@neyugn/agent-kits 0.1.0

package/kits/coder/workflows/orchestrate.md

@@ -0,0 +1,243 @@
+---
+description: Coordinate multiple agents for complex tasks. Use for multi-perspective analysis, comprehensive reviews, or tasks requiring different domain expertise.
+---
+
+# /orchestrate - Multi-Agent Coordination Workflow
+
+$ARGUMENTS
+
+---
+
+## Trigger
+
+Use when user says: "orchestrate", "coordinate", "multi-agent", or `/orchestrate`
+
+## Agent
+
+Route to `orchestrator` agent
+
+---
+
+## 🔴 Critical Rules
+
+1. **Minimum 3 Agents** - Orchestration requires 3+ different specialists
+2. **2-Phase Execution** - Planning first, then implementation
+3. **Context Passing** - Always pass full context to subagents
+4. **User Approval** - Get approval before Phase 2
+
+---
+
+## Agent Selection Matrix
+
+| Task Type      | REQUIRED Agents (minimum)                                                 |
+| -------------- | ------------------------------------------------------------------------- |
+| **Web App**    | frontend-specialist, backend-specialist, test-engineer                    |
+| **API**        | backend-specialist, security-auditor, test-engineer                       |
+| **UI/Design**  | frontend-specialist, ux-researcher, performance-analyst                   |
+| **Database**   | database-specialist, backend-specialist, security-auditor                 |
+| **Full Stack** | project-planner, frontend-specialist, backend-specialist, devops-engineer |
+| **Debug**      | debugger, test-engineer, performance-analyst                              |
+| **Security**   | security-auditor, test-engineer, devops-engineer                          |
+
+---
+
+## Workflow
+
+### Phase 1: Planning (Sequential)
+
+Only these agents allowed during planning:
+
+| Agent             | Purpose              |
+| ----------------- | -------------------- |
+| `project-planner` | Create PLAN.md       |
+| `orchestrator`    | Coordinate and route |
+
+```markdown
+## Phase 1: Planning
+
+1. Analyze task domains
+2. Create docs/PLAN-{slug}.md
+3. Define agent assignments
+4. Wait for user approval
+```
+
+### ⏸️ CHECKPOINT: User Approval
+
+After plan is created, ask:
+
+```markdown
+✅ **Plan created:** `docs/PLAN-{slug}.md`
+
+Proceed with implementation? (Y/N)
+
+- Y: Start Phase 2 with multiple agents
+- N: Modify plan first
+```
+
+🔴 **DO NOT proceed to Phase 2 without explicit approval!**
+
+### Phase 2: Implementation (Parallel)
+
+After approval, invoke agents in parallel groups:
+
+| Group          | Agents                                  | Tasks                    |
+| -------------- | --------------------------------------- | ------------------------ |
+| **Foundation** | database-specialist, security-auditor   | Schema, security review  |
+| **Core**       | backend-specialist, frontend-specialist | API, UI implementation   |
+| **Polish**     | test-engineer, devops-engineer          | Tests, deployment config |
+
+### Phase 3: Verification
+
+Last agent runs verification:
+
+```bash
+# Run security scan
+python .agent/skills/security-fundamentals/scripts/security_scan.py .
+
+# Run linting
+pnpm lint
+
+# Run tests
+pnpm test
+```
+
+### Phase 4: Synthesis
+
+Combine all agent outputs into unified report.
+
+---
+
+## Context Passing Protocol (MANDATORY)
+
+When invoking ANY subagent, include:
+
+```markdown
+## CONTEXT for [Agent Name]
+
+**Original Request:** [Full user request]
+**Decisions Made:** [All answers to Socratic questions]
+**Previous Agent Work:** [Summary of completed work]
+**Current Plan:** [Reference to PLAN.md if exists]
+
+**YOUR TASK:** [Specific task for this agent]
+```
+
+⚠️ **VIOLATION:** Invoking agent without context = wrong assumptions!
+
+---
+
+## Output Format
+
+```markdown
+## 🎼 Orchestration Report
+
+### Task
+
+[Original task summary]
+
+### Agents Invoked (MINIMUM 3)
+
+| #   | Agent               | Focus Area         | Status |
+| --- | ------------------- | ------------------ | ------ |
+| 1   | project-planner     | Task breakdown     | ✅     |
+| 2   | frontend-specialist | UI implementation  | ✅     |
+| 3   | backend-specialist  | API implementation | ✅     |
+| 4   | test-engineer       | Verification       | ✅     |
+
+### Phase 1: Planning
+
+- [x] PLAN.md created
+- [x] User approved plan
+
+### Phase 2: Implementation
+
+- [x] Database schema designed
+- [x] API endpoints implemented
+- [x] UI components built
+- [x] Tests written
+
+### Phase 3: Verification
+
+- [x] Security scan passed
+- [x] Lint check passed
+- [x] All tests passing
+
+### Key Findings
+
+1. **project-planner**: Identified 12 tasks across 4 domains
+2. **frontend-specialist**: Created 8 reusable components
+3. **backend-specialist**: Implemented 15 API endpoints
+4. **test-engineer**: Added 45 test cases
+
+### Deliverables
+
+| Deliverable | Location              |
+| ----------- | --------------------- |
+| Plan        | `docs/PLAN-{slug}.md` |
+| API         | `src/api/`            |
+| UI          | `src/components/`     |
+| Tests       | `tests/`              |
+
+### Summary
+
+[One paragraph synthesis of all agent work]
+```
+
+---
+
+## Exit Gate
+
+Before completing orchestration, verify:
+
+| Check            | Requirement                    |
+| ---------------- | ------------------------------ |
+| ✅ Agent Count   | `invoked_agents >= 3`          |
+| ✅ Plan Approved | User said Y to proceed         |
+| ✅ Verification  | At least one scan/test ran     |
+| ✅ Report        | Orchestration report generated |
+
+If any check fails → DO NOT complete. Invoke more agents or run verification.
+
+---
+
+## Available Agents (19)
+
+### Tier 1: Master
+
+- `orchestrator`, `project-planner`, `debugger`
+
+### Tier 2: Development
+
+- `frontend-specialist`, `backend-specialist`, `mobile-developer`
+- `database-specialist`, `devops-engineer`
+
+### Tier 3: Quality
+
+- `security-auditor`, `code-reviewer`, `test-engineer`, `performance-analyst`
+
+### Tier 4: Domain
+
+- `realtime-specialist`, `multi-tenant-architect`, `queue-specialist`, `integration-specialist`
+
+### Tier 5: Support
+
+- `documentation-writer`, `i18n-specialist`, `ux-researcher`
+
+---
+
+## Exit Conditions
+
+- ✅ **Success:** 3+ agents invoked, plan approved, verification passed, report generated
+- ❌ **Failure:** Fewer than 3 agents, user rejected plan, verification failed
+- ⚠️ **Warning:** Completed but with verification warnings
+
+---
+
+## Usage Examples
+
+```
+/orchestrate build e-commerce site
+/orchestrate full security audit
+/orchestrate refactor with tests
+/orchestrate xây dựng API cho mobile app
+```

package/kits/coder/workflows/plan.md

@@ -0,0 +1,134 @@
+---
+description: Create project plan using project-planner agent. No code writing - only plan file generation.
+---
+
+# /plan - Project Planning Workflow
+
+$ARGUMENTS
+
+---
+
+## Trigger
+
+Use when user says: "plan", "lập kế hoạch", "create plan", "make a plan for", or `/plan`
+
+## Agent
+
+Route to `project-planner` agent
+
+---
+
+## 🔴 Critical Rules
+
+1. **NO CODE WRITING** - This workflow creates plan file ONLY
+2. **Use project-planner agent** - Follow 4-phase methodology
+3. **Socratic Gate** - Ask clarifying questions BEFORE planning
+4. **Dynamic Naming** - Plan file named based on task
+
+---
+
+## Workflow
+
+### Phase 1: Context Check
+
+Understand the user's request:
+
+- What is being planned?
+- Is this a new project or feature addition?
+- Any constraints mentioned?
+
+### Phase 2: Socratic Gate
+
+Ask minimum 3 clarifying questions:
+
+```markdown
+Before I create the plan, I need to understand:
+
+1. **Scope**: What are the main features/requirements?
+2. **Users**: Who is the target audience?
+3. **Tech**: Any technology preferences or constraints?
+```
+
+Wait for user response before proceeding.
+
+### Phase 3: Planning
+
+Using `project-planner` agent, create plan with:
+
+- Task breakdown (WBS)
+- Dependencies and ordering
+- Agent assignments
+- Verification checklist
+
+**Dynamic Naming Convention:**
+
+| Rule                        | Example                  |
+| --------------------------- | ------------------------ |
+| Extract 2-3 key words       | "e-commerce cart"        |
+| Lowercase, hyphen-separated | `ecommerce-cart`         |
+| Max 30 characters           | `PLAN-ecommerce-cart.md` |
+
+Output file: `docs/PLAN-{task-slug}.md`
+
+### Phase 4: Report
+
+Report to user:
+
+```markdown
+✅ **Plan Created:** `docs/PLAN-{slug}.md`
+
+**Contents:**
+
+- [ ] Requirements analysis
+- [ ] Task breakdown
+- [ ] Agent assignments
+- [ ] Verification checklist
+
+**Next Steps:**
+
+- Review the plan
+- Run `/create` to start implementation
+- Or modify plan manually
+```
+
+---
+
+## Expected Output
+
+| Deliverable            | Location                   |
+| ---------------------- | -------------------------- |
+| Project Plan           | `docs/PLAN-{task-slug}.md` |
+| Task Breakdown         | Inside plan file           |
+| Agent Assignments      | Inside plan file           |
+| Verification Checklist | Phase X in plan file       |
+
+---
+
+## Naming Examples
+
+| Request                           | Plan File                     |
+| --------------------------------- | ----------------------------- |
+| `/plan e-commerce site with cart` | `docs/PLAN-ecommerce-cart.md` |
+| `/plan mobile app for fitness`    | `docs/PLAN-fitness-app.md`    |
+| `/plan add dark mode feature`     | `docs/PLAN-dark-mode.md`      |
+| `/plan fix authentication bug`    | `docs/PLAN-auth-fix.md`       |
+| `/plan SaaS dashboard`            | `docs/PLAN-saas-dashboard.md` |
+
+---
+
+## Exit Conditions
+
+- ✅ **Success:** Plan file created in `docs/` directory
+- ❌ **Failure:** User cancels or requirements too vague after 3 attempts
+- ⚠️ **Warning:** Partial plan due to incomplete information
+
+---
+
+## Usage
+
+```
+/plan e-commerce site with cart
+/plan mobile app for fitness tracking
+/plan SaaS dashboard with analytics
+/plan thêm tính năng dark mode
+```

package/kits/coder/workflows/test.md

@@ -0,0 +1,237 @@
+---
+description: Test generation and test running command. Creates and executes tests for code.
+---
+
+# /test - Test Generation and Execution Workflow
+
+$ARGUMENTS
+
+---
+
+## Trigger
+
+Use when user says: "test", "kiểm tra", "write tests", "run tests", or `/test`
+
+## Agent
+
+Route to `test-engineer` agent
+
+---
+
+## Sub-commands
+
+| Command                | Description                        |
+| ---------------------- | ---------------------------------- |
+| `/test`                | Run all tests                      |
+| `/test [file/feature]` | Generate tests for specific target |
+| `/test coverage`       | Show test coverage report          |
+| `/test watch`          | Run tests in watch mode            |
+
+---
+
+## 🔴 Critical Rules
+
+1. **Test Pyramid** - Unit > Integration > E2E
+2. **AAA Pattern** - Arrange, Act, Assert
+3. **Behavior over Implementation** - Test what, not how
+4. **One Assertion per Test** - When practical
+
+---
+
+## Workflow
+
+### Phase 1: Analyze Target
+
+Determine what needs testing:
+
+```markdown
+## Test Analysis
+
+- **Target**: [File/Feature/Component]
+- **Type**: Unit / Integration / E2E
+- **Framework**: Jest / Vitest / Playwright / etc.
+- **Existing Tests**: [Count] tests found
+```
+
+### Phase 2: Generate Test Plan
+
+Create comprehensive test plan:
+
+```markdown
+## 🧪 Test Plan: [Target]
+
+| Test Case                     | Type        | Coverage   |
+| ----------------------------- | ----------- | ---------- |
+| Should create user            | Unit        | Happy path |
+| Should reject invalid email   | Unit        | Validation |
+| Should handle db error        | Unit        | Error case |
+| Should return 404 for missing | Integration | Edge case  |
+```
+
+Identify:
+
+- Happy path tests
+- Error cases
+- Edge cases
+- Integration points
+
+### Phase 3: Write Tests
+
+Generate tests using project's framework:
+
+```typescript
+describe("[Component/Service]", () => {
+  describe("[method/feature]", () => {
+    it("should [expected behavior]", async () => {
+      // Arrange
+      const input = {
+        /* test data */
+      };
+
+      // Act
+      const result = await subject.method(input);
+
+      // Assert
+      expect(result).toBeDefined();
+    });
+
+    it("should throw for [invalid case]", async () => {
+      // Arrange
+      const invalidInput = {
+        /* invalid data */
+      };
+
+      // Act & Assert
+      await expect(subject.method(invalidInput)).rejects.toThrow(
+        "[ExpectedError]",
+      );
+    });
+  });
+});
+```
+
+### Phase 4: Execute Tests
+
+Run the tests:
+
+```bash
+# Run all tests
+pnpm test
+
+# Run specific file
+pnpm test src/services/auth.test.ts
+
+# Run with coverage
+pnpm test --coverage
+```
+
+### Phase 5: Report
+
+Present results to user:
+
+```markdown
+## 🧪 Test Results
+
+### Summary
+
+✅ **15 tests** (14 passed, 1 failed)
+
+### By Status
+
+| Status    | Count | Files                      |
+| --------- | ----- | -------------------------- |
+| ✅ Passed | 14    | auth.test.ts, user.test.ts |
+| ❌ Failed | 1     | order.test.ts              |
+
+### Failed Tests
+
+❌ `should calculate total with discount`
+
+- Expected: 90
+- Received: 100
+- File: `order.test.ts:45`
+
+### Coverage
+
+| Metric     | Value |
+| ---------- | ----- |
+| Statements | 85%   |
+| Branches   | 72%   |
+| Functions  | 90%   |
+| Lines      | 84%   |
+
+### Next Steps
+
+- Fix failed test in `order.test.ts`
+- Consider adding tests for uncovered branches
+```
+
+---
+
+## Test Patterns
+
+### Unit Test (AAA Pattern)
+
+```typescript
+it("should return user by id", async () => {
+  // Arrange
+  const userId = "user-123";
+  mockDb.findOne.mockResolvedValue({ id: userId, name: "Test" });
+
+  // Act
+  const user = await userService.findById(userId);
+
+  // Assert
+  expect(user.id).toBe(userId);
+  expect(mockDb.findOne).toHaveBeenCalledWith({ id: userId });
+});
+```
+
+### Integration Test
+
+```typescript
+describe("POST /api/users", () => {
+  it("should create user and return 201", async () => {
+    const response = await request(app)
+      .post("/api/users")
+      .send({ name: "Test", email: "test@test.com" });
+
+    expect(response.status).toBe(201);
+    expect(response.body.id).toBeDefined();
+  });
+});
+```
+
+### E2E Test (Playwright)
+
+```typescript
+test("user can login and see dashboard", async ({ page }) => {
+  await page.goto("/login");
+  await page.fill('[name="email"]', "test@test.com");
+  await page.fill('[name="password"]', "password123");
+  await page.click('button[type="submit"]');
+
+  await expect(page).toHaveURL("/dashboard");
+  await expect(page.locator("h1")).toContainText("Welcome");
+});
+```
+
+---
+
+## Exit Conditions
+
+- ✅ **Success:** All tests passing, coverage targets met
+- ❌ **Failure:** Tests cannot run due to syntax/config errors
+- ⚠️ **Warning:** Tests run but some fail, coverage below target
+
+---
+
+## Usage Examples
+
+```
+/test
+/test src/services/auth.service.ts
+/test user registration flow
+/test coverage
+/test fix failed tests
+```

package/kits/coder/workflows/ui-ux-pro-max.md

@@ -0,0 +1,109 @@
+---
+description: Plan and implement UI/UX with design intelligence. Generates design system, style guide, and implementation checklist.
+---
+
+# /ui-ux-pro-max Workflow
+
+> UI/UX Design Intelligence workflow with BM25-powered style matching.
+
+## When to Use
+
+- Designing new landing pages, dashboards, or web apps
+- Choosing color palettes, typography, and style
+- Building UI with specific style requirements
+- Need design system recommendations for a product type
+
+## Workflow Steps
+
+### Phase 1: Requirements Analysis
+
+1. **Extract from user request:**
+   - Product type (SaaS, e-commerce, portfolio, dashboard, etc.)
+   - Style keywords (minimal, playful, professional, dark mode, etc.)
+   - Industry (healthcare, fintech, gaming, education, etc.)
+   - Tech stack (React, Vue, Next.js - default to `html-tailwind`)
+
+### Phase 2: Generate Design System (REQUIRED)
+
+2. **Run design system generator:**
+
+```bash
+python3 .agent/skills/ui-ux-pro-max/scripts/search.py "<product_type> <industry> <keywords>" --design-system -p "Project Name"
+```
+
+**Example:**
+
+```bash
+python3 .agent/skills/ui-ux-pro-max/scripts/search.py "beauty spa wellness" --design-system -p "Serenity Spa"
+```
+
+### Phase 3: Detailed Searches (Optional)
+
+3. **Get additional details if needed:**
+
+| Need                  | Command                                 |
+| --------------------- | --------------------------------------- |
+| More style options    | `--domain style "glassmorphism dark"`   |
+| Chart recommendations | `--domain chart "real-time dashboard"`  |
+| UX guidelines         | `--domain ux "animation accessibility"` |
+| Alternative fonts     | `--domain typography "elegant luxury"`  |
+| Landing structure     | `--domain landing "hero social-proof"`  |
+
+### Phase 4: Stack Guidelines
+
+4. **Get stack-specific best practices:**
+
+```bash
+python3 .agent/skills/ui-ux-pro-max/scripts/search.py "<keywords>" --stack html-tailwind
+```
+
+Available stacks: `html-tailwind`, `react`, `nextjs`, `vue`, `svelte`, `swiftui`, `react-native`, `flutter`, `shadcn`
+
+### Phase 5: Implementation
+
+5. **Build with design system:**
+   - Apply colors from design system
+   - Use recommended typography (Google Fonts)
+   - Follow layout pattern
+   - Implement key effects
+   - Avoid anti-patterns
+
+### Phase 6: Pre-Delivery Checklist
+
+6. **Verify before delivery:**
+   - [ ] No emojis as icons (use SVG: Heroicons/Lucide)
+   - [ ] cursor-pointer on all clickable elements
+   - [ ] Hover states with smooth transitions (150-300ms)
+   - [ ] Light mode: text contrast 4.5:1 minimum
+   - [ ] Focus states visible for keyboard nav
+   - [ ] prefers-reduced-motion respected
+   - [ ] Responsive: 375px, 768px, 1024px, 1440px
+
+## Available Domains
+
+| Domain       | Use For                              |
+| ------------ | ------------------------------------ |
+| `product`    | Product type recommendations         |
+| `style`      | UI styles, colors, effects           |
+| `typography` | Font pairings, Google Fonts          |
+| `color`      | Color palettes by product type       |
+| `landing`    | Page structure, CTA strategies       |
+| `chart`      | Chart types, library recommendations |
+| `ux`         | Best practices, anti-patterns        |
+| `react`      | React/Next.js performance            |
+| `web`        | Web interface guidelines             |
+
+## Critical Rules
+
+1. **Always start with `--design-system`** for comprehensive recommendations
+2. **Default stack is `html-tailwind`** unless user specifies otherwise
+3. **Follow Pre-Delivery Checklist** before delivering any UI code
+4. **Avoid Purple Ban** - Never use purple/violet as primary unless requested
+5. **No emojis as icons** - Always use SVG icons (Heroicons, Lucide)
+
+## Exit Conditions
+
+- ✅ Design system generated and applied
+- ✅ UI implementation matches design system
+- ✅ Pre-delivery checklist passed
+- ✅ Responsive design verified