메뉴
Mobile-specific code review with two-stage review gates, platform conventions, and priority-ranked findings
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-code |
| description | Mobile-specific code review with two-stage review gates, platform conventions, and priority-ranked findings |
| source_type | command |
| source_file | commands/review-code.md |
Migrated from commands/review-code.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./tl-telar:review-code; invoke it as $review-code or through @tl-telar.skills/orchestration/<name>, load the generated Codex skill at ../orchestration-<name>/SKILL.md first. The original source copy also exists under ../../source/skills/orchestration/<name>/SKILL.md for exact Telar-source references.Comprehensive mobile-specific code review with two-stage review gates.
skills:
- review-gates # Two-stage review gates
rules:
- platform-conventions # HIG/Material traceability
If PLAN.md exists:
If no PLAN.md:
Before concluding any phase, require fresh verification:
skills:
- verification-before-completion
agents:
- react-native-expert OR flutter-expert
- mobile-navigation-architect
Project structure
Component architecture
Navigation structure
- [ ] Clear separation of concerns
- [ ] Consistent folder structure
- [ ] Appropriate module boundaries
- [ ] No circular dependencies
agents:
- mobile-state-management
State management
Data fetching
Component patterns
// ❌ State in wrong place
const [globalData, setGlobalData] = useState() // Should be global
// ❌ Missing error handling
const data = await fetch(url) // No try/catch
// ❌ Prop drilling
<A><B><C><D prop={value} /></C></B></A>
agents:
- mobile-performance-optimizer
Render performance
List performance
Bundle size
// ❌ Re-render on every render
<Item style={{ margin: 10 }} />
// ❌ Missing keyExtractor
<FlatList data={items} />
// ❌ Full library import
import _ from 'lodash'
agents:
- mobile-security-specialist
Data storage
Network security
Input validation
// ❌ Sensitive data in AsyncStorage
await AsyncStorage.setItem('token', authToken)
// ❌ Hardcoded secrets
const API_KEY = 'sk-xxx'
// ❌ Missing validation
const data = await response.json() // No validation
agents:
- mobile-accessibility-expert
Screen reader support
Touch targets
Visual accessibility
// ❌ Missing accessibility label
<TouchableOpacity onPress={onPress}>
<Icon name="settings" />
</TouchableOpacity>
// ❌ Small touch target
<Pressable style={{ padding: 4 }} />
| Category | Issues | Critical | High | Medium | Low |
|----------|--------|----------|------|--------|-----|
| Architecture | 3 | 0 | 1 | 2 | 0 |
| Patterns | 5 | 0 | 2 | 2 | 1 |
| Performance | 4 | 1 | 1 | 2 | 0 |
| Security | 2 | 1 | 1 | 0 | 0 |
| Accessibility | 6 | 0 | 2 | 3 | 1 |
- [ ] Follows project patterns (codebase-first)
- [ ] Platform conventions respected (HIG/Material)
- [ ] Touch targets >= 44x44 (iOS) / 48x48 (Android)
- [ ] Deep link handling correct
- [ ] Error states handled
- [ ] Tests included
- [ ] No duplication (textual or semantic — same job, different code) whose sites change together for the same reason; existing shared units reused, not re-implemented
- [ ] No bloat / speculative abstraction (simplicity-first); design patterns applied only where they earn complexity
- [ ] NOT flagged: coincidental similarity with different responsibilities (wrong abstraction), dogmatic tiny-function/length gates
Apply the full rule catalog from
resources/rubrics/orchestration/maintainability-design-adversarial-rubric.md(D-DUP / D-REUSE / D-BLOAT / D-SMELL / D-SOLID / D-PATTERN / D-CLEAN). Genuine duplication/bloat → P1 (blocks merge); reuse/refactor suggestions → P3 (advisory). Honor the Metz "change together for the same reason" guardrail.
rules/platform-conventions.md for HIG/Material complianceskills/review-gates.md for two-stage review processresources/rubrics/orchestration/maintainability-design-adversarial-rubric.md for the senior maintainability/design rule catalog (duplication, reuse, bloat, smells, SOLID)skills/clean-code.md for the implementer-side authoring contract