[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BMV6QJBTESJRMB94DPR8RC":3,"skill-same:01M7BMV6QJBTESJRMB94DPR8RC":48},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7BMV6QJBTESJRMB94DPR8RC","workflow-patterns",null,"Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-agents\u002Fplugins\u002Fconductor\u002Fskills\u002Fworkflow-patterns\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: workflow-patterns\ndescription: Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.\nversion: 1.0.0\n---\n\n# Workflow Patterns\n\nGuide for implementing tasks using Conductor's TDD workflow, managing phase checkpoints, handling git commits, and executing the verification protocol that ensures quality throughout implementation.\n\n## When to Use This Skill\n\n- Implementing tasks from a track's plan.md\n- Following TDD red-green-refactor cycle\n- Completing phase checkpoints\n- Managing git commits and notes\n- Understanding quality assurance gates\n- Handling verification protocols\n- Recording progress in plan files\n\n## TDD Task Lifecycle\n\nFollow these 11 steps for each task:\n\n### Step 1: Select Next Task\n\nRead plan.md and identify the next pending `[ ]` task. Select tasks in order within the current phase. Do not skip ahead to later phases.\n\n### Step 2: Mark as In Progress\n\nUpdate plan.md to mark the task as `[~]`:\n\n```markdown\n- [~] **Task 2.1**: Implement user validation\n```\n\nCommit this status change separately from implementation.\n\n### Step 3: RED - Write Failing Tests\n\nWrite tests that define the expected behavior before writing implementation:\n\n- Create test file if needed\n- Write test cases covering happy path\n- Write test cases covering edge cases\n- Write test cases covering error conditions\n- Run tests - they should FAIL\n\nExample:\n\n```python\ndef test_validate_user_email_valid():\n    user = User(email=\"test@example.com\")\n    assert user.validate_email() is True\n\ndef test_validate_user_email_invalid():\n    user = User(email=\"invalid\")\n    assert user.validate_email() is False\n```\n\n### Step 4: GREEN - Implement Minimum Code\n\nWrite the minimum code necessary to make tests pass:\n\n- Focus on making tests green, not perfection\n- Avoid premature optimization\n- Keep implementation simple\n- Run tests - they should PASS\n\n### Step 5: REFACTOR - Improve Clarity\n\nWith green tests, improve the code:\n\n- Extract common patterns\n- Improve naming\n- Remove duplication\n- Simplify logic\n- Run tests after each change - they should remain GREEN\n\n### Step 6: Verify Coverage\n\nCheck test coverage meets the 80% target:\n\n```bash\npytest --cov=module --cov-report=term-missing\n```\n\nIf coverage is below 80%:\n\n- Identify uncovered lines\n- Add tests for missing paths\n- Re-run coverage check\n\n### Step 7: Document Deviations\n\nIf implementation deviated from plan or introduced new dependencies:\n\n- Update tech-stack.md with new dependencies\n- Note deviations in plan.md task comments\n- Update spec.md if requirements changed\n\n### Step 8: Commit Implementation\n\nCreate a focused commit for the task:\n\n```bash\ngit add -A\ngit commit -m \"feat(user): implement email validation\n\n- Add validate_email method to User class\n- Handle empty and malformed emails\n- Add comprehensive test coverage\n\nTask: 2.1\nTrack: user-auth_20250115\"\n```\n\nCommit message format:\n\n- Type: feat, fix, refactor, test, docs, chore\n- Scope: affected module or component\n- Summary: imperative, present tense\n- Body: bullet points of changes\n- Footer: task and track references\n\n### Step 9: Attach Git Notes\n\nAdd rich task summary as git note:\n\n```bash\ngit notes add -m \"Task 2.1: Implement user validation\n\nSummary:\n- Added email validation using regex pattern\n- Handles edge cases: empty, no @, no domain\n- Coverage: 94% on validation module\n\nFiles changed:\n- src\u002Fmodels\u002Fuser.py (modified)\n- tests\u002Ftest_user.py (modified)\n\nDecisions:\n- Used simple regex over email-validator library\n- Reason: No external dependency for basic validation\"\n```\n\n### Step 10: Update Plan with SHA\n\nUpdate plan.md to mark task complete with commit SHA:\n\n```markdown\n- [x] **Task 2.1**: Implement user validation `abc1234`\n```\n\n### Step 11: Commit Plan Update\n\nCommit the plan status update:\n\n```bash\ngit add conductor\u002Ftracks\u002F*\u002Fplan.md\ngit commit -m \"docs: update plan - task 2.1 complete\n\nTrack: user-auth_20250115\"\n```\n\n## Phase Completion Protocol\n\nWhen all tasks in a phase are complete, execute the verification protocol:\n\n### Identify Changed Files\n\nList all files modified since the last checkpoint:\n\n```bash\ngit diff --name-only \u003Clast-checkpoint-sha>..HEAD\n```\n\n### Ensure Test Coverage\n\nFor each modified file:\n\n1. Identify corresponding test file\n2. Verify tests exist for new\u002Fchanged code\n3. Run coverage for modified modules\n4. Add tests if coverage \u003C 80%\n\n### Run Full Test Suite\n\nExecute complete test suite:\n\n```bash\npytest -v --tb=short\n```\n\nAll tests must pass before proceeding.\n\n### Generate Manual Verification Steps\n\nCreate checklist of manual verifications:\n\n```markdown\n## Phase 1 Verification Checklist\n\n- [ ] User can register with valid email\n- [ ] Invalid email shows appropriate error\n- [ ] Database stores user correctly\n- [ ] API returns expected response codes\n```\n\n### WAIT for User Approval\n\nPresent verification checklist to user:\n\n```\nPhase 1 complete. Please verify:\n1. [ ] Test suite passes (automated)\n2. [ ] Coverage meets target (automated)\n3. [ ] Manual verification items (requires human)\n\nRespond with 'approved' to continue, or note issues.\n```\n\nDo NOT proceed without explicit approval.\n\n### Create Checkpoint Commit\n\nAfter approval, create checkpoint commit:\n\n```bash\ngit add -A\ngit commit -m \"checkpoint: phase 1 complete - user-auth_20250115\n\nVerified:\n- All tests passing\n- Coverage: 87%\n- Manual verification approved\n\nPhase 1 tasks:\n- [x] Task 1.1: Setup database schema\n- [x] Task 1.2: Implement user model\n- [x] Task 1.3: Add validation logic\"\n```\n\n### Record Checkpoint SHA\n\nUpdate plan.md checkpoints table:\n\n```markdown\n## Checkpoints\n\n| Phase   | Checkpoint SHA | Date       | Status   |\n| ------- | -------------- | ---------- | -------- |\n| Phase 1 | def5678        | 2025-01-15 | verified |\n| Phase 2 |                |            | pending  |\n```\n\n## Quality Assurance Gates\n\nBefore marking any task complete, verify these gates:\n\n### Passing Tests\n\n- All existing tests pass\n- New tests pass\n- No test regressions\n\n### Coverage >= 80%\n\n- New code has 80%+ coverage\n- Overall project coverage maintained\n- Critical paths fully covered\n\n### Style Compliance\n\n- Code follows style guides\n- Linting passes\n- Formatting correct\n\n### Documentation\n\n- Public APIs documented\n- Complex logic explained\n- README updated if needed\n\n### Type Safety\n\n- Type hints present (if applicable)\n- Type checker passes\n- No type: ignore without reason\n\n### No Linting Errors\n\n- Zero linter errors\n- Warnings addressed or justified\n- Static analysis clean\n\n### Mobile Compatibility\n\nIf applicable:\n\n- Responsive design verified\n- Touch interactions work\n- Performance acceptable\n\n### Security Audit\n\n- No secrets in code\n- Input validation present\n- Authentication\u002Fauthorization correct\n- Dependencies vulnerability-free\n\n## Git Integration\n\n### Commit Message Format\n\n```\n\u003Ctype>(\u003Cscope>): \u003Csubject>\n\n\u003Cbody>\n\n\u003Cfooter>\n```\n\nTypes:\n\n- `feat`: New feature\n- `fix`: Bug fix\n- `refactor`: Code change without feature\u002Ffix\n- `test`: Adding tests\n- `docs`: Documentation\n- `chore`: Maintenance\n\n### Git Notes for Rich Summaries\n\nAttach detailed notes to commits:\n\n```bash\ngit notes add -m \"\u003Cdetailed summary>\"\n```\n\nView notes:\n\n```bash\ngit log --show-notes\n```\n\nBenefits:\n\n- Preserves context without cluttering commit message\n- Enables semantic queries across commits\n- Supports track-based operations\n\n### SHA Recording in plan.md\n\nAlways record the commit SHA when completing tasks:\n\n```markdown\n- [x] **Task 1.1**: Setup schema `abc1234`\n- [x] **Task 1.2**: Add model `def5678`\n```\n\nThis enables:\n\n- Traceability from plan to code\n- Semantic revert operations\n- Progress auditing\n\n## Verification Checkpoints\n\n### Why Checkpoints Matter\n\nCheckpoints create restore points for semantic reversion:\n\n- Revert to end of any phase\n- Maintain logical code state\n- Enable safe experimentation\n\n### When to Create Checkpoints\n\nCreate checkpoint after:\n\n- All phase tasks complete\n- All phase verifications pass\n- User approval received\n\n### Checkpoint Commit Content\n\nInclude in checkpoint commit:\n\n- All uncommitted changes\n- Updated plan.md\n- Updated metadata.json\n- Any documentation updates\n\n### How to Use Checkpoints\n\nFor reverting:\n\n```bash\n# Revert to end of Phase 1\ngit revert --no-commit \u003Cphase-2-commits>...\ngit commit -m \"revert: rollback to phase 1 checkpoint\"\n```\n\nFor review:\n\n```bash\n# See what changed in Phase 2\ngit diff \u003Cphase-1-sha>..\u003Cphase-2-sha>\n```\n\n## Handling Deviations\n\nDuring implementation, deviations from the plan may occur. Handle them systematically:\n\n### Types of Deviations\n\n**Scope Addition**\nDiscovered requirement not in original spec.\n\n- Document in spec.md as new requirement\n- Add tasks to plan.md\n- Note addition in task comments\n\n**Scope Reduction**\nFeature deemed unnecessary during implementation.\n\n- Mark tasks as `[-]` (skipped) with reason\n- Update spec.md scope section\n- Document decision rationale\n\n**Technical Deviation**\nDifferent implementation approach than planned.\n\n- Note deviation in task completion comment\n- Update tech-stack.md if dependencies changed\n- Document why original approach was unsuitable\n\n**Requirement Change**\nUnderstanding of requirement changes during work.\n\n- Update spec.md with corrected requirement\n- Adjust plan.md tasks if needed\n- Re-verify acceptance criteria\n\n### Deviation Documentation Format\n\nWhen completing a task with deviation:\n\n```markdown\n- [x] **Task 2.1**: Implement validation `abc1234`\n  - DEVIATION: Used library instead of custom code\n  - Reason: Better edge case handling\n  - Impact: Added email-validator to dependencies\n```\n\n## Error Recovery\n\n### Failed Tests After GREEN\n\nIf tests fail after reaching GREEN:\n\n1. Do NOT proceed to REFACTOR\n2. Identify which test started failing\n3. Check if refactoring broke something\n4. Revert to last known GREEN state\n5. Re-approach the implementation\n\n### Checkpoint Rejection\n\nIf user rejects a checkpoint:\n\n1. Note rejection reason in plan.md\n2. Create tasks to address issues\n3. Complete remediation tasks\n4. Request checkpoint approval again\n\n### Blocked by Dependency\n\nIf task cannot proceed:\n\n1. Mark task as `[!]` with blocker description\n2. Check if other tasks can proceed\n3. Document expected resolution timeline\n4. Consider creating dependency resolution track\n\n## TDD Variations by Task Type\n\n### Data Model Tasks\n\n```\nRED: Write test for model creation and validation\nGREEN: Implement model class with fields\nREFACTOR: Add computed properties, improve types\n```\n\n### API Endpoint Tasks\n\n```\nRED: Write test for request\u002Fresponse contract\nGREEN: Implement endpoint handler\nREFACTOR: Extract validation, improve error handling\n```\n\n### Integration Tasks\n\n```\nRED: Write test for component interaction\nGREEN: Wire components together\nREFACTOR: Improve error propagation, add logging\n```\n\n### Refactoring Tasks\n\n```\nRED: Add characterization tests for current behavior\nGREEN: Apply refactoring (tests should stay green)\nREFACTOR: Clean up any introduced complexity\n```\n\n## Working with Existing Tests\n\nWhen modifying code with existing tests:\n\n### Extend, Don't Replace\n\n- Keep existing tests passing\n- Add new tests for new behavior\n- Update tests only when requirements change\n\n### Test Migration\n\nWhen refactoring changes test structure:\n\n1. Run existing tests (should pass)\n2. Add new tests for refactored code\n3. Migrate test cases to new structure\n4. Remove old tests only after new tests pass\n\n### Regression Prevention\n\nAfter any change:\n\n1. Run full test suite\n2. Check for unexpected failures\n3. Investigate any new failures\n4. Fix regressions before proceeding\n\n## Checkpoint Verification Details\n\n### Automated Verification\n\nRun before requesting approval:\n\n```bash\n# Test suite\npytest -v --tb=short\n\n# Coverage\npytest --cov=src --cov-report=term-missing\n\n# Linting\nruff check src\u002F tests\u002F\n\n# Type checking (if applicable)\nmypy src\u002F\n```\n\n### Manual Verification Guidance\n\nFor manual items, provide specific instructions:\n\n```markdown\n## Manual Verification Steps\n\n### User Registration\n\n1. Navigate to \u002Fregister\n2. Enter valid email: test@example.com\n3. Enter password meeting requirements\n4. Click Submit\n5. Verify success message appears\n6. Verify user appears in database\n\n### Error Handling\n\n1. Enter invalid email: \"notanemail\"\n2. Verify error message shows\n3. Verify form retains other entered data\n```\n\n## Performance Considerations\n\n### Test Suite Performance\n\nKeep test suite fast:\n\n- Use fixtures to avoid redundant setup\n- Mock slow external calls\n- Run subset during development, full suite at checkpoints\n\n### Commit Performance\n\nKeep commits atomic:\n\n- One logical change per commit\n- Complete thought, not work-in-progress\n- Tests should pass after every commit\n\n## Best Practices\n\n1. **Never skip RED**: Always write failing tests first\n2. **Small commits**: One logical change per commit\n3. **Immediate updates**: Update plan.md right after task completion\n4. **Wait for approval**: Never skip checkpoint verification\n5. **Rich git notes**: Include context that helps future understanding\n6. **Coverage discipline**: Don't accept coverage below target\n7. **Quality gates**: Check all gates before marking complete\n8. **Sequential phases**: Complete phases in order\n9. **Document deviations**: Note any changes from original plan\n10. **Clean state**: Each commit should leave code in working state\n11. **Fast feedback**: Run relevant tests frequently during development\n12. **Clear blockers**: Address blockers promptly, don't work around them\n","# Workflow Patterns\n\nGuide for implementing tasks using Conductor's TDD workflow, managing phase checkpoints, handling git commits, and executing the verification protocol that ensures quality throughout implementation.\n\n## When to Use This Skill\n\n- Implementing tasks from a track's plan.md\n- Following TDD red-green-refactor cycle\n- Completing phase checkpoints\n- Managing git commits and notes\n- Understanding quality assurance gates\n- Handling verification protocols\n- Recording progress in plan files\n\n## TDD Task Lifecycle\n\nFollow these 11 steps for each task:\n\n### Step 1: Select Next Task\n\nRead plan.md and identify the next pending `[ ]` task. Select tasks in order within the current phase. Do not skip ahead to later phases.\n\n### Step 2: Mark as In Progress\n\nUpdate plan.md to mark the task as `[~]`:\n\n```markdown\n- [~] **Task 2.1**: Implement user validation\n```\n\nCommit this status change separately from implementation.\n\n### Step 3: RED - Write Failing Tests\n\nWrite tests that define the expected behavior before writing implementation:\n\n- Create test file if needed\n- Write test cases covering happy path\n- Write test cases covering edge cases\n- Write test cases covering error conditions\n- Run tests - they should FAIL\n\nExample:\n\n```python\ndef test_validate_user_email_valid():\n    user = User(email=\"test@example.com\")\n    assert user.validate_email() is True\n\ndef test_validate_user_email_invalid():\n    user = User(email=\"invalid\")\n    assert user.validate_email() is False\n```\n\n### Step 4: GREEN - Implement Minimum Code\n\nWrite the minimum code necessary to make tests pass:\n\n- Focus on making tests green, not perfection\n- Avoid premature optimization\n- Keep implementation simple\n- Run tests - they should PASS\n\n### Step 5: REFACTOR - Improve Clarity\n\nWith green tests, improve the code:\n\n- Extract common patterns\n- Improve naming\n- Remove duplication\n- Simplify logic\n- Run tests after each change - they should remain GREEN\n\n### Step 6: Verify Coverage\n\nCheck test coverage meets the 80% target:\n\n```bash\npytest --cov=module --cov-report=term-missing\n```\n\nIf coverage is below 80%:\n\n- Identify uncovered lines\n- Add tests for missing paths\n- Re-run coverage check\n\n### Step 7: Document Deviations\n\nIf implementation deviated from plan or introduced new dependencies:\n\n- Update tech-stack.md with new dependencies\n- Note deviations in plan.md task comments\n- Update spec.md if requirements changed\n\n### Step 8: Commit Implementation\n\nCreate a focused commit for the task:\n\n```bash\ngit add -A\ngit commit -m \"feat(user): implement email validation\n\n- Add validate_email method to User class\n- Handle empty and malformed emails\n- Add comprehensive test coverage\n\nTask: 2.1\nTrack: user-auth_20250115\"\n```\n\nCommit message format:\n\n- Type: feat, fix, refactor, test, docs, chore\n- Scope: affected module or component\n- Summary: imperative, present tense\n- Body: bullet points of changes\n- Footer: task and track references\n\n### Step 9: Attach Git Notes\n\nAdd rich task summary as git note:\n\n```bash\ngit notes add -m \"Task 2.1: Implement user validation\n\nSummary:\n- Added email validation using regex pattern\n- Handles edge cases: empty, no @, no domain\n- Coverage: 94% on validation module\n\nFiles changed:\n- src\u002Fmodels\u002Fuser.py (modified)\n- tests\u002Ftest_user.py (modified)\n\nDecisions:\n- Used simple regex over email-validator library\n- Reason: No external dependency for basic validation\"\n```\n\n### Step 10: Update Plan with SHA\n\nUpdate plan.md to mark task complete with commit SHA:\n\n```markdown\n- [x] **Task 2.1**: Implement user validation `abc1234`\n```\n\n### Step 11: Commit Plan Update\n\nCommit the plan status update:\n\n```bash\ngit add conductor\u002Ftracks\u002F*\u002Fplan.md\ngit commit -m \"docs: update plan - task 2.1 complete\n\nTrack: user-auth_20250115\"\n```\n\n## Phase Completion Protocol\n\nWhen all tasks in a phase are complete, execute the verification protocol:\n\n### Identify Changed Files\n\nList all files modified since the last checkpoint:\n\n```bash\ngit diff --name-only \u003Clast-checkpoint-sha>..HEAD\n```\n\n### Ensure Test Coverage\n\nFor each modified file:\n\n1. Identify corresponding test file\n2. Verify tests exist for new\u002Fchanged code\n3. Run coverage for modified modules\n4. Add tests if coverage \u003C 80%\n\n### Run Full Test Suite\n\nExecute complete test suite:\n\n```bash\npytest -v --tb=short\n```\n\nAll tests must pass before proceeding.\n\n### Generate Manual Verification Steps\n\nCreate checklist of manual verifications:\n\n```markdown\n## Phase 1 Verification Checklist\n\n- [ ] User can register with valid email\n- [ ] Invalid email shows appropriate error\n- [ ] Database stores user correctly\n- [ ] API returns expected response codes\n```\n\n### WAIT for User Approval\n\nPresent verification checklist to user:\n\n```\nPhase 1 complete. Please verify:\n1. [ ] Test suite passes (automated)\n2. [ ] Coverage meets target (automated)\n3. [ ] Manual verification items (requires human)\n\nRespond with 'approved' to continue, or note issues.\n```\n\nDo NOT proceed without explicit approval.\n\n### Create Checkpoint Commit\n\nAfter approval, create checkpoint commit:\n\n```bash\ngit add -A\ngit commit -m \"checkpoint: phase 1 complete - user-auth_20250115\n\nVerified:\n- All tests passing\n- Coverage: 87%\n- Manual verification approved\n\nPhase 1 tasks:\n- [x] Task 1.1: Setup database schema\n- [x] Task 1.2: Implement user model\n- [x] Task 1.3: Add validation logic\"\n```\n\n### Record Checkpoint SHA\n\nUpdate plan.md checkpoints table:\n\n```markdown\n## Checkpoints\n\n| Phase   | Checkpoint SHA | Date       | Status   |\n| ------- | -------------- | ---------- | -------- |\n| Phase 1 | def5678        | 2025-01-15 | verified |\n| Phase 2 |                |            | pending  |\n```\n\n## Quality Assurance Gates\n\nBefore marking any task complete, verify these gates:\n\n### Passing Tests\n\n- All existing tests pass\n- New tests pass\n- No test regressions\n\n### Coverage >= 80%\n\n- New code has 80%+ coverage\n- Overall project coverage maintained\n- Critical paths fully covered\n\n### Style Compliance\n\n- Code follows style guides\n- Linting passes\n- Formatting correct\n\n### Documentation\n\n- Public APIs documented\n- Complex logic explained\n- README updated if needed\n\n### Type Safety\n\n- Type hints present (if applicable)\n- Type checker passes\n- No type: ignore without reason\n\n### No Linting Errors\n\n- Zero linter errors\n- Warnings addressed or justified\n- Static analysis clean\n\n### Mobile Compatibility\n\nIf applicable:\n\n- Responsive design verified\n- Touch interactions work\n- Performance acceptable\n\n### Security Audit\n\n- No secrets in code\n- Input validation present\n- Authentication\u002Fauthorization correct\n- Dependencies vulnerability-free\n\n## Git Integration\n\n### Commit Message Format\n\n```\n\u003Ctype>(\u003Cscope>): \u003Csubject>\n\n\u003Cbody>\n\n\u003Cfooter>\n```\n\nTypes:\n\n- `feat`: New feature\n- `fix`: Bug fix\n- `refactor`: Code change without feature\u002Ffix\n- `test`: Adding tests\n- `docs`: Documentation\n- `chore`: Maintenance\n\n### Git Notes for Rich Summaries\n\nAttach detailed notes to commits:\n\n```bash\ngit notes add -m \"\u003Cdetailed summary>\"\n```\n\nView notes:\n\n```bash\ngit log --show-notes\n```\n\nBenefits:\n\n- Preserves context without cluttering commit message\n- Enables semantic queries across commits\n- Supports track-based operations\n\n### SHA Recording in plan.md\n\nAlways record the commit SHA when completing tasks:\n\n```markdown\n- [x] **Task 1.1**: Setup schema `abc1234`\n- [x] **Task 1.2**: Add model `def5678`\n```\n\nThis enables:\n\n- Traceability from plan to code\n- Semantic revert operations\n- Progress auditing\n\n## Verification Checkpoints\n\n### Why Checkpoints Matter\n\nCheckpoints create restore points for semantic reversion:\n\n- Revert to end of any phase\n- Maintain logical code state\n- Enable safe experimentation\n\n### When to Create Checkpoints\n\nCreate checkpoint after:\n\n- All phase tasks complete\n- All phase verifications pass\n- User approval received\n\n### Checkpoint Commit Content\n\nInclude in checkpoint commit:\n\n- All uncommitted changes\n- Updated plan.md\n- Updated metadata.json\n- Any documentation updates\n\n### How to Use Checkpoints\n\nFor reverting:\n\n```bash\n# Revert to end of Phase 1\ngit revert --no-commit \u003Cphase-2-commits>...\ngit commit -m \"revert: rollback to phase 1 checkpoint\"\n```\n\nFor review:\n\n```bash\n# See what changed in Phase 2\ngit diff \u003Cphase-1-sha>..\u003Cphase-2-sha>\n```\n\n## Handling Deviations\n\nDuring implementation, deviations from the plan may occur. Handle them systematically:\n\n### Types of Deviations\n\n**Scope Addition**\nDiscovered requirement not in original spec.\n\n- Document in spec.md as new requirement\n- Add tasks to plan.md\n- Note addition in task comments\n\n**Scope Reduction**\nFeature deemed unnecessary during implementation.\n\n- Mark tasks as `[-]` (skipped) with reason\n- Update spec.md scope section\n- Document decision rationale\n\n**Technical Deviation**\nDifferent implementation approach than planned.\n\n- Note deviation in task completion comment\n- Update tech-stack.md if dependencies changed\n- Document why original approach was unsuitable\n\n**Requirement Change**\nUnderstanding of requirement changes during work.\n\n- Update spec.md with corrected requirement\n- Adjust plan.md tasks if needed\n- Re-verify acceptance criteria\n\n### Deviation Documentation Format\n\nWhen completing a task with deviation:\n\n```markdown\n- [x] **Task 2.1**: Implement validation `abc1234`\n  - DEVIATION: Used library instead of custom code\n  - Reason: Better edge case handling\n  - Impact: Added email-validator to dependencies\n```\n\n## Error Recovery\n\n### Failed Tests After GREEN\n\nIf tests fail after reaching GREEN:\n\n1. Do NOT proceed to REFACTOR\n2. Identify which test started failing\n3. Check if refactoring broke something\n4. Revert to last known GREEN state\n5. Re-approach the implementation\n\n### Checkpoint Rejection\n\nIf user rejects a checkpoint:\n\n1. Note rejection reason in plan.md\n2. Create tasks to address issues\n3. Complete remediation tasks\n4. Request checkpoint approval again\n\n### Blocked by Dependency\n\nIf task cannot proceed:\n\n1. Mark task as `[!]` with blocker description\n2. Check if other tasks can proceed\n3. Document expected resolution timeline\n4. Consider creating dependency resolution track\n\n## TDD Variations by Task Type\n\n### Data Model Tasks\n\n```\nRED: Write test for model creation and validation\nGREEN: Implement model class with fields\nREFACTOR: Add computed properties, improve types\n```\n\n### API Endpoint Tasks\n\n```\nRED: Write test for request\u002Fresponse contract\nGREEN: Implement endpoint handler\nREFACTOR: Extract validation, improve error handling\n```\n\n### Integration Tasks\n\n```\nRED: Write test for component interaction\nGREEN: Wire components together\nREFACTOR: Improve error propagation, add logging\n```\n\n### Refactoring Tasks\n\n```\nRED: Add characterization tests for current behavior\nGREEN: Apply refactoring (tests should stay green)\nREFACTOR: Clean up any introduced complexity\n```\n\n## Working with Existing Tests\n\nWhen modifying code with existing tests:\n\n### Extend, Don't Replace\n\n- Keep existing tests passing\n- Add new tests for new behavior\n- Update tests only when requirements change\n\n### Test Migration\n\nWhen refactoring changes test structure:\n\n1. Run existing tests (should pass)\n2. Add new tests for refactored code\n3. Migrate test cases to new structure\n4. Remove old tests only after new tests pass\n\n### Regression Prevention\n\nAfter any change:\n\n1. Run full test suite\n2. Check for unexpected failures\n3. Investigate any new failures\n4. Fix regressions before proceeding\n\n## Checkpoint Verification Details\n\n### Automated Verification\n\nRun before requesting approval:\n\n```bash\n# Test suite\npytest -v --tb=short\n\n# Coverage\npytest --cov=src --cov-report=term-missing\n\n# Linting\nruff check src\u002F tests\u002F\n\n# Type checking (if applicable)\nmypy src\u002F\n```\n\n### Manual Verification Guidance\n\nFor manual items, provide specific instructions:\n\n```markdown\n## Manual Verification Steps\n\n### User Registration\n\n1. Navigate to \u002Fregister\n2. Enter valid email: test@example.com\n3. Enter password meeting requirements\n4. Click Submit\n5. Verify success message appears\n6. Verify user appears in database\n\n### Error Handling\n\n1. Enter invalid email: \"notanemail\"\n2. Verify error message shows\n3. Verify form retains other entered data\n```\n\n## Performance Considerations\n\n### Test Suite Performance\n\nKeep test suite fast:\n\n- Use fixtures to avoid redundant setup\n- Mock slow external calls\n- Run subset during development, full suite at checkpoints\n\n### Commit Performance\n\nKeep commits atomic:\n\n- One logical change per commit\n- Complete thought, not work-in-progress\n- Tests should pass after every commit\n\n## Best Practices\n\n1. **Never skip RED**: Always write failing tests first\n2. **Small commits**: One logical change per commit\n3. **Immediate updates**: Update plan.md right after task completion\n4. **Wait for approval**: Never skip checkpoint verification\n5. **Rich git notes**: Include context that helps future understanding\n6. **Coverage discipline**: Don't accept coverage below target\n7. **Quality gates**: Check all gates before marking complete\n8. **Sequential phases**: Complete phases in order\n9. **Document deviations**: Note any changes from original plan\n10. **Clean state**: Each commit should leave code in working state\n11. **Fast feedback**: Run relevant tests frequently during development\n12. **Clear blockers**: Address blockers promptly, don't work around them\n",{"name":5,"version":24,"description":7},"1.0.0","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Agent-智能体\u002FYYC3-Agent-智能体-agents\u002Fplugins\u002Fconductor\u002Fskills\u002Fworkflow-patterns",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill workflow-patterns",{"tool":40,"command":41},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill workflow-patterns",{"tool":43,"command":44},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill workflow-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-agents\u002Fplugins\u002Fconductor\u002Fskills\u002Fworkflow-patterns\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]