fec-accessibility-chec…
Use when reviewing or improving frontend accessibility, semantic structure, keyboard support, focus management, ARIA labels,…
@bovinphangInstall SkillDevelopment
Skill
/fec-refactoring
Use when restructuring existing frontend code while preserving observable behavior, including responsibility extraction, module movement, conditional simplification, API cleanup, or data organization. Do not use for new feature behavior, behavior-changing bug fixes, dependency
Claude Code
$ npx -y skills add bovinphang/frontend-craft --skill fec-refactoring --agent claude-code
Codex
$ npx skills add bovinphang/frontend-craft --skill fec-refactoring -a codex -y
Cursor
$ npx skills add bovinphang/frontend-craft --skill fec-refactoring -a cursor -y
Gemini CLI
$ npx skills add bovinphang/frontend-craft --skill fec-refactoring -a gemini-cli -y
GitHub Copilot
$ npx skills add bovinphang/frontend-craft --skill fec-refactoring -a github-copilot -y
OpenCode
$ npx skills add bovinphang/frontend-craft --skill fec-refactoring -a opencode -y
Windsurf
$ npx skills add bovinphang/frontend-craft --skill fec-refactoring -a windsurf -y
SKILL.md
fec-refactoring.SKILL.mdname: fec-refactoring
description: Use when restructuring existing frontend code while preserving observable behavior, including responsibility extraction, module movement, conditional simplification, API cleanup, or data organization. Do not use for new feature behavior, behavior-changing bug fixes, dependency or framework migrations, or proven dead-code cleanup.
Frontend behavior-preserving refactoring
Follow the [common refactoring method](references/common/refactoring.md): GREEN → REFACTOR → GREEN. Its shared contract defines Behavior Preservation, Green Baseline First, One Refactoring at a Time, Verify Every Step, Revert Before Repairing, and the Diff Budget.
Frontend observable boundaries
Identify props/emits/slots, hooks/composables, DOM, loading/error/empty states, focus/keyboard behavior, routes/URLs, state ownership and object identity, requests, caches, lifecycles, SSR/hydration, exports and dynamic registration.
Frontend risk and scope
Assess authentication, permissions, routing, storage, SSR/hydration, network contracts and architecture-wide state movement by their actual effects. A technique name does not establish SAFE risk.
Domain references
- [Domain evidence and observable contracts](references/principles.md)
- [Frontend validation ladder](references/workflow.md)
- [When to refactor](references/when-to-refactor.md)
- [Boundary with behavior changes](references/refactoring-vs-feature-change.md)
Deliver the common method's PASS, PARTIAL or NOT PROVEN verdict, per-step Diff Budget, executed verification and residual risk.
Read more
name: fec-refactoring description: Use when restructuring existing frontend code while preserving observable behavior, including responsibility extraction, module movement, conditional simplification, API cleanup, or data organization. Do not use for new feature behavior, behavior-changing bug fixes, dependency or framework migrations, or proven dead-code cleanup.
Frontend behavior-preserving refactoring
Follow the [common refactoring method](references/common/refactoring.md): GREEN → REFACTOR → GREEN. Its shared contract defines Behavior Preservation, Green Baseline First, One Refactoring at a Time, Verify Every Step, Revert Before Repairing, and the Diff Budget.
Frontend observable boundaries
Identify props/emits/slots, hooks/composables, DOM, loading/error/empty states, focus/keyboard behavior, routes/URLs, state ownership and object identity, requests, caches, lifecycles, SSR/hydration, exports and dynamic registration.
Frontend risk and scope
Assess authentication, permissions, routing, storage, SSR/hydration, network contracts and architecture-wide state movement by their actual effects. A technique name does not establish SAFE risk.
Domain references
- [Domain evidence and observable contracts](references/principles.md)
- [Frontend validation ladder](references/workflow.md)
- [When to refactor](references/when-to-refactor.md)
- [Boundary with behavior changes](references/refactoring-vs-feature-change.md)
Deliver the common method's PASS, PARTIAL or NOT PROVEN verdict, per-step Diff Budget, executed verification and residual risk.
Stats
23
Stars
3
Forks
Active
Maintenance
TypeScript
Language
MIT
License
Last commit
Created
Ships withfrontend-craft
frontend-craft is a universal frontend plugin that brings the same opinionated engineering standards to all 15 AI coding assistants.
2256 skills14 agents6 MCP
Stars on GitHub
Momentum
- stars in total
- 22
Other skills on frontend-craft.
@bovinphangInstall Skillfec-alchemy
Use when absorbing ideas, capabilities, workflows, architecture, quality systems, ecosystem extensions, or engineering practices…
@bovinphangInstall Skillfec-api-integration
Use when designing, implementing, or reviewing frontend-to-backend API integration, typed API clients, REST/tRPC/OpenAPI client…
@bovinphangInstall Skillfec-backend-requiremen…
Use when frontend work needs to communicate data, action, state, permission, validation, or business-rule needs to backend teams…
@bovinphangInstall Skillfec-browser-storage
Use when choosing, implementing, or reviewing browser storage such as localStorage, sessionStorage, IndexedDB, cookies, client…
@bovinphangInstall Skillfec-canvas-threejs
Use when building or reviewing Canvas 2D, Three.js/WebGL, React Three Fiber, GLSL shaders, ShaderToy-to-WebGL adaptation, 2D/3D…
@bovinphangInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about fec-refactoring.
- Which coding agents can use fec-refactoring?
- fec-refactoring installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.