원클릭으로
review-gates
Two-stage review gates ensuring both requirement compliance and code quality before merging.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Two-stage review gates ensuring both requirement compliance and code quality before merging.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
End-to-end orchestrated execution. Takes a feature description and drives the entire pipeline — plan, plan review (3 fresh reviewers), WU decomposition, 4-phase execution loop per WU, final review, COMMIT-READY emit. Honors user's git policy (no auto-commit).
`--default-domain` comes from the project-detect framework signal (orchestrator Step 5b / project-context); it only decides how UI files with no strong path marker are classified. `--risk-tier` is the WU's `risk_tier` fi
**Capture the WU baseline ONCE per WU, before attempt 1 (NOT on retries).** This is what makes file-scope checks correct across a multi-WU run where the user has not yet committed prior WUs (per the `ben yapacagim` git p
This gate has **two interchangeable execution paths that MUST emit the identical aggregated verdict object** (Step 3). The prose path below is the canonical fallback and the single source of truth for reviewer prompts an
A baton-based system for building mobile features across multiple Claude Code sessions with persistent progress tracking and simulator verification between steps.
Set up end-to-end testing framework with CI integration
| name | review-gates |
| description | Two-stage review gates ensuring both requirement compliance and code quality before merging. |
| source_type | skill |
| source_file | skills/review-gates.md |
Migrated from skills/review-gates.md.
references/... or workflow/..., are packaged beside this SKILL.md.agents/..., commands/..., scripts/..., resources/..., rules/..., hooks/..., or templates/..., are packaged at this plugin root.skills/orchestration/...) is packaged under source/skills/orchestration/... for exact-reference lookups; all other Telar skills exist here only as the generated adapters under the plugin-root skills/ directory.../.. when reading support files or running packaged scripts.Two-stage review gates ensuring both requirement compliance and code quality before merging.
Does the implementation meet the requirements?
For each F-x and UI-x covered by this implementation:
## Requirements Compliance
| Requirement | Description | Status | Evidence |
|-------------|-------------|--------|----------|
| F-1 | Email auth | PASS | `lib/features/auth/auth_repository.dart` |
| F-7 | Calendar view | FAIL | Missing conflict resolution (F-7 business rule 3) |
| UI-5 | Calendar screen | PASS | `lib/screens/calendar/calendar_screen.dart` |
### Verdict: FAIL (1 unmet requirement)
Action: Implement F-7 business rule 3 before Stage 2
If PLAN.md and PROGRESS.md exist:
## Task Acceptance Check
| Task | Requirement | Acceptance Criteria | Status |
|------|-------------|--------------------|---------|
| T1 | F-1 | Auth repository initialises without errors | PASS |
| T3 | F-7 | Calendar loads events for current month | PASS |
| T4 | F-7 | Conflict shown when two events overlap | FAIL |
### Verdict: FAIL (1 unmet criterion)
Both 1A and 1B must pass before Stage 2 begins.
Verification requirement: Evidence must be fresh — re-run tests and re-verify on simulator before claiming pass. See
verification-before-completionskill.
Does the code follow project standards?
## Code Quality Check
### Architecture
- [ ] Follows existing project structure
- [ ] No circular dependencies
- [ ] Appropriate separation of concerns
### Patterns
- [ ] Matches existing state management approach
- [ ] Consistent error handling pattern
- [ ] Proper loading state management
- [ ] API responses validated
### Performance
- [ ] No unnecessary re-renders / rebuilds
- [ ] List rendering optimised
- [ ] No large imports
- [ ] Images optimised
### Platform Conventions
- [ ] Touch targets >= 44pt iOS / 48dp Android
- [ ] Safe area handling correct
- [ ] Platform-specific navigation patterns respected
- [ ] Deep link handling for new routes
### Accessibility
- [ ] Interactive elements have accessibility labels
- [ ] Error messages announced
- [ ] Focus order logical
- [ ] Color contrast WCAG AA
### Testing
- [ ] Unit tests for business logic
- [ ] Component tests for UI
- [ ] Edge cases covered
### Maintainability
- [ ] No duplicated logic (textual or semantic) whose sites change together for the same reason — unified, not copy-pasted
- [ ] Existing shared components/utils/RPCs/views reused, not re-implemented
- [ ] No speculative abstraction / dead flexibility (simplicity-first)
- [ ] Design patterns consistent with codebase conventions; no misapplied pattern
- [ ] Reuse/refactor opportunities noted as advisories (non-blocking)
- [ ] NOT flagged: coincidental similarity with different responsibilities (wrong abstraction), dogmatic tiny-function/length gates
### Verdict: PASS / FAIL
commands/review-code.mdrules/quality-gates.mdREQUIREMENTS.md, PLAN.md, PROGRESS.mdskills/requirements-traceability.md