Agent skill
pmtl-fe-implementation
Frontend implementation rules for PMTL_VN. Use for React or Next.js feature work, UI refactors, and frontend code reviews that should follow repo conventions, human-like code quality, and strict production-ready discipline.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/pmtl-fe-implementation
SKILL.md
PMTL Frontend Implementation
Purpose
Guide day-to-day React and Next.js implementation in PMTL so frontend work stays feature-first, type-safe, and production-ready.
Use When
- Adding or refactoring frontend features in
apps/web. - Updating client/server boundaries, component structure, or fetch flows.
- Reviewing whether a frontend change follows PMTL implementation habits.
Required Inputs
- touched route, feature folder, or component boundary
- current owner docs when the surface already exists
- verification scope expected after the edit
Expected Output
- Frontend code placed in the right layer with clear domain ownership.
- No placeholder branches, weak typing, or accidental client-side sprawl.
Read First
AGENTS.mddesign/ui/PAGE_INVENTORY.mdwhen route or page purpose mattersdesign/ui/USER_FLOWS.mdwhen the work changes journey behaviordesign/ui/COMPONENT_SPECS.mdor module owner docs when component or domain rules already exist
Execution Approach
- Inspect the existing feature folder before creating new abstractions.
- Default to Server Components and only move to the client when interactivity requires it.
- Keep data contracts typed and validated close to the boundary.
- Finish with a verification pass through the quality gate.
Core rules
- Default to Server Components. Add
"use client"only for real interactivity. - Reuse existing feature folders before creating new shared abstractions.
- Keep code flat with early returns and domain naming.
- Never ship
TODO, placeholder comments, or half-finished state branches. - Validate API inputs and responses with Zod-backed shapes.
- Avoid
any. Use narrow unions and explicit types. - Trigger independent async work in parallel.
- Add concise comments only when the reason is not obvious from the code.
File placement
- Route entrypoints:
apps/web/src/app - Feature code:
apps/web/src/features/<domain> - Shared web utilities:
apps/web/src/lib - Shared UI primitives:
apps/web/src/components
Verification
- Run
py infra/tools/codex_actions.py quality-gate --scope webafter meaningful changes. - Recheck that the final file placement still respects feature-first boundaries.
- If the change touched route behavior, compare the implemented surface against the relevant
design/ui/*owner docs. - If the change touched auth/search/runtime boundaries, pair with the narrower verification skill instead of relying on web-only checks.
Edge Cases
- Quick fixes often leak business logic into route files or shared UI.
- Over-eager client components usually indicate missing server-first design, not a requirement.
References
AGENTS.mddocs/architecture/conventions.mddesign/ui/PAGE_INVENTORY.mddesign/ui/USER_FLOWS.mddesign/ui/COMPONENT_SPECS.mdapps/web/src/features
Pair with
pmtl-ui-behaviorfor accessibility, forms, and state discipline.pmtl-ui-style-systemfor visual direction.vercel-react-best-practiceswhen performance is part of the task.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?