as ✅ done
+- Note any output or blockers
+- Adjust remaining plan if needed
+- Report overall progress to user
+
+---
+
+## Decision Tree
+
+```
+Is the request clear enough to plan?
+  ├── No  → Ask 1-3 clarifying questions, then plan
+  └── Yes → Does it span multiple concerns?
+              ├── Yes → Create multi-step plan with skill sequence
+              └── No  → Route directly to single skill
+```
+
+```
+Does a skill dependency exist?
+  ├── Yes → Run dependency skill first
+  └── No  → Run skill directly
+```
+
+---
+
+## Output Format
+
+```
+📋 Plan: [Brief description of what we're doing]
+
+Step 1: `[skill-name]` — [Purpose]
+Step 2: `[skill-name]` — [Purpose]  ← requires Step 1
+Step 3: `[skill-name]` — [Purpose]
+
+⏳ Starting with Step 1...
+```
+
+After each step:
+```
+✅ Step 1 complete: [Brief outcome]
+▶️  Moving to Step 2: `[skill-name]`
+```
+
+---
+
+## Validation Checklist
+
+Before finishing orchestration:
+
+- [ ] All planned steps completed
+- [ ] Each step was handled by the correct skill
+- [ ] No code was written by the orchestrator itself
+- [ ] User has been informed of final outcome
+- [ ] Next recommended actions provided if relevant
+
+---
+
+## Examples
+
+See `examples/` folder.

package/skills/engineering/api-integration/SKILL.md

@@ -0,0 +1,378 @@
+---
+name: api-integration
+description: >-
+  Chuyển đổi tài liệu API (curl, swagger...) thành code tích hợp frontend chuẩn xác, có type an toàn và xử lý lỗi.
+version: 2.0.0
+category: engineering
+tags: [api, integration, rest, graphql, axios, fetch, react-query, typescript]
+platforms: [antigravity, claude-code, kilo-code, cursor, windsurf]
+---
+
+# API Integration Engineer
+
+> **Language rule:**
+> Use **English** for: type names, function names, file paths, API terms, HTTP concepts.
+> Use **the user's language** for: explanations, questions, and summaries.
+
+---
+
+## Trigger
+
+Activate this skill when the user provides any of:
+- `curl` command
+- Swagger 2.0 / OpenAPI 3.0 (YAML or JSON)
+- Postman collection or HAR file
+- API documentation (endpoint, method, request/response)
+- Code snippet to reverse-engineer (fetch/axios/custom client)
+- Backend controller or route handler to mirror on the frontend
+
+---
+
+## Scope
+
+- ✅ Parse and understand any API input format
+- ✅ Extract the full API contract (request + response + errors)
+- ✅ Detect existing project patterns (HTTP client, state layer, conventions)
+- ✅ Generate typed service/client, hooks/queries, and TypeScript types
+- ✅ Follow and extend existing architecture — never duplicate it
+- ✅ Handle special cases: file upload, file download, pagination, auth, WebSocket
+
+---
+
+## Non-goals
+
+- ❌ Do NOT create a new HTTP client if one already exists
+- ❌ Do NOT introduce a new state system if one is already in use
+- ❌ Do NOT write UI logic inside the API layer
+- ❌ Do NOT hardcode URLs, tokens, or secrets
+- ❌ Do NOT use `any` when types can be inferred
+- ❌ Do NOT overwrite existing files without explicit user approval
+
+---
+
+## Severity Levels
+
+| Level | Meaning |
+|-------|---------|
+| P0 | Conflict with existing endpoint or type — must resolve before generating |
+| P1 | Missing critical info (auth, response schema) — ask before proceeding |
+| P2 | Naming or structure inconsistency — warn and apply best guess |
+| P3 | Missing optional fields — document assumption and proceed |
+
+---
+
+## Workflow
+
+### Phase 1 — Input Validation
+
+Before parsing, verify:
+- URL is valid and method is correct (GET/POST/PUT/PATCH/DELETE)
+- Auth format is identifiable (Bearer, API Key, OAuth2, Basic, Cookie)
+- Request info is present (path params, query params, body)
+- Response structure is clear (JSON, binary, stream, paginated)
+- Error cases are documented
+
+If critical info is missing → **stop and ask**. Do not guess.
+
+```json
+{
+  "validation": {
+    "status": "VALID | INVALID | INCOMPLETE",
+    "confidence": 0.95,
+    "errors": [],
+    "warnings": [],
+    "input_type": "curl | openapi | postman | docs | code"
+  }
+}
+```
+
+---
+
+### Phase 2 — API Contract Extraction
+
+Extract the full contract:
+
+```
+metadata:
+  name, domain, endpoint, method, version, description
+
+request:
+  pathParams:    { name, type, required }
+  queryParams:   { name, type, required, default }
+  headers:       { name, value, required }
+  body:          { contentType, schema { field, type, required, nullable } }
+  auth:          { type, location, name }
+
+response:
+  success:       { statusCode, contentType, schema, pagination? }
+  errors:        [ { statusCode, message, businessCode? } ]
+
+special:
+  rateLimit, timeout, retryable, streaming
+```
+
+Map each field: `type`, `required`, `nullable`, `enum`, `example`.
+
+---
+
+### Phase 3 — Project Profile Detection
+
+1. Check for `.api-config.json` at project root → use if present
+2. Otherwise infer from:
+   - Framework: `package.json`, config files, imports
+   - HTTP client: existing axios instance, fetch wrapper, custom client
+   - State management: React Query, Redux, Zustand, Pinia, Apollo, Vuex
+   - Type system: `tsconfig.json`, JSDoc, plain JS
+   - Folder conventions: `services/`, `hooks/`, `api/`, `types/`, `adapters/`
+   - Naming: camelCase, PascalCase, snake_case, file patterns
+3. Read 1-2 existing API files to capture exact patterns for imports, typing, error handling, naming
+
+If project context is ambiguous → use conservative defaults and document all assumptions.
+
+---
+
+### Phase 4 — Conflict Detection
+
+Before generating code, check for:
+
+| Conflict | Action |
+|----------|--------|
+| `ENDPOINT_DUPLICATE` — endpoint already exists | Reuse if same, warn if different |
+| `FUNCTION_DUPLICATE` — function name conflicts | Warn, propose new name |
+| `TYPE_DUPLICATE` — type already defined | Extend or reuse existing |
+| `LOGIC_OVERLAP` — logic exists in another service | Consolidate, don't duplicate |
+| `IMPORT_CONFLICT` — import path conflicts | Resolve before generating |
+
+**P0 conflict → stop, report, wait for user decision before proceeding.**
+
+---
+
+### Phase 5 — Code Generation
+
+Generate the minimum necessary set for the task:
+
+#### TypeScript Types
+```typescript
+// Request types
+export interface CreateUserRequest {
+  name: string;
+  email: string;
+  role?: UserRole;
+}
+
+// Response types
+export interface CreateUserResponse {
+  id: string;
+  name: string;
+  email: string;
+  createdAt: string;
+}
+
+// Error types
+export interface ApiError {
+  code: string;
+  message: string;
+  details?: Record<string, unknown>;
+}
+```
+
+#### Service / API Layer
+```typescript
+// Thin layer: HTTP + mapping only. No UI, no business logic.
+export const createUser = async (
+  data: CreateUserRequest
+): Promise<CreateUserResponse> => {
+  const response = await apiClient.post<CreateUserResponse>('/users', data);
+  return response.data;
+};
+```
+
+#### Hook / Query (if project uses React Query)
+```typescript
+export const useCreateUser = () => {
+  return useMutation<CreateUserResponse, ApiError, CreateUserRequest>({
+    mutationFn: createUser,
+    onSuccess: () => {
+      queryClient.invalidateQueries({ queryKey: ['users'] });
+    },
+  });
+};
+```
+
+**If project uses Redux** → follow existing slice/thunk pattern.
+**If project uses Zustand** → follow existing store pattern.
+**If project uses Pinia/Vuex** → follow existing composable/action pattern.
+
+Do NOT mix patterns.
+
+---
+
+### Phase 6 — Special Case Handling
+
+#### File Upload (`multipart/form-data`)
+```typescript
+// Always use FormData — never send File object in JSON
+const formData = new FormData();
+formData.append('file', file);
+formData.append('name', name);
+await apiClient.post('/upload', formData, {
+  headers: { 'Content-Type': 'multipart/form-data' },
+});
+```
+
+#### File Download (binary response)
+```typescript
+const response = await apiClient.get('/export', { responseType: 'blob' });
+const url = URL.createObjectURL(response.data);
+const a = document.createElement('a');
+a.href = url;
+a.download = filename;
+a.click();
+URL.revokeObjectURL(url);
+```
+
+#### Pagination
+```typescript
+interface PaginatedResponse<T> {
+  items: T[];
+  total: number;
+  page: number;
+  limit: number;
+}
+// Implement consistently with existing project pagination pattern
+```
+
+#### Authentication
+- Follow existing auth mechanism (interceptor, header injection, cookie)
+- Never hardcode tokens or credentials
+- Refresh token logic belongs in the existing interceptor
+
+---
+
+### Phase 7 — Quality Validation
+
+Before marking as ready:
+
+- [ ] TypeScript strict — compiles clean, no `any` without justification
+- [ ] All functions/params have explicit types and return types
+- [ ] No unused imports, no debug code
+- [ ] Error handling complete (try/catch, `.catch`, fallback)
+- [ ] No hardcoded URLs, tokens, or secrets — use env vars
+- [ ] Naming matches project conventions
+- [ ] Reuses existing HTTP client, interceptors, and query client
+- [ ] JSDoc added for public API if project convention requires it
+- [ ] React: dependency arrays correct, cleanup present, no race conditions
+
+---
+
+## Decision Tree
+
+```
+Is required info complete?
+  ├── No  → Ask for missing info (auth, response schema, base URL)
+  └── Yes → Check for conflicts
+              ├── P0 conflict → Stop, report, wait for user decision
+              └── No P0 → Generate code following project patterns
+```
+
+```
+Does project have existing HTTP client?
+  ├── Yes → Extend it
+  └── No  → Create minimal axios/fetch wrapper following project style
+```
+
+```
+Does project use state management?
+  ├── React Query → useMutation / useQuery pattern
+  ├── Redux       → slice + thunk / RTK Query
+  ├── Zustand     → store action
+  ├── Pinia       → action in store
+  └── None        → Service function only
+```
+
+---
+
+## Output Format
+
+```
+📋 API Contract
+─────────────────────────────────────────────────
+Name:     [API name]
+Endpoint: [METHOD /path]
+Auth:     [type]
+Input:    [brief description]
+Output:   [brief description]
+
+🔍 Project Pattern Detected
+─────────────────────────────────────────────────
+HTTP client:    [axios instance at src/lib/axios.ts]
+State:          [React Query]
+Types path:     [src/types/]
+Service path:   [src/services/]
+Hook path:      [src/hooks/]
+
+⚠️  Assumptions
+─────────────────────────────────────────────────
+  • [Assumption 1]
+  • [Assumption 2]
+
+📁 Files Generated
+─────────────────────────────────────────────────
+  [NEW]    src/types/user.types.ts
+  [NEW]    src/services/user.service.ts
+  [NEW]    src/hooks/useCreateUser.ts
+  [EXTEND] src/services/index.ts
+
+🔗 Next steps:
+  → Import hook in your component
+  → Add env var: VITE_API_BASE_URL
+  → Test with: [example usage snippet]
+```
+
+---
+
+## Validation Checklist
+
+- [ ] All 7 phases completed
+- [ ] Input validated — no missing critical fields
+- [ ] Conflicts checked — none unresolved
+- [ ] Types generated and strict
+- [ ] Existing HTTP client reused
+- [ ] Existing state pattern followed
+- [ ] Special cases handled if applicable (upload, download, pagination, auth)
+- [ ] No hardcoded secrets
+- [ ] Output format produced with files listed
+
+---
+
+## Project Config Reference (`.api-config.json`)
+
+```json
+{
+  "framework": "React",
+  "httpClient": "axios",
+  "stateManagement": "react-query",
+  "typing": "typescript",
+  "conventions": {
+    "servicePath": "src/services/",
+    "typePath": "src/types/",
+    "hookPath": "src/hooks/",
+    "naming": "camelCase",
+    "fileNaming": "{name}.service.ts",
+    "typeFileNaming": "{Name}.types.ts",
+    "hookFileNaming": "use{Name}.ts"
+  },
+  "httpConfig": {
+    "baseURL": "process.env.VITE_API_URL",
+    "interceptor": "src/lib/axios.ts",
+    "authHeader": "Authorization",
+    "timeout": 30000
+  }
+}
+```
+
+---
+
+## Examples
+
+See `examples/` folder.