[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CQYT7A1G4CPQTZKXR5TCK9":3,"skill-same:01M6CQYT7A1G4CPQTZKXR5TCK9":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6CQYT7A1G4CPQTZKXR5TCK9","test-plan-generator",null,"Generate comprehensive E2E test plans from PRDs, task lists, or descriptions with environment-aware prerequisites and issue tracking.","dundas\u002Fagentbootup-public","dundas","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F627426?v=4","01M6CQVP2KHXEP7JH9WKKF59S7","David K. Dundas","01M6CQVP76D48NCMMXYDK9CBA8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftest-plan-generator\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[27,28,29,30,31,32,33,34,35,36,37,38],"test","test plan","test plan generator","plan","generate","e2e","quality","tracking","environment","e2e test","issue","task","2026-11-10 10:12:30",false,"---\nname: test-plan-generator\ndescription: Generate comprehensive E2E test plans from PRDs, task lists, or descriptions with environment-aware prerequisites and issue tracking.\ncategory: quality\n---\n\n# Test Plan Generator\n\n## Goal\nCreate a detailed, executable End-to-End Test Plan that an AI agent or developer can follow to verify a feature works correctly, track issues, and iterate to completion.\n\n## Input Sources (Auto-Detect)\n1. **PRD File** - Generate test plan from `\u002Ftasks\u002F[n]-prd-*.md`\n2. **Task List** - Generate test plan from `\u002Ftasks\u002Ftasks-*.md`\n3. **Text Description** - Generate from user's verbal description\n\n## Output\n- **Format:** Markdown (`.md`)\n- **Location:** `\u002Ftasks\u002F`\n- **Filename:** `testplan-[source].md`\n  - From PRD: `testplan-0001-prd-user-auth.md`\n  - From tasks: `testplan-tasks-0001-prd-user-auth.md`\n  - From description: `testplan-[feature-slug].md`\n\n---\n\n## Process\n\n### Phase 1: Environment & Context Gathering\n\n1. **Identify Input Source**\n   - Check if user provided a PRD file, task list, or description\n   - If PRD\u002Ftask list: read and analyze the document\n   - If description: capture requirements\n\n2. **GATE: Environment Declaration (REQUIRED)**\n   Ask the user explicitly:\n   ```\n   Which environment is this test plan for?\n   a) Local\u002FDevelopment\n   b) Staging\n   c) Production\n\n   Please confirm your environment before I proceed.\n   ```\n   **Do NOT proceed without explicit confirmation.**\n\n3. **If Production Environment:**\n   - **BLOCKING GATE:** Require deployment verification\n   ```\n   PRODUCTION TEST PLAN REQUIREMENTS:\n\n   Before I generate this test plan, please confirm:\n   1. What is the current deployed version\u002Fcommit?\n   2. When was the last deployment?\n   3. How do you deploy updates? (document the process)\n\n   I need explicit confirmation that the feature under test\n   is deployed before proceeding.\n   ```\n   - Document deployment process in the test plan\n   - Include rollback procedures\n\n4. **Codebase Analysis**\n   - Scan project structure to identify:\n     - Service directories (backend, frontend, microservices)\n     - Package managers (`package.json`, `bun.lockb`, etc.)\n     - Existing scripts (`npm run dev`, `bun run dev`, etc.)\n     - Environment files (`.env.example`, `.env.local`)\n     - Existing test infrastructure (Jest, Vitest, Playwright, etc.)\n   - **Normalize commands to actual repo structure**\n\n5. **Service Discovery**\n   - Identify all services that need to run\n   - Determine ports from config files or `.env.example`\n   - Generate health check commands for each service\n\n6. **GATE: Test Account Strategy**\n   Ask the user:\n   ```\n   How should test accounts be handled?\n   a) Use existing test account (provide credentials location)\n   b) Create new account via UI signup flow\n   c) Create new account via CLI\u002Fseed script\n   d) Create new account via direct database insert (dev only)\n\n   Where are credentials stored for this project?\n   (e.g., .env.local, 1Password, AWS Secrets Manager, etc.)\n   ```\n   Document the chosen approach in the test plan.\n\n### Phase 2: Test Plan Generation\n\n7. **Generate Prerequisites Section**\n   - List all services with start commands\n   - Include health check curl\u002Ffetch commands\n   - Document required environment variables\n   - Document test account strategy and credential locations\n\n8. **Map Full User Journey**\n   Before writing individual test cases, map the complete user journey:\n\n   ```\n   USER JOURNEY MAP (customize per feature):\n\n   1. AUTHENTICATION\n      └─ Login \u002F Session restoration \u002F Token refresh\n\n   2. INITIAL STATE\n      └─ User data loading\n      └─ Permissions\u002Froles loaded\n      └─ UI renders correctly\n\n   3. NAVIGATION\n      └─ Navigate to feature\n      └─ Required data fetched\n      └─ Loading states handled\n\n   4. CORE FUNCTIONALITY\n      └─ Primary user action (e.g., send message, create item)\n      └─ Secondary actions\n      └─ State updates correctly\n\n   5. DATA VERIFICATION\n      └─ Changes persisted\n      └─ UI reflects changes\n      └─ Other users see changes (if applicable)\n\n   6. ERROR SCENARIOS\n      └─ Invalid input handling\n      └─ Network failure handling\n      └─ Permission denied handling\n\n   7. EDGE CASES\n      └─ Empty states\n      └─ Maximum limits\n      └─ Concurrent access\n\n   8. CLEANUP (if needed)\n      └─ Logout\n      └─ Session cleanup\n      └─ Test data cleanup\n   ```\n\n   **AI Action:** Analyze the PRD, task list, or codebase to identify:\n   - Authentication flow (how users login)\n   - Data loading patterns (what loads on startup)\n   - Navigation paths (how to reach the feature)\n   - Core actions (what the feature does)\n   - Persistence layer (where data is saved)\n\n   Then **propose** the journey map to the user:\n   > \"Based on my analysis, here's the user journey I'll test. Please confirm or correct:\n   > 1. Login via [method]\n   > 2. User profile loads from [API]\n   > 3. Navigate to [feature path]\n   > 4. [Core action]\n   > 5. Verify [persistence]\n   > ...\"\n\n   Wait for user confirmation before proceeding.\n\n9. **Generate Test Cases**\n   - Create test cases that follow the user journey map\n   - Each test case includes:\n     - Clear steps (numbered)\n     - Expected outcomes for each step\n     - Verification commands where applicable\n   - Ensure NO GAPS in the journey (every step from auth to completion)\n\n10. **Generate Troubleshooting Section**\n    - Common failure modes and solutions\n    - Log file locations\n    - Debug commands\n    - Authentication\u002Fcredential issues\n\n11. **Generate Success Criteria**\n    - Checklist format for \"done\" state\n    - All acceptance criteria from PRD\u002Fdescription\n\n12. **Generate Issue Tracking Template**\n    - Run log table format\n    - Issue note template\n    - Fix loop process\n\n### Phase 3: Review & Save\n\n13. **Present draft to user for review**\n14. **Save to `\u002Ftasks\u002Ftestplan-[source].md`**\n\n---\n\n## Output Format\n\n```markdown\n# End-to-End Test Plan: [Feature Name]\n\n**Source:** `[PRD\u002FTask List path or \"User Description\"]`\n**Generated:** YYYY-MM-DD\n**Environment:** Local | Staging | Production\n\n---\n\n## Environment Declaration\n\n**Target Environment:** [Local\u002FStaging\u002FProduction]\n**Confirmed by:** [User confirmation timestamp or note]\n\n### If Production\n- **Deployed Version:** [commit hash or version]\n- **Last Deployment:** [date\u002Ftime]\n- **Deployment Process:**\n  ```bash\n  # How to deploy updates\n  [deployment commands]\n  ```\n- **Rollback Process:**\n  ```bash\n  # How to rollback if needed\n  [rollback commands]\n  ```\n\n---\n\n## Prerequisites\n\n### 1. Services Required\n\n| Service | Directory | Port | Start Command |\n|---------|-----------|------|---------------|\n| Backend API | `.\u002Fbackend` | 3012 | `PORT=3012 bun run dev` |\n| Frontend | `.\u002Ffrontend` | 3007 | `PORT=3007 npm run dev` |\n| [Service N] | `.\u002Fpath` | XXXX | `command` |\n\n### 2. Health Checks\n\nVerify all services are healthy before testing:\n\n```bash\n# Backend API\ncurl -f http:\u002F\u002Flocalhost:3012\u002Fhealth | jq '.status'\n# Expected: \"healthy\"\n\n# Frontend\ncurl -f http:\u002F\u002Flocalhost:3007 -o \u002Fdev\u002Fnull -w \"%{http_code}\"\n# Expected: 200\n\n# [Service N]\ncurl -f http:\u002F\u002Flocalhost:XXXX\u002Fhealth\n```\n\n### 3. Environment Setup\n\n⚠️ **SECURITY WARNING**\n- **Never commit credentials to version control**\n- Ensure `.env`, `.env.local`, `.env.*.local` are in `.gitignore`\n- Use secure storage for sensitive values (1Password, AWS Secrets Manager, etc.)\n- Production credentials should NEVER be in local `.env` files\n\n```bash\n# Copy environment template\ncp .env.example .env.local\n\n# Required variables (set these):\n# - DATABASE_URL=...\n# - API_KEY=...\n\n# Verify .gitignore includes environment files\ngrep -q \"\\.env\" .gitignore || echo \"⚠️  WARNING: .env not in .gitignore!\"\n```\n\n### 4. Test Accounts & Credentials\n\n⚠️ **CREDENTIAL SECURITY**\n- **NEVER store credentials in files that are committed to git**\n- **NEVER hardcode passwords in test scripts**\n- Use environment variables or secure vaults\n- Review `.gitignore` to ensure credential files are excluded\n\n#### Credential Storage\n| Credential Type | Location | Notes |\n|-----------------|----------|-------|\n| Local dev accounts | `.env.local` (git-ignored) | **MUST be in .gitignore** |\n| Staging accounts | Team password manager \u002F secrets vault | Shared test accounts |\n| Production accounts | Secure vault (1Password, AWS Secrets, etc.) | Requires explicit access, NEVER local |\n\n#### Account Strategy\n**Choose ONE approach and document it:**\n\n**Option A: Use Existing Test Account**\n- Account email: `[existing-test@example.com]`\n- Password location: `[where to find it - e.g., \"1Password > Team Vault > Staging Accounts\"]`\n- Account permissions: `[admin\u002Fuser\u002Fspecific roles needed]`\n\n**Option B: Create New Test Account**\n- **Via UI signup:**\n  1. Navigate to `http:\u002F\u002Flocalhost:3007\u002Fsignup`\n  2. Register with email: `test-[feature]-[date]@example.com`\n  3. [Complete verification if required]\n\n- **Via CLI\u002Fseed script:**\n  ```bash\n  # Create test user via CLI\n  bun run db:seed --user test@example.com --password testpass123\n\n  # Or via API\n  curl -X POST http:\u002F\u002Flocalhost:3012\u002Fapi\u002Fauth\u002Fregister \\\n    -H \"Content-Type: application\u002Fjson\" \\\n    -d '{\"email\": \"test@example.com\", \"password\": \"testpass123\"}'\n  ```\n\n- **Via database directly (dev only):**\n  ```bash\n  # Insert test user (adjust for your DB)\n  bun run db:query \"INSERT INTO users (email, password_hash) VALUES (...)\"\n  ```\n\n#### Credential Checklist\n- [ ] Test account credentials documented (not committed to git)\n- [ ] Account has required permissions\u002Froles for testing\n- [ ] Password meets minimum requirements (if creating new)\n- [ ] Multi-factor auth handled (disabled for test account, or codes available)\n\n### 5. Test Data \u002F Fixtures\n\n- [ ] Database seeded: `bun run db:seed`\n- [ ] Required test records exist (orders, products, etc.)\n- [ ] File uploads\u002Fassets available if needed\n- [ ] [Other data prerequisites]\n\n---\n\n## User Journey Map\n\nBefore executing individual tests, understand the full user flow:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│ 1. AUTHENTICATION                                           │\n│    └─ [Login method: email\u002FOAuth\u002FSSO]                       │\n│    └─ [Session handling: token\u002Fcookie]                      │\n├─────────────────────────────────────────────────────────────┤\n│ 2. INITIAL STATE                                            │\n│    └─ [User profile loads]                                  │\n│    └─ [Permissions\u002Froles verified]                          │\n│    └─ [Dashboard\u002Fhome renders]                              │\n├─────────────────────────────────────────────────────────────┤\n│ 3. NAVIGATION                                               │\n│    └─ [Navigate to: \u002Fpath\u002Fto\u002Ffeature]                       │\n│    └─ [Required data fetched: API calls]                    │\n│    └─ [Loading states: spinners\u002Fskeletons]                  │\n├─────────────────────────────────────────────────────────────┤\n│ 4. CORE FUNCTIONALITY                                       │\n│    └─ [Primary action: e.g., send message]                  │\n│    └─ [Secondary actions: e.g., attach file]                │\n│    └─ [State updates: UI reflects changes]                  │\n├─────────────────────────────────────────────────────────────┤\n│ 5. DATA VERIFICATION                                        │\n│    └─ [Changes persisted to database]                       │\n│    └─ [UI shows updated state]                              │\n│    └─ [Other users see changes: if real-time]               │\n├─────────────────────────────────────────────────────────────┤\n│ 6. ERROR SCENARIOS                                          │\n│    └─ [Invalid input: validation messages]                  │\n│    └─ [Network failure: retry\u002Ferror UI]                     │\n│    └─ [Permission denied: proper handling]                  │\n├─────────────────────────────────────────────────────────────┤\n│ 7. EDGE CASES                                               │\n│    └─ [Empty state: first-time user]                        │\n│    └─ [Maximum limits: char limits, file size]              │\n│    └─ [Concurrent access: if applicable]                    │\n├─────────────────────────────────────────────────────────────┤\n│ 8. CLEANUP                                                  │\n│    └─ [Logout: session cleared]                             │\n│    └─ [Test data: cleaned or noted for manual cleanup]      │\n└─────────────────────────────────────────────────────────────┘\n```\n\n**Coverage Checklist:**\n- [ ] All journey stages have at least one test case\n- [ ] No gaps between stages (each flows into next)\n- [ ] Both happy path and error paths covered\n\n---\n\n## Test Cases\n\n### Test 1: [Scenario Name]\n\n**Purpose:** [What this test verifies]\n\n#### Steps\n\n1. **[Action]**\n   - Navigate to `http:\u002F\u002Flocalhost:3007\u002Fpath`\n   - **Expected:** [What should happen]\n\n2. **[Action]**\n   - [Detailed instruction]\n   - **Expected:** [Outcome]\n   - **Verify:**\n     ```bash\n     # Optional verification command\n     curl http:\u002F\u002Flocalhost:3012\u002Fapi\u002Fendpoint | jq '.field'\n     ```\n\n3. **[Continue numbered steps...]**\n\n#### Success Criteria\n- [ ] [Criterion 1]\n- [ ] [Criterion 2]\n\n---\n\n### Test 2: [Scenario Name]\n\n[Same structure as Test 1...]\n\n---\n\n## Troubleshooting\n\n### Service Won't Start\n\n**Symptom:** `[error message]`\n\n**Check:**\n1. Port already in use: `lsof -i :3012`\n2. Missing dependencies: `bun install`\n3. Environment variables: Verify `.env` file exists\n\n**Solution:**\n```bash\n# Kill existing process\nkill $(lsof -t -i :3012)\n\n# Restart service\nbun run dev\n```\n\n### Authentication\u002FLogin Issues\n\n**Symptom:** Cannot login, \"Invalid credentials\", or session expired\n\n**Check:**\n1. Verify account exists: Check database or user management\n2. Verify password: Confirm from credential storage location\n3. Check token expiry: JWT\u002Fsession may need refresh\n4. Check MFA: Disable for test account or have codes ready\n\n**Solution:**\n```bash\n# Reset password via CLI (if available)\nbun run auth:reset-password --email test@example.com\n\n# Check user exists in database\nbun run db:query \"SELECT * FROM users WHERE email = 'test@example.com'\"\n\n# Clear session\u002Fcookies and re-login\n# [Browser: DevTools > Application > Clear Storage]\n```\n\n### [Issue Category N]\n\n**Symptom:** [description]\n**Check:** [diagnostic steps]\n**Solution:** [fix]\n\n---\n\n## Success Criteria\n\n### Feature Acceptance\n- [ ] [Criterion from PRD\u002Fdescription]\n- [ ] [Criterion from PRD\u002Fdescription]\n- [ ] All test cases pass\n\n### Quality Gates\n- [ ] No console errors in browser\n- [ ] API responses \u003C 500ms\n- [ ] All health checks green\n\n---\n\n## E2E Completion Criteria\n\n### The Rule\n> **If an issue would happen in production, it is NOT \"unrelated\" - fix it NOW.**\n\n### Completion Checklist\n- [ ] Happy path works end-to-end\n- [ ] Error scenarios fail gracefully\n- [ ] Edge cases handled correctly\n- [ ] **ALL encountered issues fixed** (none deferred as \"out of scope\")\n- [ ] Re-validated after each fix\n- [ ] Production-ready confidence achieved\n\n### Fix-In-Place Protocol\nWhen ANY issue is encountered during testing:\n1. STOP - Don't mark test as passing\n2. ASSESS - Would this happen in production?\n3. FIX - If yes, fix it now (not later, not \"separate task\")\n4. RE-VALIDATE - Re-run E2E after fix\n5. REPEAT - Until full flow works\n\n### Sign-Off\n- [ ] All issues encountered during E2E testing have been addressed\n- [ ] No issues deferred as \"architectural\" or \"unrelated\"\n- [ ] Tester confirms: \"This would work in production\"\n\n**Signed:** _____________ **Date:** _____________\n\n---\n\n## Issue Tracking\n\n### Run Log Template\n\n| Step | Expected | Actual | Status | Logs\u002FArtifacts | Fix Commit |\n|------|----------|--------|--------|----------------|------------|\n| Test 1.1 | Page loads | | | | |\n| Test 1.2 | Form submits | | | | |\n\n### Issue Note Template\n\nWhen a test fails, create an issue note:\n\n```markdown\n## Issue: [Brief description]\n\n**Test Case:** [Test N, Step M]\n**Environment:** [Local\u002FStaging\u002FProduction]\n\n### Repro Steps\n1. [Exact commands to reproduce]\n\n### Error Output\n\\`\\`\\`\n[Paste error logs]\n\\`\\`\\`\n\n### Root Cause Hypothesis\n[What you think is wrong]\n\n### Proposed Fix\n[How to fix it]\n\n### Done When\n[What proves it's fixed]\n```\n\n### Fix Loop Process\n\nFor each failing test:\n\n1. **Reproduce** in smallest scope (single test\u002Fendpoint)\n2. **Add regression test** where appropriate:\n   - Backend: `__tests__\u002F` or `*.test.ts`\n   - Frontend: `*.test.tsx`\n   - E2E: Playwright spec\n3. **Implement fix**\n4. **Rerun failing test** to verify\n5. **Rerun full suite** for confidence\n6. **Update run log** with fix commit\n\n---\n\n## Next Steps\n\nAfter all tests pass:\n\n1. [ ] Document any discovered edge cases\n2. [ ] Update test plan if requirements changed\n3. [ ] Consider automation opportunities\n4. [ ] [Feature-specific follow-ups]\n\n---\n\n*Test plan generated YYYY-MM-DD by test-plan-generator skill*\n```\n\n---\n\n## Interaction Model\n\n1. **Input Detection** - Auto-detect source type\n2. **Environment Gate** - ALWAYS ask explicitly, never assume\n3. **Production Gate** - BLOCKING confirmation required\n4. **Draft Review** - Present for user feedback before saving\n5. **Iterative Refinement** - Update based on user corrections\n\n## Key Principles\n\n- **Normalize to actual repo** - Don't assume structure, discover it\n- **Executable commands** - Every health check, every start command should be copy-pasteable\n- **Issue tracking built-in** - Run log table is mandatory\n- **Fix loop defined** - Clear process for handling failures\n- **Environment-aware** - Different rigor for prod vs local\n\n---\n\n## CRITICAL: E2E Completion Criteria\n\n**This section MUST be included in every generated test plan.**\n\n### The Production Reality Rule\n\n> **If an issue would happen in production, it is NOT \"unrelated\" - it MUST be fixed.**\n\nWhen executing E2E tests, you will encounter issues. The natural instinct is to categorize them:\n- \"This is a bug in our feature\" → Fix it\n- \"This is an architecture issue\" → Defer it\n- \"This is unrelated to what we're testing\" → Ignore it\n\n**THIS IS WRONG.** In E2E testing, there is no such thing as an \"unrelated\" issue if it blocks the production flow.\n\n### Anti-Patterns (DO NOT DO)\n\n```\n❌ \"We've fixed the login issue, but there's an architecture problem\n    with the session handling that's unrelated to our feature.\"\n\n❌ \"The feature works, but the database connection pooling is a\n    separate infrastructure concern.\"\n\n❌ \"This test passes, but I noticed the API rate limiting would\n    cause issues - that's out of scope for this task.\"\n\n❌ \"The happy path works. The error handling issue is a different\n    story that should be addressed separately.\"\n```\n\n### Correct Behavior (DO THIS)\n\n```\n✅ \"The login works, but I discovered a session handling issue that\n    would affect production users. Fixing it now before proceeding.\"\n\n✅ \"While testing, I found the database connection pooling causes\n    timeouts under load. This would happen in production, so I'm\n    addressing it as part of this E2E validation.\"\n\n✅ \"The feature works but would hit API rate limits in production.\n    Implementing proper rate limiting before marking complete.\"\n\n✅ \"The happy path works. Now testing error scenarios and fixing\n    any issues found before marking the E2E test as complete.\"\n```\n\n### The Completion Standard\n\nA test is **NOT COMPLETE** until:\n\n| Criterion | Question to Ask |\n|-----------|-----------------|\n| **Happy path works** | Does the primary user flow succeed? |\n| **Error paths work** | Do error scenarios fail gracefully? |\n| **Edge cases handled** | Do boundary conditions behave correctly? |\n| **No blocking issues** | Would a real user encounter any problems? |\n| **Production-ready** | Could we deploy this right now with confidence? |\n\n### The Fix-In-Place Protocol\n\nWhen you encounter ANY issue during E2E testing:\n\n1. **STOP** - Don't mark the current test as passing\n2. **ASSESS** - Would this issue occur in production?\n3. **If YES → FIX IT NOW**\n   - Don't defer to a \"future task\"\n   - Don't categorize as \"out of scope\"\n   - Don't label as \"architecture issue\" and move on\n4. **RE-VALIDATE** - After fixing, re-run the E2E test\n5. **REPEAT** - Continue until the full flow works without issues\n\n### Including This in Generated Test Plans\n\nEvery test plan generated by this skill MUST include an \"E2E Completion Criteria\" section that:\n\n1. Lists the specific completion criteria for this feature\n2. Explicitly states the \"no unrelated issues\" rule\n3. Includes the fix-in-place protocol\n4. Requires sign-off that all encountered issues were addressed\n\n---\n\n## References\n- See `reference.md` for template structure details\n- See `.claude\u002Fagents\u002Ftdd-developer.md` for test implementation\n","# Test Plan Generator\n\n## Goal\nCreate a detailed, executable End-to-End Test Plan that an AI agent or developer can follow to verify a feature works correctly, track issues, and iterate to completion.\n\n## Input Sources (Auto-Detect)\n1. **PRD File** - Generate test plan from `\u002Ftasks\u002F[n]-prd-*.md`\n2. **Task List** - Generate test plan from `\u002Ftasks\u002Ftasks-*.md`\n3. **Text Description** - Generate from user's verbal description\n\n## Output\n- **Format:** Markdown (`.md`)\n- **Location:** `\u002Ftasks\u002F`\n- **Filename:** `testplan-[source].md`\n  - From PRD: `testplan-0001-prd-user-auth.md`\n  - From tasks: `testplan-tasks-0001-prd-user-auth.md`\n  - From description: `testplan-[feature-slug].md`\n\n---\n\n## Process\n\n### Phase 1: Environment & Context Gathering\n\n1. **Identify Input Source**\n   - Check if user provided a PRD file, task list, or description\n   - If PRD\u002Ftask list: read and analyze the document\n   - If description: capture requirements\n\n2. **GATE: Environment Declaration (REQUIRED)**\n   Ask the user explicitly:\n   ```\n   Which environment is this test plan for?\n   a) Local\u002FDevelopment\n   b) Staging\n   c) Production\n\n   Please confirm your environment before I proceed.\n   ```\n   **Do NOT proceed without explicit confirmation.**\n\n3. **If Production Environment:**\n   - **BLOCKING GATE:** Require deployment verification\n   ```\n   PRODUCTION TEST PLAN REQUIREMENTS:\n\n   Before I generate this test plan, please confirm:\n   1. What is the current deployed version\u002Fcommit?\n   2. When was the last deployment?\n   3. How do you deploy updates? (document the process)\n\n   I need explicit confirmation that the feature under test\n   is deployed before proceeding.\n   ```\n   - Document deployment process in the test plan\n   - Include rollback procedures\n\n4. **Codebase Analysis**\n   - Scan project structure to identify:\n     - Service directories (backend, frontend, microservices)\n     - Package managers (`package.json`, `bun.lockb`, etc.)\n     - Existing scripts (`npm run dev`, `bun run dev`, etc.)\n     - Environment files (`.env.example`, `.env.local`)\n     - Existing test infrastructure (Jest, Vitest, Playwright, etc.)\n   - **Normalize commands to actual repo structure**\n\n5. **Service Discovery**\n   - Identify all services that need to run\n   - Determine ports from config files or `.env.example`\n   - Generate health check commands for each service\n\n6. **GATE: Test Account Strategy**\n   Ask the user:\n   ```\n   How should test accounts be handled?\n   a) Use existing test account (provide credentials location)\n   b) Create new account via UI signup flow\n   c) Create new account via CLI\u002Fseed script\n   d) Create new account via direct database insert (dev only)\n\n   Where are credentials stored for this project?\n   (e.g., .env.local, 1Password, AWS Secrets Manager, etc.)\n   ```\n   Document the chosen approach in the test plan.\n\n### Phase 2: Test Plan Generation\n\n7. **Generate Prerequisites Section**\n   - List all services with start commands\n   - Include health check curl\u002Ffetch commands\n   - Document required environment variables\n   - Document test account strategy and credential locations\n\n8. **Map Full User Journey**\n   Before writing individual test cases, map the complete user journey:\n\n   ```\n   USER JOURNEY MAP (customize per feature):\n\n   1. AUTHENTICATION\n      └─ Login \u002F Session restoration \u002F Token refresh\n\n   2. INITIAL STATE\n      └─ User data loading\n      └─ Permissions\u002Froles loaded\n      └─ UI renders correctly\n\n   3. NAVIGATION\n      └─ Navigate to feature\n      └─ Required data fetched\n      └─ Loading states handled\n\n   4. CORE FUNCTIONALITY\n      └─ Primary user action (e.g., send message, create item)\n      └─ Secondary actions\n      └─ State updates correctly\n\n   5. DATA VERIFICATION\n      └─ Changes persisted\n      └─ UI reflects changes\n      └─ Other users see changes (if applicable)\n\n   6. ERROR SCENARIOS\n      └─ Invalid input handling\n      └─ Network failure handling\n      └─ Permission denied handling\n\n   7. EDGE CASES\n      └─ Empty states\n      └─ Maximum limits\n      └─ Concurrent access\n\n   8. CLEANUP (if needed)\n      └─ Logout\n      └─ Session cleanup\n      └─ Test data cleanup\n   ```\n\n   **AI Action:** Analyze the PRD, task list, or codebase to identify:\n   - Authentication flow (how users login)\n   - Data loading patterns (what loads on startup)\n   - Navigation paths (how to reach the feature)\n   - Core actions (what the feature does)\n   - Persistence layer (where data is saved)\n\n   Then **propose** the journey map to the user:\n   > \"Based on my analysis, here's the user journey I'll test. Please confirm or correct:\n   > 1. Login via [method]\n   > 2. User profile loads from [API]\n   > 3. Navigate to [feature path]\n   > 4. [Core action]\n   > 5. Verify [persistence]\n   > ...\"\n\n   Wait for user confirmation before proceeding.\n\n9. **Generate Test Cases**\n   - Create test cases that follow the user journey map\n   - Each test case includes:\n     - Clear steps (numbered)\n     - Expected outcomes for each step\n     - Verification commands where applicable\n   - Ensure NO GAPS in the journey (every step from auth to completion)\n\n10. **Generate Troubleshooting Section**\n    - Common failure modes and solutions\n    - Log file locations\n    - Debug commands\n    - Authentication\u002Fcredential issues\n\n11. **Generate Success Criteria**\n    - Checklist format for \"done\" state\n    - All acceptance criteria from PRD\u002Fdescription\n\n12. **Generate Issue Tracking Template**\n    - Run log table format\n    - Issue note template\n    - Fix loop process\n\n### Phase 3: Review & Save\n\n13. **Present draft to user for review**\n14. **Save to `\u002Ftasks\u002Ftestplan-[source].md`**\n\n---\n\n## Output Format\n\n```markdown\n# End-to-End Test Plan: [Feature Name]\n\n**Source:** `[PRD\u002FTask List path or \"User Description\"]`\n**Generated:** YYYY-MM-DD\n**Environment:** Local | Staging | Production\n\n---\n\n## Environment Declaration\n\n**Target Environment:** [Local\u002FStaging\u002FProduction]\n**Confirmed by:** [User confirmation timestamp or note]\n\n### If Production\n- **Deployed Version:** [commit hash or version]\n- **Last Deployment:** [date\u002Ftime]\n- **Deployment Process:**\n  ```bash\n  # How to deploy updates\n  [deployment commands]\n  ```\n- **Rollback Process:**\n  ```bash\n  # How to rollback if needed\n  [rollback commands]\n  ```\n\n---\n\n## Prerequisites\n\n### 1. Services Required\n\n| Service | Directory | Port | Start Command |\n|---------|-----------|------|---------------|\n| Backend API | `.\u002Fbackend` | 3012 | `PORT=3012 bun run dev` |\n| Frontend | `.\u002Ffrontend` | 3007 | `PORT=3007 npm run dev` |\n| [Service N] | `.\u002Fpath` | XXXX | `command` |\n\n### 2. Health Checks\n\nVerify all services are healthy before testing:\n\n```bash\n# Backend API\ncurl -f http:\u002F\u002Flocalhost:3012\u002Fhealth | jq '.status'\n# Expected: \"healthy\"\n\n# Frontend\ncurl -f http:\u002F\u002Flocalhost:3007 -o \u002Fdev\u002Fnull -w \"%{http_code}\"\n# Expected: 200\n\n# [Service N]\ncurl -f http:\u002F\u002Flocalhost:XXXX\u002Fhealth\n```\n\n### 3. Environment Setup\n\n⚠️ **SECURITY WARNING**\n- **Never commit credentials to version control**\n- Ensure `.env`, `.env.local`, `.env.*.local` are in `.gitignore`\n- Use secure storage for sensitive values (1Password, AWS Secrets Manager, etc.)\n- Production credentials should NEVER be in local `.env` files\n\n```bash\n# Copy environment template\ncp .env.example .env.local\n\n# Required variables (set these):\n# - DATABASE_URL=...\n# - API_KEY=...\n\n# Verify .gitignore includes environment files\ngrep -q \"\\.env\" .gitignore || echo \"⚠️  WARNING: .env not in .gitignore!\"\n```\n\n### 4. Test Accounts & Credentials\n\n⚠️ **CREDENTIAL SECURITY**\n- **NEVER store credentials in files that are committed to git**\n- **NEVER hardcode passwords in test scripts**\n- Use environment variables or secure vaults\n- Review `.gitignore` to ensure credential files are excluded\n\n#### Credential Storage\n| Credential Type | Location | Notes |\n|-----------------|----------|-------|\n| Local dev accounts | `.env.local` (git-ignored) | **MUST be in .gitignore** |\n| Staging accounts | Team password manager \u002F secrets vault | Shared test accounts |\n| Production accounts | Secure vault (1Password, AWS Secrets, etc.) | Requires explicit access, NEVER local |\n\n#### Account Strategy\n**Choose ONE approach and document it:**\n\n**Option A: Use Existing Test Account**\n- Account email: `[existing-test@example.com]`\n- Password location: `[where to find it - e.g., \"1Password > Team Vault > Staging Accounts\"]`\n- Account permissions: `[admin\u002Fuser\u002Fspecific roles needed]`\n\n**Option B: Create New Test Account**\n- **Via UI signup:**\n  1. Navigate to `http:\u002F\u002Flocalhost:3007\u002Fsignup`\n  2. Register with email: `test-[feature]-[date]@example.com`\n  3. [Complete verification if required]\n\n- **Via CLI\u002Fseed script:**\n  ```bash\n  # Create test user via CLI\n  bun run db:seed --user test@example.com --password testpass123\n\n  # Or via API\n  curl -X POST http:\u002F\u002Flocalhost:3012\u002Fapi\u002Fauth\u002Fregister \\\n    -H \"Content-Type: application\u002Fjson\" \\\n    -d '{\"email\": \"test@example.com\", \"password\": \"testpass123\"}'\n  ```\n\n- **Via database directly (dev only):**\n  ```bash\n  # Insert test user (adjust for your DB)\n  bun run db:query \"INSERT INTO users (email, password_hash) VALUES (...)\"\n  ```\n\n#### Credential Checklist\n- [ ] Test account credentials documented (not committed to git)\n- [ ] Account has required permissions\u002Froles for testing\n- [ ] Password meets minimum requirements (if creating new)\n- [ ] Multi-factor auth handled (disabled for test account, or codes available)\n\n### 5. Test Data \u002F Fixtures\n\n- [ ] Database seeded: `bun run db:seed`\n- [ ] Required test records exist (orders, products, etc.)\n- [ ] File uploads\u002Fassets available if needed\n- [ ] [Other data prerequisites]\n\n---\n\n## User Journey Map\n\nBefore executing individual tests, understand the full user flow:\n\n```\n┌─────────────────────────────────────────────────────────────┐\n│ 1. AUTHENTICATION                                           │\n│    └─ [Login method: email\u002FOAuth\u002FSSO]                       │\n│    └─ [Session handling: token\u002Fcookie]                      │\n├─────────────────────────────────────────────────────────────┤\n│ 2. INITIAL STATE                                            │\n│    └─ [User profile loads]                                  │\n│    └─ [Permissions\u002Froles verified]                          │\n│    └─ [Dashboard\u002Fhome renders]                              │\n├─────────────────────────────────────────────────────────────┤\n│ 3. NAVIGATION                                               │\n│    └─ [Navigate to: \u002Fpath\u002Fto\u002Ffeature]                       │\n│    └─ [Required data fetched: API calls]                    │\n│    └─ [Loading states: spinners\u002Fskeletons]                  │\n├─────────────────────────────────────────────────────────────┤\n│ 4. CORE FUNCTIONALITY                                       │\n│    └─ [Primary action: e.g., send message]                  │\n│    └─ [Secondary actions: e.g., attach file]                │\n│    └─ [State updates: UI reflects changes]                  │\n├─────────────────────────────────────────────────────────────┤\n│ 5. DATA VERIFICATION                                        │\n│    └─ [Changes persisted to database]                       │\n│    └─ [UI shows updated state]                              │\n│    └─ [Other users see changes: if real-time]               │\n├─────────────────────────────────────────────────────────────┤\n│ 6. ERROR SCENARIOS                                          │\n│    └─ [Invalid input: validation messages]                  │\n│    └─ [Network failure: retry\u002Ferror UI]                     │\n│    └─ [Permission denied: proper handling]                  │\n├─────────────────────────────────────────────────────────────┤\n│ 7. EDGE CASES                                               │\n│    └─ [Empty state: first-time user]                        │\n│    └─ [Maximum limits: char limits, file size]              │\n│    └─ [Concurrent access: if applicable]                    │\n├─────────────────────────────────────────────────────────────┤\n│ 8. CLEANUP                                                  │\n│    └─ [Logout: session cleared]                             │\n│    └─ [Test data: cleaned or noted for manual cleanup]      │\n└─────────────────────────────────────────────────────────────┘\n```\n\n**Coverage Checklist:**\n- [ ] All journey stages have at least one test case\n- [ ] No gaps between stages (each flows into next)\n- [ ] Both happy path and error paths covered\n\n---\n\n## Test Cases\n\n### Test 1: [Scenario Name]\n\n**Purpose:** [What this test verifies]\n\n#### Steps\n\n1. **[Action]**\n   - Navigate to `http:\u002F\u002Flocalhost:3007\u002Fpath`\n   - **Expected:** [What should happen]\n\n2. **[Action]**\n   - [Detailed instruction]\n   - **Expected:** [Outcome]\n   - **Verify:**\n     ```bash\n     # Optional verification command\n     curl http:\u002F\u002Flocalhost:3012\u002Fapi\u002Fendpoint | jq '.field'\n     ```\n\n3. **[Continue numbered steps...]**\n\n#### Success Criteria\n- [ ] [Criterion 1]\n- [ ] [Criterion 2]\n\n---\n\n### Test 2: [Scenario Name]\n\n[Same structure as Test 1...]\n\n---\n\n## Troubleshooting\n\n### Service Won't Start\n\n**Symptom:** `[error message]`\n\n**Check:**\n1. Port already in use: `lsof -i :3012`\n2. Missing dependencies: `bun install`\n3. Environment variables: Verify `.env` file exists\n\n**Solution:**\n```bash\n# Kill existing process\nkill $(lsof -t -i :3012)\n\n# Restart service\nbun run dev\n```\n\n### Authentication\u002FLogin Issues\n\n**Symptom:** Cannot login, \"Invalid credentials\", or session expired\n\n**Check:**\n1. Verify account exists: Check database or user management\n2. Verify password: Confirm from credential storage location\n3. Check token expiry: JWT\u002Fsession may need refresh\n4. Check MFA: Disable for test account or have codes ready\n\n**Solution:**\n```bash\n# Reset password via CLI (if available)\nbun run auth:reset-password --email test@example.com\n\n# Check user exists in database\nbun run db:query \"SELECT * FROM users WHERE email = 'test@example.com'\"\n\n# Clear session\u002Fcookies and re-login\n# [Browser: DevTools > Application > Clear Storage]\n```\n\n### [Issue Category N]\n\n**Symptom:** [description]\n**Check:** [diagnostic steps]\n**Solution:** [fix]\n\n---\n\n## Success Criteria\n\n### Feature Acceptance\n- [ ] [Criterion from PRD\u002Fdescription]\n- [ ] [Criterion from PRD\u002Fdescription]\n- [ ] All test cases pass\n\n### Quality Gates\n- [ ] No console errors in browser\n- [ ] API responses \u003C 500ms\n- [ ] All health checks green\n\n---\n\n## E2E Completion Criteria\n\n### The Rule\n> **If an issue would happen in production, it is NOT \"unrelated\" - fix it NOW.**\n\n### Completion Checklist\n- [ ] Happy path works end-to-end\n- [ ] Error scenarios fail gracefully\n- [ ] Edge cases handled correctly\n- [ ] **ALL encountered issues fixed** (none deferred as \"out of scope\")\n- [ ] Re-validated after each fix\n- [ ] Production-ready confidence achieved\n\n### Fix-In-Place Protocol\nWhen ANY issue is encountered during testing:\n1. STOP - Don't mark test as passing\n2. ASSESS - Would this happen in production?\n3. FIX - If yes, fix it now (not later, not \"separate task\")\n4. RE-VALIDATE - Re-run E2E after fix\n5. REPEAT - Until full flow works\n\n### Sign-Off\n- [ ] All issues encountered during E2E testing have been addressed\n- [ ] No issues deferred as \"architectural\" or \"unrelated\"\n- [ ] Tester confirms: \"This would work in production\"\n\n**Signed:** _____________ **Date:** _____________\n\n---\n\n## Issue Tracking\n\n### Run Log Template\n\n| Step | Expected | Actual | Status | Logs\u002FArtifacts | Fix Commit |\n|------|----------|--------|--------|----------------|------------|\n| Test 1.1 | Page loads | | | | |\n| Test 1.2 | Form submits | | | | |\n\n### Issue Note Template\n\nWhen a test fails, create an issue note:\n\n```markdown\n## Issue: [Brief description]\n\n**Test Case:** [Test N, Step M]\n**Environment:** [Local\u002FStaging\u002FProduction]\n\n### Repro Steps\n1. [Exact commands to reproduce]\n\n### Error Output\n\\`\\`\\`\n[Paste error logs]\n\\`\\`\\`\n\n### Root Cause Hypothesis\n[What you think is wrong]\n\n### Proposed Fix\n[How to fix it]\n\n### Done When\n[What proves it's fixed]\n```\n\n### Fix Loop Process\n\nFor each failing test:\n\n1. **Reproduce** in smallest scope (single test\u002Fendpoint)\n2. **Add regression test** where appropriate:\n   - Backend: `__tests__\u002F` or `*.test.ts`\n   - Frontend: `*.test.tsx`\n   - E2E: Playwright spec\n3. **Implement fix**\n4. **Rerun failing test** to verify\n5. **Rerun full suite** for confidence\n6. **Update run log** with fix commit\n\n---\n\n## Next Steps\n\nAfter all tests pass:\n\n1. [ ] Document any discovered edge cases\n2. [ ] Update test plan if requirements changed\n3. [ ] Consider automation opportunities\n4. [ ] [Feature-specific follow-ups]\n\n---\n\n*Test plan generated YYYY-MM-DD by test-plan-generator skill*\n```\n\n---\n\n## Interaction Model\n\n1. **Input Detection** - Auto-detect source type\n2. **Environment Gate** - ALWAYS ask explicitly, never assume\n3. **Production Gate** - BLOCKING confirmation required\n4. **Draft Review** - Present for user feedback before saving\n5. **Iterative Refinement** - Update based on user corrections\n\n## Key Principles\n\n- **Normalize to actual repo** - Don't assume structure, discover it\n- **Executable commands** - Every health check, every start command should be copy-pasteable\n- **Issue tracking built-in** - Run log table is mandatory\n- **Fix loop defined** - Clear process for handling failures\n- **Environment-aware** - Different rigor for prod vs local\n\n---\n\n## CRITICAL: E2E Completion Criteria\n\n**This section MUST be included in every generated test plan.**\n\n### The Production Reality Rule\n\n> **If an issue would happen in production, it is NOT \"unrelated\" - it MUST be fixed.**\n\nWhen executing E2E tests, you will encounter issues. The natural instinct is to categorize them:\n- \"This is a bug in our feature\" → Fix it\n- \"This is an architecture issue\" → Defer it\n- \"This is unrelated to what we're testing\" → Ignore it\n\n**THIS IS WRONG.** In E2E testing, there is no such thing as an \"unrelated\" issue if it blocks the production flow.\n\n### Anti-Patterns (DO NOT DO)\n\n```\n❌ \"We've fixed the login issue, but there's an architecture problem\n    with the session handling that's unrelated to our feature.\"\n\n❌ \"The feature works, but the database connection pooling is a\n    separate infrastructure concern.\"\n\n❌ \"This test passes, but I noticed the API rate limiting would\n    cause issues - that's out of scope for this task.\"\n\n❌ \"The happy path works. The error handling issue is a different\n    story that should be addressed separately.\"\n```\n\n### Correct Behavior (DO THIS)\n\n```\n✅ \"The login works, but I discovered a session handling issue that\n    would affect production users. Fixing it now before proceeding.\"\n\n✅ \"While testing, I found the database connection pooling causes\n    timeouts under load. This would happen in production, so I'm\n    addressing it as part of this E2E validation.\"\n\n✅ \"The feature works but would hit API rate limits in production.\n    Implementing proper rate limiting before marking complete.\"\n\n✅ \"The happy path works. Now testing error scenarios and fixing\n    any issues found before marking the E2E test as complete.\"\n```\n\n### The Completion Standard\n\nA test is **NOT COMPLETE** until:\n\n| Criterion | Question to Ask |\n|-----------|-----------------|\n| **Happy path works** | Does the primary user flow succeed? |\n| **Error paths work** | Do error scenarios fail gracefully? |\n| **Edge cases handled** | Do boundary conditions behave correctly? |\n| **No blocking issues** | Would a real user encounter any problems? |\n| **Production-ready** | Could we deploy this right now with confidence? |\n\n### The Fix-In-Place Protocol\n\nWhen you encounter ANY issue during E2E testing:\n\n1. **STOP** - Don't mark the current test as passing\n2. **ASSESS** - Would this issue occur in production?\n3. **If YES → FIX IT NOW**\n   - Don't defer to a \"future task\"\n   - Don't categorize as \"out of scope\"\n   - Don't label as \"architecture issue\" and move on\n4. **RE-VALIDATE** - After fixing, re-run the E2E test\n5. **REPEAT** - Continue until the full flow works without issues\n\n### Including This in Generated Test Plans\n\nEvery test plan generated by this skill MUST include an \"E2E Completion Criteria\" section that:\n\n1. Lists the specific completion criteria for this feature\n2. Explicitly states the \"no unrelated issues\" rule\n3. Includes the fix-in-place protocol\n4. Requires sign-off that all encountered issues were addressed\n\n---\n\n## References\n- See `reference.md` for template structure details\n- See `.claude\u002Fagents\u002Ftdd-developer.md` for test implementation\n",{"name":5,"category":33,"description":7},"main","47b89745588c3057f0ccd0517a2eb8967df27054","templates\u002F.claude\u002Fskills\u002Ftest-plan-generator","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public","https:\u002F\u002Fgithub.com\u002Fdundas","derivative.io","2026-09-02 20:12:15",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add dundas\u002Fagentbootup-public --skill test-plan-generator",{"tool":57,"command":58},"bunx","bunx skills add dundas\u002Fagentbootup-public --skill test-plan-generator",{"tool":60,"command":61},"pnpm","pnpm dlx skills add dundas\u002Fagentbootup-public --skill test-plan-generator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftest-plan-generator\u002FSKILL.md",true,[65,71],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"reference.md","REFERENCE","参考文档",6820,"https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftest-plan-generator\u002Freference.md",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"skill-bundle-manifest.json",1043,"https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftest-plan-generator\u002Fskill-bundle-manifest.json",[76,88,107,125,134,149],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":85,"publishedAt":39},"01M6CQZ7DFJB965BJJ5ZZ54CXY","fixture-skill","Secret-free recovery fixture skill.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftests\u002Fruntime-adapters\u002Ffixtures\u002Fhermes\u002F0.18.2-darwin-arm64-real\u002Froot\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[86,87],"fixture skill","recovery",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":99,"publishedAt":39},"01M6CQZ4NN0KVH1Z4E1Y1GJ3X9","user-story-generator","Generate standalone user stories for features without creating a full PRD. Perfect for backlog grooming and story refinement.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Fuser-story-generator\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[100,101,102,103,104,105,31,106],"user story generator","Story","user story","user","prd","documentation","backlog",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":117,"publishedAt":39},"01M6CQZ16VC27HMWM31CCKK6BC","user-journey-mapper","Map user flows and journeys through your application for UX design and workflow visualization, independent of testing.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Fuser-journey-mapper\u002FSKILL.md",[113,114],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":115,"categoryName":116,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000032","设计师",[118,119,103,120,105,121,122,123,124],"user journey mapper","journey","ux","visualization","workflow","design","testing",{"skillNo":126,"name":127,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":39},"01M6CQYXSQQJ4Z5CRAX2SSMHW1","transcript-query","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftranscript-query\u002FSKILL.md",[],[131,132,133],"transcript","transcript query","query",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":39},"01M6CQYQAWFSPTYE2VTJJVW72G","tasklist-generator","Generate high-level tasks and gated sub-tasks from a PRD, with agent assignments, commit\u002FPR strategy, and relevant files.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftasklist-generator\u002FSKILL.md",[140],{"categoryNo":83,"categoryName":84,"taxonomyType":21,"taxonomyTypeDesc":22},[142,143,122,144,145,146,104,31,147,148],"tasklist generator","commit","gated","files","strategy","tasks","pr",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":39},"01M6CQYMPPAMFGCVABR7T5FRXX","task-processor","Process a task list one sub-task at a time with pause\u002Fconfirm gates, test\u002Fcommit protocol, and file tracking.","https:\u002F\u002Fgithub.com\u002Fdundas\u002Fagentbootup-public\u002Fblob\u002Fmain\u002Ftemplates\u002F.claude\u002Fskills\u002Ftask-processor\u002FSKILL.md",[],[38,156,157,158,34,159,160,161,143,27,122],"processor","task processor","process","list","file","protocol"]