Not in the top 1,000 by GitHub stars
bovinphang/frontend-craft
frontend-craft is a universal frontend plugin that brings the same opinionated engineering standards to all 15 AI coding assistants.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
localized/zh-CN/skills/fec-accessibility-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-alchemy/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-api-integration/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-backend-requirements-handoff/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-browser-storage/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-canvas-threejs/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-code-review/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-code-smells/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-component-testing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-data-fetching/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-debug-framework/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-dependency-upgrade/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-doc-sync/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-drawio-studio/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-e2e-testing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-form-handling/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-image-generation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-implement-from-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-legacy-to-modern-migration/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-legacy-web-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-list-virtualization/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-monorepo-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-motion-interaction/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-nextjs-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-nuxt-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-performance-optimization/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-pwa-implementation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-react-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactor-clean/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-api/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-catalog/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-control/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-data/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-encapsulation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-functions/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-inheritance/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-move-features/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-refactoring-validation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-responsive-layout/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-route-protection/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-security-review/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-source-driven-development/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-state-management/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-storybook-component-doc/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-svg-animation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-tailwind-design-system/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-tdd-workflow/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-testing-strategy/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-typescript-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-ui-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-validation-fix/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-vite-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-vue3-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-web-video-presentation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 5d4478257202
No earlier version was observed for comparison.
localized/zh-CN/skills/fec-web-workers/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-accessibility-check/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-alchemy/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-api-integration/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-backend-requirements-handoff/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-browser-storage/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-canvas-threejs/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-code-review/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-code-smells/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-component-testing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-data-fetching/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-debug-framework/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-dependency-upgrade/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-doc-sync/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-drawio-studio/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-e2e-testing/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-form-handling/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-image-generation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-implement-from-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-legacy-to-modern-migration/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-legacy-web-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-list-virtualization/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-monorepo-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-motion-interaction/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-nextjs-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-nuxt-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-performance-optimization/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-pwa-implementation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-react-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactor-clean/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-api/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-catalog/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-control/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-data/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-encapsulation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-functions/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-inheritance/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-move-features/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-refactoring-validation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-responsive-layout/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-route-protection/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-security-review/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-source-driven-development/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-state-management/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-storybook-component-doc/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-svg-animation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-tailwind-design-system/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-tdd-workflow/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-testing-strategy/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-typescript-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-ui-design/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-validation-fix/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-vite-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-vue3-project-standard/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-web-video-presentation/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 5d4478257202
No earlier version was observed for comparison.
skills/fec-web-workers/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 5d4478257202
No earlier version was observed for comparison.
Verified commit 5d44782572025045a552ff8945b354726eb5d183
git clone --filter=blob:none --no-checkout https://github.com/bovinphang/frontend-craft.git .hotskills/bovinphang-frontend-craft && git -C .hotskills/bovinphang-frontend-craft checkout --detach 5d44782572025045a552ff8945b354726eb5d183
# Copy each selected skill directory from .hotskills/bovinphang-frontend-craft into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/bovinphang/frontend-craft.git .hotskills/bovinphang-frontend-craft && git -C .hotskills/bovinphang-frontend-craft checkout --detach 5d44782572025045a552ff8945b354726eb5d183
# Copy each selected skill directory from .hotskills/bovinphang-frontend-craft into .agents/skills/<skill-name>/Heat
1.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- fec-accessibility-check
localized/zh-CN/skills/fec-accessibility-check - fec-alchemy
localized/zh-CN/skills/fec-alchemy - fec-api-integration
localized/zh-CN/skills/fec-api-integration - fec-backend-requirements-handoff
localized/zh-CN/skills/fec-backend-requirements-handoff - fec-browser-storage
localized/zh-CN/skills/fec-browser-storage - fec-canvas-threejs
localized/zh-CN/skills/fec-canvas-threejs - fec-code-review
localized/zh-CN/skills/fec-code-review - fec-code-smells
localized/zh-CN/skills/fec-code-smells - fec-component-testing
localized/zh-CN/skills/fec-component-testing - fec-data-fetching
localized/zh-CN/skills/fec-data-fetching - fec-debug-framework
localized/zh-CN/skills/fec-debug-framework - fec-dependency-upgrade
localized/zh-CN/skills/fec-dependency-upgrade - fec-doc-sync
localized/zh-CN/skills/fec-doc-sync - fec-drawio-studio
localized/zh-CN/skills/fec-drawio-studio - fec-e2e-testing
localized/zh-CN/skills/fec-e2e-testing - fec-form-handling
localized/zh-CN/skills/fec-form-handling - fec-image-generation
localized/zh-CN/skills/fec-image-generation - fec-implement-from-design
localized/zh-CN/skills/fec-implement-from-design - fec-legacy-to-modern-migration
localized/zh-CN/skills/fec-legacy-to-modern-migration - fec-legacy-web-standard
localized/zh-CN/skills/fec-legacy-web-standard - fec-list-virtualization
localized/zh-CN/skills/fec-list-virtualization - fec-monorepo-project-standard
localized/zh-CN/skills/fec-monorepo-project-standard - fec-motion-interaction
localized/zh-CN/skills/fec-motion-interaction - fec-nextjs-project-standard
localized/zh-CN/skills/fec-nextjs-project-standard - fec-nuxt-project-standard
localized/zh-CN/skills/fec-nuxt-project-standard - fec-performance-optimization
localized/zh-CN/skills/fec-performance-optimization - fec-pwa-implementation
localized/zh-CN/skills/fec-pwa-implementation - fec-react-project-standard
localized/zh-CN/skills/fec-react-project-standard - fec-refactor-clean
localized/zh-CN/skills/fec-refactor-clean - fec-refactoring
localized/zh-CN/skills/fec-refactoring - fec-refactoring-api
localized/zh-CN/skills/fec-refactoring-api - fec-refactoring-catalog
localized/zh-CN/skills/fec-refactoring-catalog - fec-refactoring-control
localized/zh-CN/skills/fec-refactoring-control - fec-refactoring-data
localized/zh-CN/skills/fec-refactoring-data - fec-refactoring-encapsulation
localized/zh-CN/skills/fec-refactoring-encapsulation - fec-refactoring-functions
localized/zh-CN/skills/fec-refactoring-functions - fec-refactoring-inheritance
localized/zh-CN/skills/fec-refactoring-inheritance - fec-refactoring-move-features
localized/zh-CN/skills/fec-refactoring-move-features - fec-refactoring-validation
localized/zh-CN/skills/fec-refactoring-validation - fec-responsive-layout
localized/zh-CN/skills/fec-responsive-layout - fec-route-protection
localized/zh-CN/skills/fec-route-protection - fec-security-review
localized/zh-CN/skills/fec-security-review - fec-source-driven-development
localized/zh-CN/skills/fec-source-driven-development - fec-state-management
localized/zh-CN/skills/fec-state-management - fec-storybook-component-doc
localized/zh-CN/skills/fec-storybook-component-doc - fec-svg-animation
localized/zh-CN/skills/fec-svg-animation - fec-tailwind-design-system
localized/zh-CN/skills/fec-tailwind-design-system - fec-tdd-workflow
localized/zh-CN/skills/fec-tdd-workflow - fec-testing-strategy
localized/zh-CN/skills/fec-testing-strategy - fec-typescript-project-standard
localized/zh-CN/skills/fec-typescript-project-standard - fec-ui-design
localized/zh-CN/skills/fec-ui-design - fec-validation-fix
localized/zh-CN/skills/fec-validation-fix - fec-vite-project-standard
localized/zh-CN/skills/fec-vite-project-standard - fec-vue3-project-standard
localized/zh-CN/skills/fec-vue3-project-standard - fec-web-video-presentation
localized/zh-CN/skills/fec-web-video-presentation - fec-web-workers
localized/zh-CN/skills/fec-web-workers - fec-accessibility-check
skills/fec-accessibility-check - fec-alchemy
skills/fec-alchemy - fec-api-integration
skills/fec-api-integration - fec-backend-requirements-handoff
skills/fec-backend-requirements-handoff - fec-browser-storage
skills/fec-browser-storage - fec-canvas-threejs
skills/fec-canvas-threejs - fec-code-review
skills/fec-code-review - fec-code-smells
skills/fec-code-smells - fec-component-testing
skills/fec-component-testing - fec-data-fetching
skills/fec-data-fetching - fec-debug-framework
skills/fec-debug-framework - fec-dependency-upgrade
skills/fec-dependency-upgrade - fec-doc-sync
skills/fec-doc-sync - fec-drawio-studio
skills/fec-drawio-studio - fec-e2e-testing
skills/fec-e2e-testing - fec-form-handling
skills/fec-form-handling - fec-image-generation
skills/fec-image-generation - fec-implement-from-design
skills/fec-implement-from-design - fec-legacy-to-modern-migration
skills/fec-legacy-to-modern-migration - fec-legacy-web-standard
skills/fec-legacy-web-standard - fec-list-virtualization
skills/fec-list-virtualization - fec-monorepo-project-standard
skills/fec-monorepo-project-standard - fec-motion-interaction
skills/fec-motion-interaction - fec-nextjs-project-standard
skills/fec-nextjs-project-standard - fec-nuxt-project-standard
skills/fec-nuxt-project-standard - fec-performance-optimization
skills/fec-performance-optimization - fec-pwa-implementation
skills/fec-pwa-implementation - fec-react-project-standard
skills/fec-react-project-standard - fec-refactor-clean
skills/fec-refactor-clean - fec-refactoring
skills/fec-refactoring - fec-refactoring-api
skills/fec-refactoring-api - fec-refactoring-catalog
skills/fec-refactoring-catalog - fec-refactoring-control
skills/fec-refactoring-control - fec-refactoring-data
skills/fec-refactoring-data - fec-refactoring-encapsulation
skills/fec-refactoring-encapsulation - fec-refactoring-functions
skills/fec-refactoring-functions - fec-refactoring-inheritance
skills/fec-refactoring-inheritance - fec-refactoring-move-features
skills/fec-refactoring-move-features - fec-refactoring-validation
skills/fec-refactoring-validation - fec-responsive-layout
skills/fec-responsive-layout - fec-route-protection
skills/fec-route-protection - fec-security-review
skills/fec-security-review - fec-source-driven-development
skills/fec-source-driven-development - fec-state-management
skills/fec-state-management - fec-storybook-component-doc
skills/fec-storybook-component-doc - fec-svg-animation
skills/fec-svg-animation - fec-tailwind-design-system
skills/fec-tailwind-design-system - fec-tdd-workflow
skills/fec-tdd-workflow - fec-testing-strategy
skills/fec-testing-strategy - fec-typescript-project-standard
skills/fec-typescript-project-standard - fec-ui-design
skills/fec-ui-design - fec-validation-fix
skills/fec-validation-fix - fec-vite-project-standard
skills/fec-vite-project-standard - fec-vue3-project-standard
skills/fec-vue3-project-standard - fec-web-video-presentation
skills/fec-web-video-presentation - fec-web-workers
skills/fec-web-workers
How it works
fec-accessibility-check
When your agent uses it
用于审查或改进前端无障碍、语义结构、键盘支持、焦点管理、ARIA 标签、屏幕阅读器行为、WCAG 2.2 问题、触控无障碍或辅助技术回归;中文触发词包括 无障碍、accessibility、a11y、WCAG、屏幕阅读器。
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
683 tokensWhen the skill is activated
Reference documents
590 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
../../../../.claude-plugin/marketplace.jsonasset2,955 bytes../../../../.claude-plugin/plugin.jsonasset796 bytes../../../../hooks/hooks.jsonasset2,280 bytes../../../../hooks/hooks.jsonasset2,280 bytes../../../../hooks/hooks.jsonasset2,280 bytes../../../../hooks/hooks.jsonasset2,280 bytes../../../../hooks/hooks.jsonasset2,280 bytes../../../../hooks/hooks.jsonasset2,280 bytes../../../../hooks/hooks.jsonasset2,280 bytesSKILL.mdcore2,524 bytesreferences/report-template.mddoc486 bytesreferences/screen-reader-testing.mddoc1,594 bytes
Read SKILL.md
# 无障碍实现规范(WCAG 2.2 AA)
## 用途
确保前端 UI 对残障用户可访问,满足 WCAG 2.2 AA 的核心要求,并能被键盘、屏幕阅读器、触控和缩放用户稳定使用。
## 流程
1. 检查语义结构:landmark、标题层级、表单 label、按钮/链接可访问名称、表格语义和图片 alt。
2. 检查键盘路径:Tab 顺序、Enter/Space/Esc 行为、焦点可见、关闭后焦点恢复。
3. 检查复杂组件:对话框、菜单、标签页、树、抽屉、表格和自定义控件的 ARIA 状态。
4. 检查动态状态:loading、empty、error、toast 和异步更新需要被屏幕阅读器感知。
5. 检查视觉与触控可读性:文本/背景对比、focus ring、缩放到 200%、减少动效偏好、触摸目标尺寸和移动端虚拟键盘行为。
6. 用真实键盘路径复核关键流程,必要时补充屏幕阅读器或浏览器无障碍树观察;屏幕阅读器流程见 [references/screen-reader-testing.md](references/screen-reader-testing.md)。View the complete source on GitHubfec-alchemy
When your agent uses it
用于从参考系统中吸收想法、能力、工作流、架构、质量体系、生态扩展或工程实践,并通过原创的项目内重设计转化为当前项目能力,而不是复制原实现。
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,168 tokensWhen the skill is activated
Reference documents
2,647 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
- 详细参考
Files
SKILL.mdcore4,568 bytesassets/absorption-plan-template.mddoc815 bytesassets/intake-template.mddoc1,420 bytesassets/review-checklist.mddoc1,055 bytesreferences/methodology.mddoc4,227 bytesreferences/originality-and-licensing.mddoc2,075 bytes
Read SKILL.md
# 项目吸收与原创化融合
## 用途
将一个或多个参考系统中的优秀思想、能力和工程实践,转化为当前项目中原创、可维护、符合目标项目风格的改进。
适用于吸收、借鉴、对标、迁移或融合另一个代码库、产品、框架、库、服务、CLI、插件、文档体系、AI/Agent 工具链、架构或工程工作流。普通 Bug 修复、单独 API 使用问题或直接文件格式转换不应使用本 Skill,除非用户明确要求项目级吸收或适配。
## 流程
1. 明确目标和参考系统:
- 将当前仓库视为目标系统,它的架构、命名、测试、发布模型和维护边界是事实来源。
- 将外部仓库、上传压缩包、文档、示例、产品描述或运行体验视为参考系统,它们只提供证据和启发。
- 识别吸收范围:产品能力、架构模式、领域模型、接口协议、数据流、运行时行为、开发体验、质量体系、交付流程、文档知识或生态扩展。View the complete source on GitHubfec-api-integration
When your agent uses it
用于设计、实现或审查前后端 API 集成、类型化 API client、REST/tRPC/OpenAPI 客户端选型、认证刷新、API 错误映射、上传流程、SSE/WebSocket/轮询选择、CORS 相关前端行为或跨边界 loading/error 状态。不要用于纯后端服务架构或仅 TanStack Query 缓存策略;中文触发词包括 API 集成、前后端联调、typed API client、接口错误处理、SSE、WebSocket。
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
1,285 tokensWhen the skill is activated
Reference documents
633 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore4,904 bytesreferences/integration-patterns.mddoc2,566 bytes
Read SKILL.md
# API 集成
适用于前端与后端边界的类型、错误、鉴权、上传、实时通信和用户状态设计。需要具体代码模式时加载 [integration-patterns.md](references/integration-patterns.md)。
## 用途
规范前端 API 集成边界,让请求、错误、鉴权和实时数据可维护。
## 流程
1. 明确接口所有权
- 同团队 TypeScript 全栈可考虑 tRPC 或共享 schema。
- 多语言或多消费者 API 优先 OpenAPI/GraphQL codegen。
- 小型内部应用可用 typed fetch wrapper,但类型必须集中维护。View the complete source on GitHubfec-backend-requirements-handoff
When your agent uses it
用于前端工作需要向后端团队说明数据、动作、状态、权限、校验或业务规则需求,但不指定端点设计、字段名、数据库形态或实现细节;中文触发词包括 前后端需求交接、后端需求、API 需求澄清、数据需求说明。
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
667 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore2,715 bytes
Read SKILL.md
# 前后端需求交接
## 用途
把前端页面和交互所需的数据、动作、状态和疑问整理成后端可讨论的需求说明。
## 流程
1. 明确功能上下文
- 说明页面、流程或组件是什么,面向哪类用户,以及用户完成任务的成功状态。
- 如果已有设计稿、路由、用户故事或权限角色,先把它们作为事实来源。
2. 描述前端展示需求
- 按屏幕或组件列出需要展示的信息、信息之间的关系、排序/过滤/分页需求和可见性规则。View the complete source on GitHubfec-browser-storage
When your agent uses it
用于选择、实现或审查 localStorage、sessionStorage、IndexedDB、cookie、客户端持久化、离线数据、安全存储或清理策略等浏览器存储方案;中文触发词包括 浏览器存储、客户端持久化。
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
431 tokensWhen the skill is activated
Reference documents
527 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore1,694 bytesreferences/storage-patterns.mddoc1,874 bytes
Read SKILL.md
# 浏览器存储
## 用途
根据数据大小、安全要求和生命周期选择合适的客户端存储方案。
## 流程
1. 先判断数据敏感度、体积、生命周期、是否需要跨 Tab、是否需要随请求发送。
2. 小量非敏感偏好用 localStorage;Tab 级临时数据用 sessionStorage;大量结构化数据或离线缓存用 IndexedDB;认证态优先 httpOnly cookie。
3. 封装统一 key 前缀、JSON parse/stringify、异常处理、过期清理和 quota 兜底。
4. 敏感数据按安全规则处理,不把明文 token、密码、信用卡信息放进可被 JS 读取的存储。
5. 审查隐私模式、存储配额、清理策略和跨浏览器兼容性。
View the complete source on GitHubfec-canvas-threejs
When your agent uses it
用于构建或审查 Canvas 2D、Three.js/WebGL、React Three Fiber、GLSL shader、ShaderToy 到 WebGL 适配、2D/3D 可视化、游戏渲染、动画循环、GPU 资源清理或渲染性能。不要用于标准 DOM UI、已有图表库覆盖的图表或非图形类性能工作;中文触发词包括 Canvas、Three.js、WebGL、GLSL、Shader、3D、数据可视化、游戏。
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
898 tokensWhen the skill is activated
Reference documents
1,307 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 核心模式
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore3,285 bytesreferences/rendering-patterns.mddoc1,715 bytesreferences/shader-webgl-patterns.mddoc2,723 bytes
Read SKILL.md
# Canvas 与 Three.js
## 用途
在浏览器中实现高性能 2D/3D 图形渲染。
## 流程
1. 先选渲染层:标准 UI 用 DOM;简单 2D 图形/签名/粒子用 Canvas 2D;3D 模型、空间交互和复杂粒子用 Three.js/WebGL;React 项目中的声明式 3D 用 React Three Fiber。
2. 为渲染容器定义稳定尺寸、DPI 适配和 resize 行为;Canvas 不会自动随 CSS 清晰缩放。
3. 动画循环使用 `requestAnimationFrame`,不可见或无变化时暂停,卸载时取消。
4. Three.js 必须释放 geometry/material/texture/renderer,并移除事件监听和 observer。
5. Shader/WebGL 任务先识别是 SDF、ray marching、noise、particle、post-processing、multipass 还是调试问题,再决定是否需要原生 WebGL2、Three.js ShaderMaterial 或 R3F。
6. WebGL2 适配时检查 GLSL 版本、入口函数、varying/in-out、texture API、uniform 使用和函数声明顺序,避免白屏只留控制台错误。View the complete source on GitHubfec-code-review
When your agent uses it
用于用户要求通用前端代码评审、PR 评审、合并就绪评估、架构可维护性、类型安全、渲染/状态风险、样式一致性、可测性缺口或横向评审总结时。深度安全、无障碍、E2E 或性能问题应委托对应专项 skill;中文触发词包括 代码审查、代码评审、review。
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
2,410 tokensWhen the skill is activated
Reference documents
320 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 评审模式与覆盖范围
- 用途
- 流程
- 多维评审编排
- 评审维度
- 详细参考
- 约束
- 预期输出
- 重构边界
Files
SKILL.mdcore9,243 bytesreferences/report-template.mddoc1,127 bytes
Read SKILL.md
# 前端代码评审
## 评审模式与覆盖范围
用户明确指定的范围优先于默认行为。采用以下三种审核模式:
- **改动审核**:仅在明确要求或当前任务已明确最近改动、本次修改、暂存区、PR 或提交上下文时,审核这些改动及必要上下文。本地模式在请求范围内检查暂存、未暂存差异及相关未跟踪项目文件;仅要求暂存区时只审核暂存改动。无改动时说明没有可审核的改动,不自动切换到最近提交或扩大范围。
- **指定范围审核**:用户指定文件或目录时,建立范围内文件清单,审核其中现有代码,包括未改动代码;不要求 Git 差异。
- **全项目审核(默认)**:未指定范围或改动上下文,或明确要求审核整个项目时,建立项目自有前端代码、相关测试、配置和依赖声明的清单,再按模块分批审核,包括未改动代码;不要求 Git 差异。
先选择范围,再收集差异。仅指定文件或目录表示全量审核该范围;路径与明确改动请求同时出现时,仅增量审核该路径的改动。未限定的调用即使存在 Git 改动也默认全项目审核。开始审核时说明选定模式和目标范围。修改后自动委托审核时,显式传入本次改动范围,避免无范围调用触发全项目审核。
默认排除依赖目录、构建产物、缓存、生成文件和第三方代码,并记录排除项。保持前端职责边界,不宣称完成后端专项审核。目标不存在或范围内无相关文件时,明确说明,不替换为其他范围。
View the complete source on GitHubfec-code-smells
When your agent uses it
需要在不修改业务代码的前提下诊断既有前端代码的结构性可维护性问题,并要求提供证据、误判检查与候选重构方向时。
What it loads into context
Frontmatter
51 tokensAlways available to the agent
SKILL.md
438 tokensWhen the skill is activated
Reference documents
12,137 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- Finding 输出契约
- 快速索引
- 常见错误
Files
SKILL.mdcore1,514 bytesreferences/detection-guide.mddoc1,371 bytesreferences/smell-catalog.mddoc32,933 bytesreferences/smell-to-refactoring-map.mddoc9,079 bytes
Read SKILL.md
# 代码坏味道诊断
## 概览
基于具体证据诊断结构问题。坏味道是进一步调查的信号,不等于必须修改代码的结论。
## 执行流程
1. 明确分析范围和项目事实。
2. 收集结构、依赖方向、职责和变化耦合证据。
3. 对照[坏味道目录](references/smell-catalog.md)。
4. 执行[误判检查](references/detection-guide.md)。
5. 根据[坏味道到重构手法映射](references/smell-to-refactoring-map.md)报告置信度、影响和候选方案。
6. 如果用户只要求诊断,不修改业务代码。
## Finding 输出契约View the complete source on GitHubfec-component-testing
When your agent uses it
用于编写或审查靠近 UI 代码的前端单元、组件或轻量集成测试,包括 React Testing Library、Vue Test Utils、hooks/composables、props/emits、回调、可访问查询、user-event 交互、mock、loading/error/empty 状态和回归覆盖。若是测试分层规划、真实浏览器旅程或现有验证失败,优先选择对应测试或验证工作流;中文触发词包括 组件测试、组件单测、单元测试、轻量集成测试。
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,207 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore4,580 bytes
Read SKILL.md
# 组件测试
## 用途
用贴近代码和用户行为的测试验证纯逻辑、组件契约与轻量模块协作,减少重构和 UI 交互回归。
## 流程
### 1. 先确定测试层级
- 单元测试:纯函数、hooks/composables、utils、状态逻辑、schema。
- 组件测试:props/emits、回调、用户交互、loading/error/empty、mock 边界。
- 轻量集成测试:表单 + API mock + Router/Store/Provider 上下文。
View the complete source on GitHubfec-data-fetching
When your agent uses it
用于实现或审查前端服务端状态流程:类型化查询、请求缓存、失效、mutation、乐观更新、无限查询、预取、SSR hydration 或 API 层整合。不要用于本地 UI 状态或 Service Worker 缓存;中文触发词包括 数据获取、缓存、乐观更新。
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
721 tokensWhen the skill is activated
Reference documents
1,007 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- React 快速开始
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore2,843 bytesreferences/query-patterns.mddoc3,748 bytes
Read SKILL.md
# Server State 数据获取
## 用途
为前端 server state 建立清晰的数据获取、缓存、失效和提交边界,避免请求状态散落在页面组件中。
## 流程
1. 判断状态来源:来自服务端且需要缓存、去重、刷新、分页或 mutation 时使用请求缓存方案;纯本地 UI 状态用组件 state 或 store。
2. 先沿用项目已有数据获取库;新增依赖时 React/Vue/Solid/Svelte 可考虑 TanStack Query,也可沿用 SWR、Nuxt/Nitro 数据获取或项目封装。
3. 设计稳定 cache key/query key:结构包含实体、动作和所有影响结果的参数。
4. API 函数保持纯请求函数,数据 hook/composable 负责缓存、select、loading/error/empty 状态。
5. mutation 成功后 invalidation;需要即时反馈时使用 optimistic update 并在失败时回滚。
View the complete source on GitHubfec-debug-framework
When your agent uses it
用于诊断前端构建失败、运行时错误、UI 异常、API/数据问题、白屏、请求失败或难以解释的线上异常;中文触发词包括 调试、debug、排查、定位、报错、异常、白屏、请求失败。
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
1,372 tokensWhen the skill is activated
Reference documents
364 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 诊断模块
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore4,880 bytesreferences/report-template.mddoc1,178 bytes
Read SKILL.md
# 前端诊断框架
## 用途
用证据驱动的分类、收集、假设、验证和修复流程定位前端故障,避免凭直觉扩大改动范围。
## 流程
所有前端问题诊断遵循统一流程:
### Step 1: 分类(Classify)
识别问题类型和影响范围:
View the complete source on GitHubfec-dependency-upgrade
When your agent uses it
用于规划、实现或审查前端依赖升级、包迁移、lockfile 变更、框架大版本升级、CVE 修复、peer dependency 冲突、ESM/CJS 切换、构建工具兼容性或 CI 验证矩阵;中文触发词包括 依赖升级、版本升级、lockfile、peer dependency、CVE 修复、大版本迁移。
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
610 tokensWhen the skill is activated
Reference documents
491 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore2,314 bytesreferences/dependency-upgrade-workflow.mddoc1,740 bytes
Read SKILL.md
# 依赖升级
适用于前端依赖升级、漏洞修复、大版本迁移和 lockfile 风险评审。需要具体流程和检查清单时加载 [references/dependency-upgrade-workflow.md](references/dependency-upgrade-workflow.md)。
## 用途
用来源驱动和小批验证的方式升级依赖,降低破坏性变更、供应链风险和 CI 回归。
## 流程
1. 建立事实基线:读取 package manager、lockfile、Node 版本、workspace 范围、CI 命令和当前验证状态。
2. 分类升级目标:安全修复、补丁升级、小版本升级、大版本迁移、框架迁移、构建工具迁移或依赖清理。
3. 查证来源:对版本敏感的库读取官方 release notes、migration guide、peer dependency、Node/browser 支持和弃用项。
4. 拆小批次:安全补丁可集中处理;大版本、构建工具、框架和测试工具必须单独批次验证。View the complete source on GitHubfec-doc-sync
When your agent uses it
用于根据 package.json、lockfile、配置、env 示例、路由、API client 或 server routes、schema、组件、测试、CI、构建/部署配置、ADR、changelog 或迁移说明等事实源同步前端项目文档。不要用于单纯润色普通文案;中文触发词包括 文档同步、更新 README、docs sync、环境变量文档、命令清单、API 文档同步。
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
899 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore3,510 bytes
Read SKILL.md
# 文档同步
## 用途
从代码、配置、测试、类型、脚本和运行时模板同步前端项目文档,避免 README、docs、环境变量说明、API/路由说明、架构决策和迁移说明与实际项目行为漂移。
## 流程
1. 识别项目栈、文档入口和本次需要同步的范围;README 同步必须扫描根目录 `README*`、`docs/*/README*`、包、应用、部署或运行时相关 README,并排除 `node_modules`、构建产物和第三方依赖目录。
2. 收集事实来源:`package.json`、lockfile、框架和构建配置、`.env.example`、路由、API clients 或 server routes、types/schemas、组件、测试、CI、build/deploy config。
3. 比对 README、docs、ADR、changelog、example prompts、setup/deploy/env docs 中的命令、环境变量、路由、API 行为、部署步骤和支持矩阵。
4. 只更新稳定的公共约定;不要把临时调试结论、一次性报告或未落地设计写入长期文档。
5. 若仓库已有多语言文档或国际化 README,主 README 的公共事实更新后必须检查其它语言 README 是否需要同步;功能名称、命令名、脚本名、包名、组件/API 名称、报告文件名、路径、环境变量、路由/API 名称、版本约束和支持矩阵必须跨语言一致。
6. 产品文案可保持本地化表达,但不得保留旧事实、旧默认推荐或过期示例;无法高质量翻译时,至少同步关键事实,并在输出中标出人工翻译风险。View the complete source on GitHubfec-drawio-studio
When your agent uses it
用于创建带 draw.io / diagrams.net 源文件的可编辑技术图,包括架构图、ERD、UML、序列图、流程图、ML 模型图、官方形状检索、品牌符号、Graphviz 自动布局、代码结构图、.drawio 校验或 draw.io CLI 导出兜底。不要用于普通位图生成、手绘草图、交互式 Canvas/Three.js 场景或装饰性 SVG 动画;中文触发词包括 draw.io、diagrams.net、可编辑架构图、.drawio、ER 图、UML、序列图、自动布局、形状检索、代码结构图。
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
1,764 tokensWhen the skill is activated
Reference documents
4,386 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 工具资源
- 约束
- 预期输出
Scripts executed separately
scripts/brand-symbols.mjsscripts/diagram-lint.mjsscripts/diagram-url.mjsscripts/drawio-export.mjsscripts/layout-graph.mjsscripts/png-embed-fix.mjsscripts/scan-go-packages.mjsscripts/scan-js-modules.mjsscripts/scan-python-classes.mjsscripts/scan-python-modules.mjsscripts/scan-rust-modules.mjsscripts/scan-ts-modules.mjsscripts/shape-query.mjsscripts/studio-core.mjs../../../../skills/fec-drawio-studio/scripts/png-embed-fix.mjs../../../../skills/fec-drawio-studio/scripts/png-embed-fix.mjs
Files
SKILL.mdcore6,319 bytesSKILL.mdcore6,319 bytesSKILL.mdcore6,319 bytesSKILL.mdcore6,319 bytesdata/THIRD_PARTY_NOTICES.mddoc880 bytesdata/brand-icons.jsonasset12,919 bytesdata/shape-index.jsonasset4,776,086 bytesreferences/data-residency.mddoc1,823 bytesreferences/diagram-patterns.mddoc2,651 bytesreferences/flowchart-quality.mddoc2,963 bytesreferences/layout-and-export.mddoc2,566 bytesreferences/troubleshooting.mddoc1,171 bytesreferences/xml-and-mermaid.mddoc3,634 bytesscripts/brand-symbols.mjsruns4,181 bytesscripts/diagram-lint.mjsruns9,942 bytesscripts/diagram-url.mjsruns3,480 bytesscripts/drawio-export.mjsruns4,479 bytesscripts/layout-graph.mjsruns4,476 bytesscripts/png-embed-fix.mjsruns1,102 bytesscripts/scan-go-packages.mjsruns1,846 bytesscripts/scan-js-modules.mjsruns2,254 bytesscripts/scan-python-classes.mjsruns1,440 bytesscripts/scan-python-modules.mjsruns2,227 bytesscripts/scan-rust-modules.mjsruns1,777 bytesscripts/scan-ts-modules.mjsruns357 bytesscripts/shape-query.mjsruns3,561 bytesscripts/studio-core.mjsruns4,479 bytesstyles/built-in/corporate.jsonasset1,471 bytesstyles/built-in/default.jsonasset1,454 bytesstyles/built-in/handdrawn.jsonasset1,474 bytesstyles/schema.jsonasset3,949 bytes../../../../skills/fec-drawio-studio/scripts/png-embed-fix.mjsruns1,102 bytes../../../../skills/fec-drawio-studio/scripts/png-embed-fix.mjsruns1,102 bytes
Read SKILL.md
# 可编辑技术图表工作流
## 用途
生成、校验和导出可继续编辑的 draw.io / diagrams.net 技术图表。
## 流程
1. 判断图表路线
- 需要长期维护在 Markdown 中的简单图,优先 Mermaid。
- 需要官方图标、泳道、复杂布局、层/标签/元数据、可编辑 PNG/SVG/PDF 或 `.drawio` 源时,使用本工作流。
- 需要快速浏览器打开或分享时,用 [diagram-url.mjs](scripts/diagram-url.mjs) 生成 URL;需要本地可审计交付时,始终保存 `.drawio` 源。
- 用户已经有 Mermaid 或 CSV 内容时,可用 `diagram-url.mjs --create --type mermaid|csv` 交给 diagrams.net 导入;需要长期维护或精确形状时,再转成 XML。
- 如果当前宿主已经配置 draw.io MCP App/Tool,可把它作为预览或编辑入口;本 skill 不要求安装 MCP server。View the complete source on GitHubfec-e2e-testing
When your agent uses it
用于创建、维护、调试或审查真实浏览器端到端测试,包括 Playwright/Cypress、Page Object、CI 产物、trace、不稳定用例、跨页面视觉回归以及登录、支付、权限或 CRUD 等关键用户旅程。若是测试层规划或靠近 UI 组件的测试,先选择对应测试工作流;中文触发词包括 E2E、端到端测试、Playwright、Cypress。
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
752 tokensWhen the skill is activated
Reference documents
2,026 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore2,900 bytesreferences/e2e-ci-reporting.mddoc1,398 bytesreferences/e2e-special-scenarios.mddoc1,751 bytesreferences/e2e-visual-regression.mddoc1,940 bytesreferences/playwright-patterns.mddoc2,280 bytes
Read SKILL.md
# E2E 测试规范
## 用途
用真实浏览器验证关键用户旅程,发现单元测试无法覆盖的集成风险。
## 流程
1. 明确关键旅程:登录、购买、创建、搜索、权限、支付等跨页面流程优先;若只是选择测试层级,先做测试分层规划。
2. 新项目优先 Playwright;已有 Cypress 项目沿用 Cypress,不为迁移而迁移。
3. 用 Page Object 或 fixtures 封装登录、页面定位器和共享数据,spec 中避免裸选择器。
4. 断言用户可见结果,依赖 Locator 自动等待、网络响应或可见状态,不使用固定 sleep。
5. CI 必须上传 HTML report、截图、trace 或视频;flaky 用例要隔离、复现、标注来源并关联 issue。
6. 调试失败时先读 trace、console、network 和截图,再改测试;不要把真实产品缺陷误判成 flaky。View the complete source on GitHubfec-form-handling
When your agent uses it
用于构建或审查较复杂表单,包括 React Hook Form、Zod schema、类型化校验、动态字段、受控第三方输入、文件上传、多步骤流程、依赖校验或表单性能。不要用于没有校验的 1-3 个字段小表单;中文触发词包括 表单、表单校验、动态字段。
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
891 tokensWhen the skill is activated
Reference documents
1,133 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- React 快速开始
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore3,397 bytesreferences/advanced-form-patterns.mddoc4,037 bytes
Read SKILL.md
# 表单处理
## 用途
管理表单状态、校验和提交,避免复杂表单输入卡顿。
## 流程
1. 先识别框架、项目既有表单库、schema 校验库、组件库和复杂度;10+ 字段、动态字段、联动校验、文件上传、多步流程或输入卡顿时再引入专门表单方案。
2. 按项目栈选型:React 可考虑 React Hook Form + Zod;Vue 可考虑 vee-validate / FormKit + Zod、Yup 或 Valibot;简单表单可用框架原生状态和基础校验。
3. 用运行时 schema 或明确校验函数守住外部输入边界;TypeScript 类型可从 schema 推导,但不要只写 TS 类型。
4. 明确默认值、字段注册、受控/非受控边界和组件库适配;错误提示用 `aria-invalid`、`aria-describedby` 和 `role="alert"`。
5. 提交时处理 loading、服务端错误、重复提交和 reset;大型表单用局部订阅和子组件隔离控制重渲染。
View the complete source on GitHubfec-image-generation
When your agent uses it
用于生成或编辑图表、图形资产、海报、UI 样机、产品图、信息图、学术图、漫画、头像、分镜、品牌板或图像编辑工作流,尤其是导出 PNG 需要视觉质检和有限自动修复时。文字密集图表优先使用确定性的 Mermaid/SVG/HTML/canvas 源;浏览器可打开的技术图优先使用 HTML technical diagrams,覆盖系统蓝图、架构图、部署拓扑、Agent runtime、memory flow、before-after architecture、流程、序列、数据流、生命周期、runbook、PII/数据血缘和状态机;不要用于不涉及生成图像的普通 UI 打磨。中文触发词包括 图片生成、图像编辑、图表生成、架构图、系统蓝图、部署拓扑、Agent runtime、memory flow、before-after architecture、工作流图、数据流、生命周期图、状态机、ER 图、UML、序列图、海报、UI 样机、产品图、信息图、学术图、漫画、头像、分镜、品牌板、PNG 自检、自动修复。
What it loads into context
Frontmatter
261 tokensAlways available to the agent
SKILL.md
2,696 tokensWhen the skill is activated
Reference documents
7,809 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
- 技术图质量与工具路由
Scripts executed separately
scripts/diagram-browser.mjsscripts/diagram-layout.mjsscripts/export-diagram.mjsscripts/interactive-diagram-server.mjsscripts/mermaid-render.mjsscripts/png-qa.mjsscripts/tech-diagram-render.mjs../../../../skills/fec-image-generation/scripts/export-diagram.mjs../../../../skills/fec-image-generation/scripts/export-diagram.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs../../../../skills/fec-image-generation/scripts/png-qa.mjs
Files
SKILL.mdcore10,180 bytesSKILL.mdcore10,180 bytesSKILL.mdcore10,180 bytesSKILL.mdcore10,180 bytesSKILL.mdcore10,180 bytesSKILL.mdcore10,180 bytesSKILL.mdcore10,180 bytesassets/interactive-diagram.htmlasset16,545 bytesassets/quality-examples/README.mddoc1,564 bytesassets/quality-examples/architecture.jsonasset2,342 bytesassets/quality-examples/invalid-explicit.jsonasset644 bytesassets/quality-examples/sequence.jsonasset1,042 bytesassets/quality-examples/sequence.mmdasset621 bytesassets/quality-examples/workflow.jsonasset1,782 bytesassets/quality-examples/workflow.mmdasset351 bytesreferences/artifact-routing.mddoc4,061 bytesreferences/diagram-workflows.mddoc6,474 bytesreferences/html-technical-diagrams.mddoc12,828 bytesreferences/png-qa-autofix.mddoc2,761 bytesscripts/diagram-browser.mjsruns7,798 bytesscripts/diagram-layout.mjsruns11,134 bytesscripts/export-diagram.mjsruns13,100 bytesscripts/interactive-diagram-server.mjsruns22,650 bytesscripts/mermaid-render.mjsruns4,615 bytesscripts/png-qa.mjsruns19,638 bytesscripts/tech-diagram-render.mjsruns65,222 bytes../../../../skills/fec-image-generation/scripts/export-diagram.mjsruns13,100 bytes../../../../skills/fec-image-generation/scripts/export-diagram.mjsruns13,100 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes../../../../skills/fec-image-generation/scripts/png-qa.mjsruns19,638 bytes
Read SKILL.md
# 图片生成与图表工作流
## 用途
生成或编辑图表、视觉资产和图片工作流,并对导出的 PNG 做可复查的自检与修复迭代。
## 流程
1. 判断产物类型
- 文本、结构和连线准确性优先时,用 Mermaid、SVG、HTML/CSS、canvas 或图表库生成可编辑源,再导出 PNG。
- 需要单文件浏览器打开、暗/亮主题和结构化 QA 的系统蓝图、架构图、部署拓扑、Agent runtime、memory flow、before-after architecture、流程、序列、数据流、生命周期、runbook、状态机或 PII/数据血缘图时,使用 HTML technical diagrams。
- 流程地图、审批流、自动化运行、异常路径和循环运营流需要清晰的起止节点、决策、参与者、步骤编号和摘要,但不需要 diagrams.net 时,在 Mermaid 不可用或明确需要浏览器泳道/主题交付时,使用兼容 HTML `workflow` 路线。
- 系统、Agent、memory、数据或 tool-call 图需要语义节点形状、有含义的连线和可浏览器打开、可导出、可 QA 的源文件时,使用主题化 HTML technical diagrams。
- 用户需要在本地浏览器里看到节点和连线实时出现,或需要在会话中拖拽、改标签、删除、缩放并快速导出草图时,使用交互式实时图表路线。View the complete source on GitHubfec-implement-from-design
When your agent uses it
用于根据 Figma、Sketch、MasterGo、Pixso、墨刀、摹客、截图、设计选区、设计 Token 或设计转代码任务实现生产级前端组件/页面;中文触发词包括 设计稿、按设计实现。
What it loads into context
Frontmatter
66 tokensAlways available to the agent
SKILL.md
1,644 tokensWhen the skill is activated
Reference documents
184 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 支持的设计工具
- 目标
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore6,199 bytesreferences/design-plan-template.mddoc603 bytes
Read SKILL.md
# 按设计稿实现
## 用途
基于设计工具(Figma、Sketch、MasterGo、Pixso、墨刀、摹客)的设计上下文,高保真实现页面或组件,强调组件复用、设计 Token 映射、可访问性和面向生产的前端实现。
## 支持的设计工具
| 工具 | MCP 集成 | 获取设计数据方式 |
| -------- | ------------------------- | ----------------------------------------- |
| Figma | `figma` / `figma-desktop` | API 获取设计结构、变量定义 |
| Sketch | `sketch` | MCP 获取设计选区截图 |
| MasterGo | `mastergo` | API 获取 DSL 结构数据 |
| Pixso | `pixso` | 本地 MCP 获取帧数据和代码 |View the complete source on GitHubfec-legacy-to-modern-migration
When your agent uses it
用于规划或实施从 JavaScript、jQuery、HTML/CSS、服务端渲染模板、MPA 遗留前端代码或旧框架代码迁移到现代前端技术栈,同时保持行为一致。不要用于仍留在旧技术栈内的日常遗留 bug 修复;中文触发词包括 遗留项目、技术栈升级、jQuery 迁移。
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
1,040 tokensWhen the skill is activated
Reference documents
2,946 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore3,897 bytesreferences/migration-execution-checklist.mddoc6,484 bytesreferences/migration-report-template.mddoc670 bytesreferences/migration-strategy-and-mapping.mddoc3,790 bytes
Read SKILL.md
# 传统前端到现代框架迁移
适用于将 JavaScript + jQuery + HTML/CSS 多页面应用(MPA)、服务端模板渲染项目或旧框架代码,渐进迁移到 React、Vue、Next.js、Nuxt、TypeScript,或保留 MPA 形态但现代化模块、构建、类型和测试的场景。
## 用途
指导传统前端项目渐进迁移到目标现代栈,提供迁移策略、概念映射、分阶段步骤和实施约束,确保功能等价和风险可控。
## 流程
1. 先识别目标栈、迁移边界和是否保留 MPA/服务端模板形态。
2. 加载 [references/migration-strategy-and-mapping.md](references/migration-strategy-and-mapping.md),选择渐进式或一次性重写策略,并明确遗留模式到目标栈的映射。
3. 加载 [references/migration-execution-checklist.md](references/migration-execution-checklist.md),完成存量盘点、依赖分析、优先级排序和分阶段迁移计划。
4. 撰写迁移分析或迁移计划报告时,加载 [references/migration-report-template.md](references/migration-report-template.md)。View the complete source on GitHubfec-legacy-web-standard
When your agent uses it
用于维护或安全修改既有非框架前端代码:原生 JavaScript、jQuery、HTML/CSS、MPA 页面、服务端渲染模板、遗留插件或需要长期保持当前技术栈的代码。若是规划迁移到 React/Vue/TypeScript,请使用迁移 skill;中文触发词包括 传统前端、原生 JS、jQuery。
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
521 tokensWhen the skill is activated
Reference documents
449 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore1,868 bytesreferences/legacy-patterns.mddoc1,658 bytes
Read SKILL.md
# 传统前端项目规范(JS + jQuery + HTML)
## 用途
在不重写技术栈的前提下安全维护 vanilla JS、jQuery、HTML/CSS 和服务端模板项目。
## 流程
1. 先确认本次改动是维护旧栈还是迁移;迁移到 React/Vue/TypeScript 时切换到现代化迁移 workflow。
2. 沿用现有架构和代码风格,优先修复问题,不在一次改动中引入多项现代化。
3. JavaScript 用 IIFE/命名空间减少全局污染,事件绑定优先委托到合理容器。
4. DOM 更新缓存选择器、批量操作、转义用户输入;Ajax 必须处理 loading、error、空状态和防重复提交。
5. HTML/CSS 保持语义、label、alt、BEM/既有命名和低选择器深度。
6. 安全重点检查 `.html()`、`innerHTML`、URL 参数渲染、CSRF token 和文件上传。View the complete source on GitHubfec-list-virtualization
When your agent uses it
用于优化或审查大列表、虚拟滚动、windowing、react-window、TanStack Virtual、可变高度行、动态测量、无限滚动、网格虚拟化或滚动性能;中文触发词包括 虚拟列表、大列表优化、滚动性能。
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
512 tokensWhen the skill is activated
Reference documents
994 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore1,797 bytesreferences/virtualization-patterns.mddoc3,606 bytes
Read SKILL.md
# 列表虚拟化优化
## 用途
通过窗口化只渲染可视区域,解决大列表 DOM 过多和滚动卡顿。
## 流程
1. 先确认列表规模和瓶颈:500+ 项、滚动掉帧、DOM 节点过多或内存飙升才引入虚拟化。
2. 先遵循项目现有框架、依赖和设计系统约束,再按场景选库:React 可考虑 `react-window` 或 TanStack Virtual;Vue/Solid/Svelte、动态测量、网格或跨框架场景优先考虑 TanStack Virtual;遗留 `react-virtualized` 只维护不新增。
3. 明确 item size、overscan、容器高度、key、滚动容器和 resize 行为。
4. 无限滚动时分离数据分页和 DOM 虚拟化;数据获取可联用数据获取 workflow。
5. 验证 DOM 节点数、滚动 FPS、键盘/屏幕阅读器体验和 Ctrl+F/SEO 限制。
View the complete source on GitHubfec-monorepo-project-standard
When your agent uses it
用于创建、审查或重构前端 monorepo,包括 pnpm workspace、Turborepo、Nx、多包依赖边界、任务编排、包命名或包发布;中文触发词包括 monorepo、workspace、多包。
What it loads into context
Frontmatter
67 tokensAlways available to the agent
SKILL.md
1,327 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 工具选择
- 目录结构
- 依赖管理
- Turborepo 任务编排
- Nx 任务编排
- 包命名
- 约束
- 预期输出
Files
SKILL.mdcore4,663 bytes
Read SKILL.md
# Monorepo 项目规范
适用于使用 pnpm workspace、Turborepo 或 Nx 的多包前端仓库。
## 用途
规范 Monorepo 项目的目录结构、依赖管理、任务编排和包发布流程,确保多包协作的构建效率和版本一致性。
## 流程
1. 先确认仓库是否已使用 pnpm workspace、Turborepo 或 Nx,并沿用现有包命名与任务约定。
2. 将应用放在 `apps/`,共享库、配置和工具放在 `packages/` 或既有等价目录。
3. 内部依赖使用 `workspace:*`,通过依赖图驱动构建顺序。
4. 为 build、lint、test 配置可缓存、可并行、可增量的根任务,并明确输入、输出和环境变量。View the complete source on GitHubfec-motion-interaction
When your agent uses it
用于设计、实现或审查前端交互动效、页面转场、滚动动画、Framer Motion、GSAP、Lottie、CSS 动画、动效强度、动画性能、减少动效行为或兼具表现力与可访问性的 UI 动效。不要用于仅 SVG 路径绘制、Canvas/WebGL 渲染或普通 hover 状态;中文触发词包括 动效设计、交互动效、页面转场、滚动动画、Framer Motion、GSAP。
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
1,551 tokensWhen the skill is activated
Reference documents
683 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore5,610 bytesreferences/motion-patterns.mddoc2,392 bytes
Read SKILL.md
# 交互动效
适用于需要把页面转场、滚动叙事、组件入场、微交互和反馈节奏设计成可维护、可降级、可验证的前端动效任务。需要具体实现模式时加载 [motion-patterns.md](references/motion-patterns.md)。
## 用途
为前端界面选择合适动效工具、强度和质量门禁。
## 流程
1. 判断动效职责
- 先写清动效服务的用户意图:定位、反馈、层级变化、状态确认、叙事引导或品牌记忆。
- 工具型界面默认克制,优先保障扫描效率;营销页和作品页可增加节奏,但不能遮挡主要信息。
- 若动效只装饰而不改善理解、反馈或品牌识别,应删掉或改成静态视觉处理。View the complete source on GitHubfec-nextjs-project-standard
When your agent uses it
用于创建或审查 Next.js 14+ App Router 项目、文件路由、layout、服务端/客户端组件边界、SSR/SSG/ISR、streaming、metadata、middleware、server actions 或 Next 特定数据获取。通用客户端 React 组件架构另按项目 React 约定处理;中文触发词包括 Next.js、App Router。
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,727 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 项目结构
- 渲染模式
- 数据获取
- 路由与布局
- 中间件
- 元数据与 SEO
- 约束
- 与客户端 UI 模式的分工
- 预期输出
Files
SKILL.mdcore6,276 bytes
Read SKILL.md
# Next.js 项目规范
适用于使用 Next.js 14+ 与 App Router 的仓库。
## 用途
规范 Next.js 14+ 项目中 App Router、SSR/SSG/ISR 渲染模式、数据获取、路由布局、中间件和 SEO 元数据的工程实践,确保服务端优先、性能优化和可维护性。
## 流程
1. 先识别目标属于 App Router、布局、服务端数据、middleware、metadata 还是客户端交互。
2. 默认服务端组件优先;只有需要浏览器 API、交互状态或事件处理时才使用 `'use client'`。
3. 明确 SSR / SSG / ISR / CSR 渲染模式和 Next fetch/cache 策略。
4. 为路由补齐 `loading.tsx`、`error.tsx`、`not-found.tsx`、metadata 和敏感逻辑的服务端边界。View the complete source on GitHubfec-nuxt-project-standard
When your agent uses it
用于创建或审查 Nuxt 3 项目、文件路由、pages、layouts、SSR/SSG/SPA 行为、Nuxt 数据获取、route middleware、plugins、modules、server routes 或 Nuxt 特定 Vue 3 约定。通用 Vue 组件架构另按项目 Vue 约定处理;中文触发词包括 Nuxt、Nuxt 3。
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,297 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 项目结构
- 渲染模式
- 数据获取
- 路由与布局
- 中间件
- 插件与模块
- 约束
- 预期输出
Files
SKILL.mdcore4,514 bytes
Read SKILL.md
# Nuxt 3 项目规范
适用于使用 Nuxt 3 + Vue 3 + TypeScript 的仓库。
## 用途
规范 Nuxt 3 项目中 SSR/SSG 渲染模式、组合式 API、自动导入、数据获取、路由中间件和模块插件的工程实践,确保约定式开发和类型安全。
## 流程
1. 先识别目标属于 Nuxt pages/layouts、渲染模式、数据获取、route middleware、plugin/module 还是 server route。
2. 明确 SSR / SSG / SPA 选择,避免服务端可执行代码依赖 `window` 或 `document`。
3. 数据获取优先使用 Nuxt 的 `useFetch` / `useAsyncData`,并检查水合一致性。
4. 路由鉴权、redirect 和权限问题与路由保护 workflow 对齐。View the complete source on GitHubfec-performance-optimization
When your agent uses it
用于诊断或改进前端性能、Core Web Vitals、包体积、运行时渲染成本、网络瀑布、内存泄漏、长任务、Lighthouse 问题或性能预算;中文触发词包括 性能优化、页面卡顿、首屏慢、包体积、Web Vitals。
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
1,287 tokensWhen the skill is activated
Reference documents
1,358 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 预算
- 检查项
- 约束
- 详细参考
- 预期输出
Files
SKILL.mdcore4,754 bytesSKILL.mdcore4,754 bytesreferences/framework-performance-patterns.mddoc3,546 bytesreferences/report-template.mddoc1,541 bytes
Read SKILL.md
# 前端性能优化
## 用途
用可度量的方式定位前端性能瓶颈,并把优化建议收敛到用户主路径、构建产物和运行时证据。
## 流程
1. 锁定体验目标
- 明确问题属于首屏加载、交互延迟、滚动卡顿、内存上涨、网络瀑布、包体积,还是视觉稳定性。
- 记录路由、设备、网络条件、浏览器、复现步骤和当前可用指标。
- 没有指标时先建立基线,不直接给出“优化一切”的泛化建议。
2. 建立度量基线View the complete source on GitHubfec-pwa-implementation
When your agent uses it
用于添加或审查 Progressive Web App 能力,如可安装性、manifest 元数据、Service Worker 注册、Workbox 缓存、离线兜底、应用更新提示、maskable icons 或 iOS PWA 兼容性。不要用于普通 API 缓存或不可安装的性能调优;中文触发词包括 PWA、离线、Service Worker。
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
561 tokensWhen the skill is activated
Reference documents
865 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore2,212 bytesreferences/manifest-and-icons.mddoc1,232 bytesreferences/service-worker-workbox.mddoc1,980 bytes
Read SKILL.md
# PWA 实现
## 用途
让 Web 应用具备可安装、离线兜底和可控更新能力。
## 流程
1. 确认 PWA 是否值得做:面向移动端/桌面安装、弱网离线、重复访问场景时优先;纯内部后台、强实时流媒体或只需要普通缓存时不要强行 PWA。
2. 先补齐 manifest、图标、主题色和 HTML 引用;图标至少覆盖 192/512,Android 需 maskable,iOS 需 apple touch icon。
3. 注册 Service Worker,并设计更新提示;不要静默 `skipWaiting()` 后强刷用户页面。
4. 用 Workbox 或框架插件管理 precache/runtime cache;登录、支付、权限变更等敏感请求必须走网络。
5. 提供 offline fallback 页面和安装提示 UI,并验证首次加载、离线访问、更新激活、卸载重装。
View the complete source on GitHubfec-react-project-standard
When your agent uses it
用于设计或审查 React + TypeScript 项目结构、feature/module 边界、组件架构、hooks 组织、路由组合、状态/API/错误/样式默认约定或仓库级 React 规范。表单、数据获取、测试、无障碍、虚拟列表、动画或安全深挖优先使用更窄的 skill;中文触发词包括 React 项目规范、React 组件架构。
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
1,408 tokensWhen the skill is activated
Reference documents
6,239 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore5,273 bytesreferences/react-performance-patterns.mddoc1,554 bytesreferences/react-project-structure.mddoc7,657 bytesreferences/react-quality-patterns.mddoc5,055 bytesreferences/react-runtime-patterns.mddoc8,889 bytes
Read SKILL.md
# React 项目规范
适用于 React + TypeScript 仓库中的中大型模块建设、页面重构和工程结构设计。
## 用途
为 React + TypeScript 项目提供工程结构、模块边界和默认实现约定,确保架构清晰、代码可维护。
## 流程
本 skill 主要解决 React 工程任务“如何设计和落地”的问题,不重复声明基础编码底线。处理 React 工程化任务时,按以下顺序执行:
1. 识别仓库已有约定
- 目录组织方式View the complete source on GitHubfec-refactor-clean
When your agent uses it
用于安全移除前端死代码、未使用导出、陈旧组件、废弃路由、未使用依赖,或由 knip、depcheck、ts-prune、TypeScript、ESLint、人工审查发现的清理目标。不要用于会改变行为的功能重写;中文触发词包括 死代码、清理未使用、refactor clean、依赖清理、删除无用代码。
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
869 tokensWhen the skill is activated
Reference documents
338 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 前端专项检查
- 约束
- 详细参考
- 预期输出
- 结构重构边界
Files
SKILL.mdcore3,296 bytesreferences/report-template.mddoc1,113 bytes
Read SKILL.md
# 重构清理
## 用途
在验证保护下识别并清理无用前端代码,减少技术债,同时避免误删动态引用、路由入口、配置文件和运行时约定。
## 流程
1. 先建立基线:运行或确认当前 lint、type-check、test、build 的状态。
2. 收集候选项:
- 优先使用仓库已有工具,如 knip、depcheck、ts-prune、eslint、TypeScript。
- 没有工具时,用 `rg` 检查引用、导出、路由、注册点和文档入口。
3. 按风险分类:
- SAFE:测试夹具、未引用工具函数、明确未导出的私有组件。View the complete source on GitHubfec-refactoring
When your agent uses it
用于在不改变可观察行为的前提下重组既有前端代码,包括职责提炼、模块搬移、条件逻辑简化、API 整理和数据组织。不要用于新增功能、改变行为的缺陷修复、依赖或框架迁移,以及已经证实的死代码清理。
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
1,204 tokensWhen the skill is activated
Reference documents
1,746 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 核心契约
- 流程
- 风险分级
- 差异预算
- 参考资料
- 约束
- 预期输出
Files
SKILL.mdcore4,521 bytesreferences/principles.mddoc2,398 bytesreferences/refactoring-vs-feature-change.mddoc1,250 bytesreferences/when-to-refactor.mddoc1,028 bytesreferences/workflow.mddoc2,056 bytes
Read SKILL.md
# 技能:保持行为的重构
## 用途
以小步、可验证、可回滚的方式重组仍在使用的前端代码,同时保持用户、调用方、测试、路由和集成能够观察到的行为不变。
## 核心契约
每次执行都遵守以下规则:
1. **行为保持**:纯重构只改变内部结构,不主动改变可观察行为。
2. **修改前基线**:编辑前先记录当前可用验证结果。
3. **一次只做一个主要重构**:每一步只有一个主要结构意图。
4. **每一步都验证**:完成一步后立即运行最小但有效的验证。View the complete source on GitHubfec-refactoring-api
When your agent uses it
保持行为的前端重构主要涉及API 类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
334 tokensWhen the skill is activated
Reference documents
6,062 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,284 bytesreferences/api-refactorings.mddoc23,577 bytes
Read SKILL.md
# API 类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[API 类重构详细卡片](references/api-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 10 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-catalog
When your agent uses it
已经有结构问题证据,需要在多种保持行为的重构手法之间比较前置条件、选择最小安全方案,或决定多个重构步骤的合理先后关系时。
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
304 tokensWhen the skill is activated
Reference documents
4,737 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 工作流
- 选择规则
Files
SKILL.mdcore1,174 bytesreferences/catalog-index.mddoc11,448 bytesreferences/composition-guide.mddoc2,367 bytesreferences/selection-guide.mddoc2,991 bytes
Read SKILL.md
# 重构目录选择
## 概览
把完整重构目录作为决策辅助,而不是自动套用的配方。只有当证据、前置条件和行为契约匹配时,才选择最小可验证的手法。
## 工作流
1. 在[重构目录索引](references/catalog-index.md)定位标准手法。
2. 若从坏味道或症状出发,使用[选择指南](references/selection-guide.md)比较成因和候选手法。
3. 若需要多个步骤,使用[组合指南](references/composition-guide.md)只安排当前代码真正需要的前置关系。
4. 确定手法后再按需加载对应 family 的详细资料。
## 选择规则
- 一个坏味道可能对应多个候选,先确认真实成因。
- 优先可回滚、局部、小范围的变换,而不是直接大改架构。View the complete source on GitHubfec-refactoring-control
When your agent uses it
保持行为的前端重构主要涉及条件控制类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
339 tokensWhen the skill is activated
Reference documents
3,672 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,319 bytesreferences/conditional-refactorings.mddoc14,474 bytes
Read SKILL.md
# 条件控制类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[条件控制类重构详细卡片](references/conditional-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 6 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-data
When your agent uses it
保持行为的前端重构主要涉及数据重组类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
340 tokensWhen the skill is activated
Reference documents
2,960 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,309 bytesreferences/data-refactorings.mddoc11,485 bytes
Read SKILL.md
# 数据重组类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[数据重组类重构详细卡片](references/data-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 5 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-encapsulation
When your agent uses it
保持行为的前端重构主要涉及封装类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
342 tokensWhen the skill is activated
Reference documents
5,574 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,309 bytesreferences/encapsulation-refactorings.mddoc21,229 bytes
Read SKILL.md
# 封装类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[封装类重构详细卡片](references/encapsulation-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 9 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-functions
When your agent uses it
保持行为的前端重构主要涉及函数类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
336 tokensWhen the skill is activated
Reference documents
6,966 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,301 bytesreferences/function-refactorings.mddoc26,695 bytes
Read SKILL.md
# 函数类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[函数类重构详细卡片](references/function-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 11 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-inheritance
When your agent uses it
保持行为的前端重构主要涉及继承关系类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
343 tokensWhen the skill is activated
Reference documents
6,922 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,324 bytesreferences/inheritance-refactorings.mddoc26,823 bytes
Read SKILL.md
# 继承关系类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[继承关系类重构详细卡片](references/inheritance-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 11 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-move-features
When your agent uses it
保持行为的前端重构主要涉及搬移特性类重构,已经选定或正在评估对应手法,需要查询该 family 的操作步骤、风险与 JavaScript/TypeScript/React/Vue 适配时。
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
348 tokensWhen the skill is activated
Reference documents
5,567 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 概览
- 执行流程
- 快速索引
- 常见错误
Files
SKILL.mdcore1,320 bytesreferences/moving-refactorings.mddoc21,475 bytes
Read SKILL.md
# 搬移特性类重构
## 概览
只有在证据和前置条件支持时才使用对应手法。一次只执行一个主要结构变换,并在完成后立即验证。
## 执行流程
1. 在[搬移特性类重构详细卡片](references/moving-refactorings.md)确认手法和前置条件。
2. 记录受影响行为与差异预算。
3. 只执行该手法最小可行的一步。
4. 在组合下一手法之前验证当前步骤。
5. 公共契约、生命周期、状态身份或实际范围超出预期时停止并重新评估。
## 快速索引
详细 Reference 包含本 family 的 9 个标准手法,每项均包括意图、信号、不适用条件、操作步骤、行为保持检查、相关坏味道、组合关系、JS/TS/React/Vue 注意事项、前端适配和原创示例。View the complete source on GitHubfec-refactoring-validation
When your agent uses it
用于证明前端重构保持了既有行为、选择合适的安全网、逐步验证结构修改,或依据证据给出 PASS、PARTIAL、NOT PROVEN 的行为保持结论。
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
632 tokensWhen the skill is activated
Reference documents
531 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 安全网等级
- 前端行为契约清单
- 参考资料
- 约束
- 预期输出
Files
SKILL.mdcore2,400 bytesreferences/behavior-preservation.mddoc889 bytesreferences/refactoring-test-checklist.mddoc1,154 bytes
Read SKILL.md
# 技能:重构验证
## 用途
定义可观察行为契约,并为每个结构步骤选择足够且不过度的验证证据。
## 流程
1. 在重要编辑前记录相关行为契约。
2. 将安全网分为 A、B、C 三个等级。
3. 运行并记录修改前基线。
4. 根据当前步骤的风险和边界选择验证方式。
5. 每个结构步骤后立即运行最小有效检查。
6. 新增失败出现时先回滚当前步骤,再扩大排查。View the complete source on GitHubfec-responsive-layout
When your agent uses it
用于设计、实现或审查响应式前端布局、移动优先断点、容器查询、流式网格、数据密集表格、触摸目标、安全区域、横竖屏变化、视口溢出或跨设备 UI 行为;中文触发词包括 响应式布局、移动端适配、断点、容器查询、横竖屏、触摸目标。
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
652 tokensWhen the skill is activated
Reference documents
793 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore2,338 bytesreferences/responsive-layout-patterns.mddoc2,669 bytes
Read SKILL.md
# 响应式布局
适用于需要让页面、工具界面、表格、仪表盘或组件在多设备上稳定工作的前端任务。需要布局模式和检查清单时加载 [references/responsive-layout-patterns.md](references/responsive-layout-patterns.md)。
## 用途
用内容优先、移动优先和容器感知的方式设计响应式布局,避免只靠固定断点修补溢出。
## 流程
1. 明确信息优先级:小屏先保留核心任务、关键操作和反馈;次要信息折叠、延后或移入详情层。
2. 选择布局策略:简单页面用 mobile-first 断点;嵌套组件、卡片网格和侧栏优先考虑 container query。
3. 设计流式尺寸:用 `minmax()`、`clamp()`、`aspect-ratio`、`max-width`、`min-width: 0` 和稳定网格轨道控制伸缩。
4. 处理数据密集界面:表格、列表、看板和编辑器需要明确横向滚动、列优先级、冻结列或移动端摘要视图。View the complete source on GitHubfec-route-protection
When your agent uses it
用于实现或审查前端路由保护、auth guard、RBAC、权限路由、登录态处理、重定向、middleware、React Router、Next.js、Vue Router 或 Nuxt route middleware;中文触发词包括 路由保护、权限路由、登录态。
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,162 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 适用场景
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore4,648 bytes
Read SKILL.md
# 路由保护
## 用途
为前端应用建立清晰的认证、授权和重定向边界,避免越权访问与闪烁渲染。
## 适用场景
- 页面需要登录后访问,或不同角色看到不同路由。
- 需要实现 React Router、Next.js、Nuxt 或 Vue Router 的路由守卫。
- 登录过期、权限不足、组织/租户切换需要统一处理。
- 不用于替代服务端授权;前端路由保护只能改善体验,不能作为唯一安全边界。
## 流程View the complete source on GitHubfec-security-review
When your agent uses it
用于审查前端安全风险,如 XSS、CSRF、敏感数据暴露、不安全 DOM API、不可信用户输入、认证/token 处理、支付流程、文件上传、CSP、依赖风险或第三方脚本;中文触发词包括 安全审查、安全检查。
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
1,159 tokensWhen the skill is activated
Reference documents
906 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 评审模式与覆盖范围
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore4,653 bytesreferences/report-template.mddoc1,030 bytesreferences/security-checklist.mddoc2,105 bytes
Read SKILL.md
# 前端安全审查
## 评审模式与覆盖范围
用户明确指定的范围优先于默认行为。采用以下三种审核模式:
- **改动审核**:仅在明确要求或当前任务已明确最近改动、本次修改、暂存区、PR 或提交上下文时,审核这些改动及必要上下文。本地模式在请求范围内检查暂存、未暂存差异及相关未跟踪项目文件;仅要求暂存区时只审核暂存改动。无改动时说明没有可审核的改动,不自动切换到最近提交或扩大范围。
- **指定范围审核**:用户指定文件或目录时,建立范围内文件清单,审核其中现有代码,包括未改动代码;不要求 Git 差异。
- **全项目审核(默认)**:未指定范围或改动上下文,或明确要求审核整个项目时,建立项目自有前端代码、相关测试、配置和依赖声明的清单,再按模块分批审核,包括未改动代码;不要求 Git 差异。
先选择范围,再收集差异。仅指定文件或目录表示全量审核该范围;路径与明确改动请求同时出现时,仅增量审核该路径的改动。未限定的调用即使存在 Git 改动也默认全项目审核。开始审核时说明选定模式和目标范围。修改后自动委托审核时,显式传入本次改动范围,避免无范围调用触发全项目审核。
默认排除依赖目录、构建产物、缓存、生成文件和第三方代码,并记录排除项。保持前端职责边界,不宣称完成后端专项审核。目标不存在或范围内无相关文件时,明确说明,不替换为其他范围。
View the complete source on GitHubfec-source-driven-development
When your agent uses it
用于前端决策依赖可能变化的框架、库、浏览器、运行时、包、API 或平台行为时,包括官方文档核验、版本敏感模式、迁移选择或公共接口假设;中文触发词包括 查官方文档、以源码为准、source-driven、版本差异。
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,330 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 本地知识检索
- 事实源优先级
- 约束
- 预期输出
Files
SKILL.mdcore5,057 bytes
Read SKILL.md
# 来源驱动开发
## 用途
在前端实现、评审和架构决策中优先依据项目内事实、官方文档和当前版本行为,避免沿用过时经验或未经验证的假设。
## 流程
1. 判断是否需要查源
- 涉及框架新版本、路由、渲染模式、缓存、构建工具、浏览器 API、包发布格式、鉴权协议或公共接口时必须查源。
- 涉及项目约定时先读本仓库 README、配置、模板、已有实现、测试和迁移记录。
- 只是稳定语言语法或明显局部重构时,可使用项目现有模式作为事实来源。
2. 收集权威材料View the complete source on GitHubfec-state-management
When your agent uses it
用于选择、实现、审查或重构 React、Vue、Next.js、Nuxt、URL 状态、服务端状态、表单状态、浏览器持久化或全局 store 的前端状态归属。TanStack Query 缓存细节、浏览器存储持久化或表单校验内部问题优先使用更窄的 skill;中文触发词包括 状态管理、状态归属、store 选型。
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
1,344 tokensWhen the skill is activated
Reference documents
809 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore5,091 bytesreferences/state-patterns.mddoc3,103 bytes
Read SKILL.md
# 前端状态管理
## 用途
为前端状态确定清晰归属,避免全局 store 膨胀、重复缓存和派生状态同步错误。
## 流程
### 1. 先分类状态来源
不要先选 Redux、Zustand、Pinia 或 Context。先把每个状态标到唯一归属,再决定工具。
| 状态类型 | 典型例子 | 默认归属 |
| ---------------- | ------------------------------------ | ------------------------ |View the complete source on GitHubfec-storybook-component-doc
When your agent uses it
用于设置或审查 Storybook 组件文档、设计系统展示、隔离组件状态预览、stories、addons、decorators、MDX 文档、组件状态交互检查、视觉基线或 Chromatic。真实浏览器跨页面旅程或更广覆盖规划优先选择对应测试工作流;中文触发词包括 Storybook、组件文档、Design System、视觉回归。
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
624 tokensWhen the skill is activated
Reference documents
633 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore2,425 bytesreferences/story-patterns.mddoc2,433 bytes
Read SKILL.md
# Storybook 组件文档化
## 用途
为 UI 组件建立文档化、设计系统展示和隔离状态预览环境;交互与视觉测试只覆盖 Storybook 场景内的组件状态。
## 流程
1. 初始化或识别现有 Storybook 配置,沿用项目框架适配器、stories glob、主题和构建命令。
2. 每个组件的 Story 覆盖默认态、主要变体、尺寸、语义 tone、disabled、loading、error、empty、selected、invalid 和关键边缘状态。
3. 依赖 Router、Store、i18n、ThemeProvider 的组件用 decorators 包裹,不在 Story 中复制应用入口。
4. 复杂组件用 MDX 补充使用说明、Props、slots/children、variant 矩阵、状态示例、可访问性要求和源码展示。
5. 需要自动化时接入 interaction tests、addon-a11y、Chromatic 或 Storybook Test Runner;这些能力服务于组件文档和设计系统展示,不承接跨页业务旅程。
6. 设计系统组件应记录 token 来源、Tailwind/class 变体、暗色模式、响应式尺寸和不支持的组合,避免消费者靠猜测拼装。View the complete source on GitHubfec-svg-animation
When your agent uses it
用于实现或审查 SVG 动画、路径绘制、图标动效、Logo 动画、插画动效、微交互、CSS/SMIL/Framer Motion/GSAP 选型、动效无障碍或降级行为;中文触发词包括 SVG 动画、路径描边、动效。
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,384 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 适用场景
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore4,764 bytes
Read SKILL.md
# SVG 动画实现
## 用途
为 SVG 图标、插画和数据可视化提供可维护、可访问、性能可控的动画方案。
## 适用场景
- 需要实现 SVG 图标、Logo、插画或路径描边动画。
- 需要在 React/Vue 组件中接入 Framer Motion、GSAP 或 CSS 动画。
- 需要根据 `prefers-reduced-motion` 提供动效降级。
- 不用于复杂 3D/WebGL 场景;此类场景优先使用 Canvas / Three.js workflow。
## 流程View the complete source on GitHubfec-tailwind-design-system
When your agent uses it
用于设计、实现或审查 Tailwind CSS 设计系统、Token 映射、主题扩展、工具类治理、组件变体、暗色模式、响应式工具、safelist 或可维护的 class 组合;中文触发词包括 Tailwind、设计 Token、组件变体、暗色模式、class 管理。
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
661 tokensWhen the skill is activated
Reference documents
813 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore2,541 bytesreferences/tailwind-system-patterns.mddoc2,940 bytes
Read SKILL.md
# Tailwind 设计系统
适用于用 Tailwind CSS 承载产品设计系统、组件变体和主题规则的前端任务。需要具体配置、variant、class 组织和迁移细节时加载 [references/tailwind-system-patterns.md](references/tailwind-system-patterns.md)。
## 用途
让 Tailwind 项目中的 token、主题、组件变体和响应式样式可维护,而不是把一次性 utility class 散落到业务代码里。
## 流程
1. 识别现状:确认 Tailwind 版本、配置位置、暗色模式策略、组件库、CSS 变量、设计 token 和 class 合并工具。
2. 建立 token 边界:颜色、间距、圆角、阴影、字体、z-index 和断点优先从项目 token 或 `theme.extend` 派生。
3. 设计组件变体:按钮、输入框、卡片、弹窗、表格等基础组件用集中 variant API 表达尺寸、语义、状态和密度。
4. 控制 class 复杂度:重复组合沉淀为组件、slot、variant 或局部 helper;不要把长 class 字符串复制到多个页面。View the complete source on GitHubfec-tdd-workflow
When your agent uses it
用于实现新前端行为、修复 bug 或重构可先由测试描述预期行为的逻辑。适用于组件、hooks/composables、工具函数、API clients、路由守卫或用户工作流;中文触发词包括 TDD、测试驱动、先写测试、红绿重构、回归测试。
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
759 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 证明式测试模式
- 前端测试选择
- 约束
- 预期输出
- 纯重构边界
Files
SKILL.mdcore2,953 bytes
Read SKILL.md
# 前端 TDD 工作流
## 用途
用“先写失败测试,再实现最小代码,再重构”的节奏交付前端功能,避免只在实现后补覆盖率。
## 流程
1. 识别可观察行为:用户能看到的 UI、组件契约、hook/composable 返回值、路由守卫结果、API client 输出或错误状态。
2. 先写一个最小失败测试:
- 纯逻辑优先单元测试。
- 组件交互优先 Testing Library / Vue Test Utils。
- 跨页关键流程优先 Playwright / Cypress。
3. 运行该测试并确认失败原因正确,失败应来自行为尚未实现,而不是语法、导入或测试环境错误。View the complete source on GitHubfec-testing-strategy
When your agent uses it
用于规划或审查前端测试策略,按风险选择正确测试层级,将覆盖映射到静态检查、单元测试、组件测试、集成测试、E2E、Storybook/视觉回归、a11y、安全、性能或 CI gates。不要用于编写单个组件/E2E 测试或只是运行现有验证命令;中文触发词包括 测试策略、测试分层、测试计划、覆盖矩阵。
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
885 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore3,320 bytes
Read SKILL.md
# 前端测试策略
## 用途
按“离代码多近 / 覆盖风险层级”选择测试方法,避免把所有风险都塞进组件测试或 E2E。
## 流程
1. 识别改动类型:纯逻辑、UI 组件、跨模块流程、浏览器能力、视觉稳定性、专项质量风险或发布门禁。
2. 建立测试层级矩阵,至少区分:
- 静态检查:TypeScript、ESLint、格式、依赖安全、构建。
- 单元测试:utils、hooks/composables、状态逻辑、schema、纯函数。
- 组件测试:props/emits、用户交互、loading/error/empty、mock 边界。
- 轻量集成测试:表单 + API mock + 路由/Store/Provider 上下文。View the complete source on GitHubfec-typescript-project-standard
When your agent uses it
用于创建、配置、审查或调试前端应用、库、SDK、CLI、monorepo 包中的 TypeScript 项目规范,包括 tsconfig、strictness、module/moduleResolution、路径别名、project references、声明文件、package exports、公共 API 类型、DTO、高级泛型、判别联合、类型守卫、类型收窄或类型级回归。React/Vue/Next/Nuxt 组件架构优先使用框架项目 skill;中文触发词包括 TypeScript 项目规范、TS 项目规范、TypeScript 类型安全、类型建模、泛型、判别联合、类型收窄、tsconfig、声明文件。
What it loads into context
Frontmatter
156 tokensAlways available to the agent
SKILL.md
1,176 tokensWhen the skill is activated
Reference documents
1,702 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Files
SKILL.mdcore4,488 bytesreferences/type-safety-patterns.mddoc2,532 bytesreferences/type-safety.mddoc3,924 bytes
Read SKILL.md
# TypeScript 项目规范
## 用途
统一 TypeScript 层的工程配置、类型边界和发布产物规则。适用于前端应用、组件库、SDK、CLI、monorepo package 和纯 TypeScript 工具库,但不接管 React、Vue、Next.js、Nuxt 或 Vite 的框架架构职责。
## 流程
1. 识别 TypeScript 上下文
- 应用项目:优先检查 `tsconfig` 分层、strictness、路径别名、类型检查脚本和框架生成类型。
- 组件库或 SDK:优先检查 public API、声明文件、package exports、peer dependencies 类型边界和发布前 pack 校验。
- CLI 或 Node 工具:优先检查 Node 目标版本、ESM/CJS 策略、`moduleResolution`、shebang 产物和 `process.env` 类型边界。
- Monorepo package:优先检查 project references、composite build、包间导入边界和 workspace 路径别名是否泄漏到发布产物。
- React、Vue、Next.js、Nuxt 等框架的组件架构、路由组织和状态管理归对应框架 skill;本流程只处理跨框架 TypeScript 契约和工程边界。View the complete source on GitHubfec-ui-design
When your agent uses it
用于构建、审查或改进需要产品专属设计方向的前端 UI,包括设计系统生成、Master/Page 覆盖、独特视觉识别、反通用界面选择、首屏层级、UI 打磨、图表 UX、交互状态、响应式行为或视觉 QA。外部设计文件为权威时,应从该来源实现,而不是自行发明方向;中文触发词包括 UI 设计、设计系统、视觉风格、不要模板化、高级感、界面打磨、交互状态。
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
2,841 tokensWhen the skill is activated
Reference documents
2,353 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Scripts executed separately
scripts/design-system.mjs../../../../skills/fec-ui-design/scripts/design-system.mjs../../../../skills/fec-ui-design/scripts/design-system.mjs
Files
SKILL.mdcore10,751 bytesdata/product-rules.jsonasset6,672 bytesdata/stack-ui-rules.jsonasset3,187 bytesdata/style-archetypes.jsonasset8,282 bytesdata/ux-quality-rules.jsonasset5,140 bytesreferences/design-intelligence.mddoc5,402 bytesreferences/master-page-overrides.mddoc1,231 bytesreferences/pre-delivery-checklist.mddoc2,175 bytesscripts/design-system.mjsruns21,324 bytes../../../../skills/fec-ui-design/scripts/design-system.mjsruns21,324 bytes../../../../skills/fec-ui-design/scripts/design-system.mjsruns21,324 bytes
Read SKILL.md
# UI 设计
适用于需要把前端界面推进到“符合产品语境、可扫描、可信赖、有辨识度,并且细节稳定”的 UI 任务。需要系统化设计建议时,加载 [design-intelligence.md](references/design-intelligence.md);需要长期沉淀设计系统时,加载 [master-page-overrides.md](references/master-page-overrides.md);上线前做 UI/UX QA 时,加载 [pre-delivery-checklist.md](references/pre-delivery-checklist.md)。
可执行设计系统生成器位于 [design-system.mjs](scripts/design-system.mjs),其原创知识包包括 [product-rules.json](data/product-rules.json)、[style-archetypes.json](data/style-archetypes.json)、[ux-quality-rules.json](data/ux-quality-rules.json) 和 [stack-ui-rules.json](data/stack-ui-rules.json)。
## 用途
为页面、组件、仪表盘和工具界面建立设计方向,并完成可落地的视觉与交互 polish。
## 流程
1. 明确界面的工作
- 先说清它帮助用户完成什么任务,而不是先选颜色或布局。View the complete source on GitHubfec-validation-fix
When your agent uses it
用于运行现有项目验证命令并修复代码变更后的失败,包括 lint、type-check、单元/集成测试、build、CI 或本地脚本失败。不要用于设计或编写新的组件/E2E 测试;中文触发词包括 验证、检查失败、修复失败、CI 失败。
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
585 tokensWhen the skill is activated
Reference documents
307 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 失败分诊
- 约束
- 详细参考
- 预期输出
Files
SKILL.mdcore2,189 bytesreferences/report-template.mddoc1,042 bytes
Read SKILL.md
# 验证并修复
## 用途
自动化执行已有验证命令,分析失败原因并安全修复,确保质量门禁达标。
## 流程
1. 从 package.json 或仓库文档中识别可用命令。
2. 优先按以下顺序执行:
- lint
- type-check
- unit/integration tests
- buildView the complete source on GitHubfec-vite-project-standard
When your agent uses it
用于创建、配置、审查或调试基于 Vite 的前端项目、vite.config.ts、环境变量、dev server proxy、HMR、插件顺序、library mode、依赖预打包、bundle splitting 或 Vite 构建性能。React/Vue 组件架构请使用框架专项 skill;中文触发词包括 Vite 配置、vite.config、Vite 构建、Vite 性能。
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,071 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 最小配置
- 约束
- 预期输出
Files
SKILL.mdcore3,901 bytes
Read SKILL.md
# Vite 项目规范
适用于 Vite 应用、组件库、开发服务器和构建配置的设计与审查。
## 用途
规范 Vite 配置、安全边界和构建性能,避免开发环境与生产构建的常见陷阱。
## 流程
1. 识别项目类型
- 应用项目优先检查 `root`、`base`、`server.proxy`、`envPrefix`、`build` 和框架插件。
- 组件库项目优先检查 `build.lib`、类型产物、peer dependencies external 和导出入口。
- Monorepo 额外检查 `server.fs.allow`、路径别名和包依赖边界。View the complete source on GitHubfec-vue3-project-standard
When your agent uses it
用于设计或审查 Vue 3 + TypeScript 项目结构、SFC/组件边界、composables 组织、路由组合、Pinia 归属、API/错误/样式默认约定、directives 或仓库级 Vue 规范。表单、数据获取、测试、无障碍、虚拟列表、动画或安全深挖优先使用更窄的 skill;中文触发词包括 Vue 3 项目规范、Vue 组件架构。
What it loads into context
Frontmatter
119 tokensAlways available to the agent
SKILL.md
1,075 tokensWhen the skill is activated
Reference documents
5,113 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore4,049 bytesreferences/vue3-composables-routing.mddoc4,784 bytesreferences/vue3-performance-patterns.mddoc518 bytesreferences/vue3-project-structure.mddoc8,092 bytesreferences/vue3-state-api-quality.mddoc5,961 bytes
Read SKILL.md
# Vue 3 项目规范
适用于使用 Vue 3 + TypeScript 的仓库。
## 用途
为 Vue 3 + TypeScript 项目提供工程结构、组件边界、Composables 和默认实现约定,确保约定式开发和类型安全。
## 流程
1. 识别仓库已有 Vue 约定:目录、路由、Pinia、请求层、样式体系、组件库和测试框架。
2. 划分页面、业务组件、通用组件、composables、stores、services 和 utils 的边界。
3. 优先沿用 `<script setup lang="ts">`、组合式 API 和仓库现有自动导入/模块出口约定。
4. 输出时补齐状态归属、API 层、错误处理、样式隔离和专项 skill 分流。View the complete source on GitHubfec-web-video-presentation
When your agent uses it
用于将文章、演讲稿、课程、产品演示或口播解释转成可录制的 16:9 网页演示,包含步骤驱动场景、可选口播对齐、主题 Token 与录屏指导;中文触发词包括 网页视频、动态演示、口播稿转视频、可录屏演示、16:9 演示。
What it loads into context
Frontmatter
96 tokensAlways available to the agent
SKILL.md
1,046 tokensWhen the skill is activated
Reference documents
1,321 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 约束
- 预期输出
Scripts executed separately
scripts/create-video-presentation.mjs../../../../skills/fec-web-video-presentation/scripts/create-video-presentation.mjs../../../../skills/fec-web-video-presentation/scripts/create-video-presentation.mjs../../../../skills/fec-web-video-presentation/scripts/create-video-presentation.mjs
Files
SKILL.mdcore3,939 bytesSKILL.mdcore3,939 bytesSKILL.mdcore3,939 bytesdata/starter-themes.jsonasset1,822 bytesreferences/chapter-craft.mddoc1,555 bytesreferences/content-plan.mddoc1,233 bytesreferences/recording-and-audio.mddoc938 bytesreferences/theme-system.mddoc966 bytesscripts/create-video-presentation.mjsruns10,857 bytes../../../../skills/fec-web-video-presentation/scripts/create-video-presentation.mjsruns10,857 bytes../../../../skills/fec-web-video-presentation/scripts/create-video-presentation.mjsruns10,857 bytes../../../../skills/fec-web-video-presentation/scripts/create-video-presentation.mjsruns10,857 bytes
Read SKILL.md
# 网页视频演示
## 用途
把文章、口播稿、课程、产品讲解或技术分享转成可录屏的 16:9 网页演示。产物应像一个可点击推进的视频舞台:每一步承载一个口播节拍,视觉设计服务内容节奏,并能用浏览器稳定录制。
## 流程
1. 判断输入形态
- 用户给文章或长文时,先拆成口播稿和 outline。
- 用户给现成口播稿时,保留原顺序,只补 outline、章节和 step。
- 用户只给主题但没有内容时,先要求素材、大纲或目标要点;不要替用户虚构整篇内容。
2. 生成内容计划View the complete source on GitHubfec-web-workers
When your agent uses it
用于将昂贵的浏览器工作移出主线程,涉及 Web Workers、SharedWorker、worker 池、Comlink、transferable objects、Vite/Webpack worker 集成或 UI 响应性修复。不要用于轻量同步工作或 DOM 操作;中文触发词包括 Web Worker、后台线程、主线程阻塞。
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
511 tokensWhen the skill is activated
Reference documents
803 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 用途
- 流程
- 详细参考
- 约束
- 预期输出
Files
SKILL.mdcore2,036 bytesreferences/advanced-workers.mddoc1,366 bytesreferences/basic-worker.mddoc1,689 bytes
Read SKILL.md
# Web Workers
## 用途
把昂贵计算移出主线程,保持输入、滚动和动画响应。
## 流程
1. 先确认瓶颈:任务超过约 10ms、用户输入延迟明显、FPS 下滑或大文件解析/图像处理/加密计算才考虑 Worker。
2. 选择通信模型:简单任务用 `postMessage`,函数式 RPC 用 Comlink,大量并行小任务用 Worker pool,跨 Tab 同步用 SharedWorker。
3. 设计消息协议:请求/响应类型、错误类型、取消或超时策略都要明确。
4. 传大对象时优先 Transferable Objects;不要让结构化克隆吞掉 Worker 带来的收益。
5. 在组件或页面卸载时 `terminate()`,并通过 Profiler、Performance 面板或 FPS 指标验证主线程改善。
View the complete source on GitHubfec-accessibility-check
When your agent uses it
Use when reviewing or improving frontend accessibility, semantic structure, keyboard support, focus management, ARIA labels, screen reader behavior, WCAG 2.2 issues, touch accessibility, or assistive-technology regressions; Chinese triggers include accessibility, accessibility, a11y, WCAG, screen reader.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
594 tokensWhen the skill is activated
Reference documents
499 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,970 bytesreferences/report-template.mddoc597 bytesreferences/screen-reader-testing.mddoc1,800 bytes
Read SKILL.md
# Accessibility Implementation Specification (WCAG 2.2 AA)
## Purpose
Ensure the front-end UI is accessible to users with disabilities, meets the core requirements of WCAG 2.2 AA, and is stable for keyboard, screen reader, touch, and zoom users.
## Procedure
1. Check the semantic structure: landmark, title level, form label, button/link accessible name, table semantics and image alt.
2. Check the keyboard path: Tab order, Enter/Space/Esc behavior, focus visible, focus restored after closing.
3. Check the ARIA status of complex components: dialog boxes, menus, tabs, trees, drawers, tables, and custom controls.
4. Check dynamic status: loading, empty, error, toast and asynchronous updates need to be perceived by screen readers.
5. Check visual and touch readability: text/background contrast, focus ring, zoom to 200%, reduced animation preference, touch target size, and mobile virtual keyboard behavior.
6. Use the real keyboard path to review the key process, and if necessary, add a screen reader or browser accessibility tree observation; see [references/screen-reader-testing.md](references/screen-reader-testing.md) for the screen reader process.View the complete source on GitHubfec-alchemy
When your agent uses it
Use when absorbing ideas, capabilities, workflows, architecture, quality systems, ecosystem extensions, or engineering practices from any reference system into the current project through original, project-native redesign rather than copying.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,053 tokensWhen the skill is activated
Reference documents
2,217 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
- Detailed reference
Files
SKILL.mdcore5,681 bytesSKILL.mdcore5,681 bytesSKILL.mdcore5,681 bytesassets/absorption-plan-template.mddoc888 bytesassets/intake-template.mddoc1,590 bytesassets/review-checklist.mddoc1,348 bytesreferences/methodology.mddoc5,072 bytesreferences/originality-and-licensing.mddoc2,445 bytes
Read SKILL.md
# Integration of project absorption and originality
## Purpose
Convert excellent ideas, capabilities, and engineering practices from one or more reference systems into improvements in the current project that are original, maintainable, and consistent with the target project style.
Suitable for absorbing, borrowing, benchmarking, migrating or integrating another code base, product, framework, library, service, CLI, plug-in, documentation system, AI/Agent tool chain, architecture or engineering workflow. This Skill should not be used for general bug fixes, individual API usage issues, or direct file format conversions, unless the user explicitly requests project-level ingestion or adaptation.
## Procedure
1. Clarify goals and reference systems:
- Treat the current repository as the target system and its architecture, naming, testing, release model and maintenance boundaries as the source of truth.
- Treat external repositories, uploaded packages, documentation, examples, product descriptions or running experiences as reference systems that only provide evidence and inspiration.
- Identify the scope of absorption: product capabilities, architectural patterns, domain models, interface protocols, data flow, runtime behavior, development experience, quality system, delivery process, documentation knowledge or ecological expansion.View the complete source on GitHubfec-api-integration
When your agent uses it
Use when designing, implementing, or reviewing frontend-to-backend API integration, typed API clients, REST/tRPC/OpenAPI client choices, auth refresh, API error mapping, upload flows, SSE/WebSocket/polling choices, CORS-facing frontend behavior, or cross-boundary loading/error states. Do not use for backend-only service architecture or TanStack Query cache policy alone; Chinese triggers include API integration, front-end and back-end joint debugging, typed API client, Interface error handling, SSE, WebSocket.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
1,237 tokensWhen the skill is activated
Reference documents
577 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore6,123 bytesreferences/integration-patterns.mddoc2,754 bytes
Read SKILL.md
# API integration
Suitable for front-end and back-end boundary types, errors, authentication, uploads, real-time communication and user status design. Load [integration-patterns.md](references/integration-patterns.md) when specific code patterns are required.
## Purpose
Standardize front-end API integration boundaries to make requests, errors, authentication, and real-time data maintainable.
## Procedure
1. Clarify interface ownership
- For TypeScript full stack in the same team, tRPC or shared schema can be considered.
- Multi-language or multi-consumer API preferred OpenAPI/GraphQL codegen.
- Typed fetch wrapper can be used for small internal applications, but types must be maintained centrally.View the complete source on GitHubfec-backend-requirements-handoff
When your agent uses it
Use when frontend work needs to communicate data, action, state, permission, validation, or business-rule needs to backend teams without dictating endpoint design, field names, database shape, or implementation details; Chinese triggers include front-end and back-end requirements handover, back-end requirements, API requirements clarification, data requirements description.
What it loads into context
Frontmatter
77 tokensAlways available to the agent
SKILL.md
658 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore3,450 bytes
Read SKILL.md
# Handover of front-end and back-end requirements
## Purpose
Organize the data, actions, status, and questions required for front-end pages and interactions into discussion-ready requirements for the back-end.
## Procedure
1. Clarify the functional context
- Describe what the page, process, or component is, what type of user it is intended for, and the success status of the user completing the task.
- If there are existing designs, routes, user stories, or permission roles, use them as sources of truth first.
2. Describe front-end display requirements
- List information to be displayed by screen or component, relationships between information, sorting/filtering/pagination requirements and visibility rules.View the complete source on GitHubfec-browser-storage
When your agent uses it
Use when choosing, implementing, or reviewing browser storage such as localStorage, sessionStorage, IndexedDB, cookies, client persistence, offline data, secure storage, or cleanup strategy; Chinese triggers include browser storage, client persistence.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
400 tokensWhen the skill is activated
Reference documents
487 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,093 bytesreferences/storage-patterns.mddoc1,980 bytes
Read SKILL.md
# Browser storage
## Purpose
Choose the appropriate client storage solution based on data size, security requirements, and lifecycle.
## Procedure
1. First determine the data sensitivity, volume, life cycle, whether it needs to be spread across tabs, and whether it needs to be sent with the request.
2. Use localStorage for a small amount of non-sensitive preferences; use sessionStorage for tab-level temporary data; use IndexedDB for large amounts of structured data or offline caching; prioritize httpOnly cookies for authentication status.
3. Encapsulate unified key prefix, JSON parse/stringify, exception handling, expiration cleanup and quota protection.
4. Sensitive data is processed according to security rules, and plain text tokens, passwords, and credit card information are not put into storage that can be read by JS.
5. Review privacy mode, storage quotas, sanitization policies, and cross-browser compatibility.
View the complete source on GitHubfec-canvas-threejs
When your agent uses it
Use when building or reviewing Canvas 2D, Three.js/WebGL, React Three Fiber, GLSL shaders, ShaderToy-to-WebGL adaptation, 2D/3D visualization, game rendering, animation loops, GPU resource cleanup, or rendering performance. Do not use for standard DOM UI, charts already covered by a chart library, or non-graphical performance work; Chinese triggers include Canvas, Three.js, WebGL, GLSL, Shader, 3D, data visualization, games.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
841 tokensWhen the skill is activated
Reference documents
1,119 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Core Patterns
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore3,851 bytesreferences/rendering-patterns.mddoc1,805 bytesreferences/shader-webgl-patterns.mddoc2,800 bytes
Read SKILL.md
# Canvas and Three.js
## Purpose
Enable high-performance 2D/3D graphics rendering in the browser.
## Procedure
1. First select the rendering layer: DOM for standard UI; Canvas 2D for simple 2D graphics/signatures/particles; Three.js/WebGL for 3D models, spatial interactions and complex particles; React Three Fiber for declarative 3D in React projects.
2. Define stable size, DPI adaptation, and resize behavior for the render container; Canvas does not automatically scale cleanly with CSS.
3. The animation loop uses `requestAnimationFrame`, which is paused when it is invisible or has no changes, and canceled when it is uninstalled.
4. Three.js must release geometry/material/texture/renderer and remove event listeners and observers.
5. Shader/WebGL tasks first identify whether it is an SDF, ray marching, noise, particle, post-processing, multipass or debugging issue, and then decide whether native WebGL2, Three.js ShaderMaterial or R3F is required.
6. Check the GLSL version, entry function, varying/in-out, texture API, uniform usage and function declaration order when adapting to WebGL2 to avoid white screen leaving only console errors.View the complete source on GitHubfec-code-review
When your agent uses it
Use when the user asks for general frontend code review, PR review, merge-readiness assessment, architecture maintainability, type-safety, rendering/state risks, style consistency, testability gaps, or a cross-cutting review summary. Delegate deep security, accessibility, E2E, or performance investigations to their specialized skills; Chinese triggers include code review, code review, review.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
2,164 tokensWhen the skill is activated
Reference documents
273 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Review modes and coverage
- Purpose
- Procedure
- Multi-dimensional review arrangement
- Review dimensions
- Detailed reference
- Constraints
- Expected Output
- Refactoring Boundary
Files
SKILL.mdcore11,297 bytesreferences/report-template.mddoc1,245 bytes
Read SKILL.md
# Front-end code review
## Review modes and coverage
User-specified scope takes precedence over the default. Use the following three review modes:
- **Change review**: only when recent changes, current edits, staged changes, a PR or a commit are explicitly requested or clearly established by the active task, review those changes and necessary context. For local changes, inspect staged and unstaged diffs and relevant untracked project files within the requested scope; a staged-only request reviews only staged changes. If there are no changes, report that there is nothing to review; do not switch to recent commits or expand scope automatically.
- **Targeted review**: when files or directories are specified, inventory and review existing code in that scope, including unchanged code; no Git diff is required.
- **Project review (default)**: when no scope or change context is specified, or when the entire project is requested, inventory project-owned frontend code, related tests, configuration and dependency declarations, then review in module batches, including unchanged code; no Git diff is required.
Select scope before collecting diffs. A file/directory alone means full review of that scope; a path combined with an explicit change request restricts incremental review to that path. An unqualified invocation defaults to project review even if Git changes exist. At review start, state the selected mode and target scope. When automatically delegating review after edits, pass the current change scope explicitly; do not trigger project review merely because the reviewer was called.
Exclude dependency directories, build outputs, caches, generated files and third-party code by default, and record exclusions. Keep the frontend responsibility boundary; this is not a backend audit. A nonexistent target or a scope with no relevant files must be reported explicitly, not replaced with another scope.
View the complete source on GitHubfec-code-smells
When your agent uses it
Use when diagnosing structural maintainability problems in existing frontend code before deciding how to refactor it, especially when evidence, false-positive checks, and candidate transformations are needed without editing business code.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
362 tokensWhen the skill is activated
Reference documents
9,096 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Finding Contract
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,695 bytesreferences/detection-guide.mddoc1,461 bytesreferences/smell-catalog.mddoc29,698 bytesreferences/smell-to-refactoring-map.mddoc8,752 bytes
Read SKILL.md
# Code Smell Diagnosis
## Overview
Diagnose structural problems from concrete evidence. A smell is a prompt to investigate, not proof that code must change.
## Procedure
1. Establish the requested scope and project facts.
2. Collect concrete structural and change-coupling evidence.
3. Match evidence against [the smell catalog](references/smell-catalog.md).
4. Apply [false-positive checks](references/detection-guide.md).
5. Report confidence, impact, and candidates from [the mapping guide](references/smell-to-refactoring-map.md).
6. If the request is diagnosis-only, do not modify business code.
## Finding ContractView the complete source on GitHubfec-component-testing
When your agent uses it
Use when authoring or reviewing frontend unit, component, or light integration tests close to UI code, including React Testing Library, Vue Test Utils, hooks/composables, props/emits, callbacks, accessible queries, user-event interactions, mocks, loading/error/empty states, and regression coverage. For layer planning, real-browser journeys, or existing validation failures, choose the matching testing or validation workflow first; Chinese triggers include component testing, Component unit testing, unit testing, lightweight integration testing.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
1,117 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore5,416 bytes
Read SKILL.md
#Component testing
## Purpose
Use tests close to the code and user behavior to verify pure logic, component contracts, and lightweight module collaboration to reduce refactoring and UI interaction regression.
## Procedure
### 1. First determine the test level
- Unit testing: pure functions, hooks/composables, utils, state logic, schema.
- Component testing: props/emis, callbacks, user interaction, loading/error/empty, mock boundaries.
- Lightweight integration testing: form + API mock + Router/Store/Provider context.
View the complete source on GitHubfec-data-fetching
When your agent uses it
Use when implementing or reviewing frontend server-state flows: typed queries, request caching, invalidation, mutations, optimistic updates, infinite queries, prefetch, SSR hydration, or API-layer integration. Do not use for local UI state or Service Worker caching; Chinese triggers include data fetch, cache, optimistic updates.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
718 tokensWhen the skill is activated
Reference documents
974 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- React Quick Start
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore3,374 bytesSKILL.mdcore3,374 bytesreferences/query-patterns.mddoc4,335 bytes
Read SKILL.md
# Server State data acquisition
## Purpose
Establish clear data acquisition, caching, invalidation and submission boundaries for front-end server state to avoid request state being scattered among page components.
## Procedure
1. Determine the source of the state: use the request caching scheme when it comes from the server and needs caching, deduplication, refreshing, paging or mutation; use component state or store for purely local UI state.
2. First use the existing data acquisition library of the project; when adding dependencies, you can consider TanStack Query for React/Vue/Solid/Svelte, or you can also use SWR, Nuxt/Nitro data acquisition or project encapsulation.
3. Stable design cache key/query key: The structure contains entities, actions and all parameters that affect the results.
4. The API function remains a pure request function, and the data hook/composable is responsible for cache, select, loading/error/empty status.
5. Invalidation after mutation succeeds; use optimistic update when immediate feedback is needed and rollback when failure occurs.
View the complete source on GitHubfec-debug-framework
When your agent uses it
Use when diagnosing frontend build failures, runtime errors, UI anomalies, API/data problems, white screens, request failures, or unexplained production exceptions; Chinese triggers include debugging, debug, troubleshooting, positioning, error reporting, exceptions, white screens, request failures.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,157 tokensWhen the skill is activated
Reference documents
299 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Diagnostic module
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore5,798 bytesreferences/report-template.mddoc1,371 bytes
Read SKILL.md
# Front-end diagnostic framework
## Purpose
Use an evidence-driven triage, collection, hypothesis, verification, and remediation process to locate front-end faults and avoid relying on intuition to expand the scope of changes.
## Procedure
All front-end problem diagnosis follows a unified process:
### Step 1: Classify
Identify problem type and scope of impact:
View the complete source on GitHubfec-dependency-upgrade
When your agent uses it
Use when planning, implementing, or reviewing frontend dependency upgrades, package migrations, lockfile changes, major framework version bumps, CVE remediation, peer dependency conflicts, ESM/CJS shifts, build-tool compatibility, or CI verification matrices; Chinese triggers include dependency upgrades, version upgrades, lockfile, peer dependency, CVE fixes, major version migrations.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
531 tokensWhen the skill is activated
Reference documents
415 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore2,817 bytesSKILL.mdcore2,817 bytesSKILL.mdcore2,817 bytesreferences/dependency-upgrade-workflow.mddoc1,986 bytes
Read SKILL.md
# Dependency upgrade
Suitable for front-end dependency upgrades, bug fixes, major version migrations and lockfile risk reviews. Load [references/dependency-upgrade-workflow.md](references/dependency-upgrade-workflow.md) when you need specific processes and checklists.
## Purpose
Reduce disruptive changes, supply chain risks, and CI regressions by upgrading dependencies in a provenance-driven and small-batch verification manner.
## Procedure
1. Establish a baseline of truth: Read package manager, lockfile, Node version, workspace scope, CI commands, and current verification status.
2. Classified upgrade goals: security fixes, patch upgrades, minor version upgrades, major version migrations, framework migrations, build tool migrations, or dependency cleanup.
3. Verify sources: For version-sensitive libraries, read official release notes, migration guide, peer dependency, Node/browser support and deprecation items.
4. Split into smaller batches: Security patches can be processed centrally; large versions, build tools, frameworks and testing tools must be verified in separate batches.View the complete source on GitHubfec-doc-sync
When your agent uses it
Use when synchronizing frontend project documentation with source-of-truth files such as package.json, lockfiles, config, env examples, routes, API clients or server routes, schemas, components, tests, CI, build/deploy config, ADRs, changelogs, or migration notes. Do not use for general prose polishing only; Chinese triggers include document synchronization, update README, docs sync, environment variable documentation, command list, API Document synchronization.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
813 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore4,421 bytesSKILL.mdcore4,421 bytes
Read SKILL.md
# Document synchronization
## Purpose
Synchronize front-end project documentation from code, configuration, tests, types, scripts and runtime templates to avoid README, docs, environment variable descriptions, API/routing descriptions, architectural decisions and migration notes from drifting from actual project behavior.
## Procedure
1. Identify the project stack, document entry and the scope that needs to be synchronized this time; README synchronization must scan the root directory `README*`, `docs/*/README*`, package, application, deployment or runtime related README, and exclude `node_modules`, build products and third-party dependency directories.
2. Gather sources of truth: `package.json`, lockfile, framework and build configurations, `.env.example`, routes, API clients or server routes, types/schemas, components, tests, CI, build/deploy config.
3. Compare commands, environment variables, routes, API behaviors, deployment steps and support matrix in README, docs, ADR, changelog, example prompts, setup/deploy/env docs.
4. Only update stable public conventions; do not write temporary debugging conclusions, one-time reports or unimplemented designs into long-term documents.
5. If the warehouse already has multilingual documents or internationalized README, after updating the public facts of the main README, you must check whether other language READMEs need to be synchronized; function names, command names, script names, package names, component/API names, report file names, paths, environment variables, routing/API names, version constraints, and support matrices must be consistent across languages.
6. Product copy can maintain localized expression, but must not retain old facts, old default recommendations, or expired examples; when high-quality translation is not possible, at least synchronize key facts, and mark the risks of manual translation in the output.View the complete source on GitHubfec-drawio-studio
When your agent uses it
Use when creating editable technical diagrams with draw.io / diagrams.net sources, including architecture diagrams, ERD, UML, sequence diagrams, flowcharts, ML model diagrams, official shape lookup, brand symbols, Graphviz auto-layout, codebase structure maps, .drawio validation, or draw.io CLI export fallback. Do not use for ordinary raster image generation, freehand sketches, interactive canvas/Three.js scenes, or decorative SVG animation. Chinese triggers include draw.io, diagrams.net, editable architecture diagrams, .drawio, ER diagrams, UML, sequence diagrams, auto layout, shape retrieval, code structure diagrams.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
1,613 tokensWhen the skill is activated
Reference documents
3,683 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Tool Resources
- Constraints
- Expected Output
Scripts executed separately
scripts/brand-symbols.mjsscripts/diagram-lint.mjsscripts/diagram-url.mjsscripts/drawio-export.mjsscripts/layout-graph.mjsscripts/png-embed-fix.mjsscripts/scan-go-packages.mjsscripts/scan-js-modules.mjsscripts/scan-python-classes.mjsscripts/scan-python-modules.mjsscripts/scan-rust-modules.mjsscripts/scan-ts-modules.mjsscripts/shape-query.mjsscripts/studio-core.mjs
Files
SKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesSKILL.mdcore7,161 bytesdata/THIRD_PARTY_NOTICES.mddoc1,031 bytesdata/brand-icons.jsonasset12,919 bytesdata/shape-index.jsonasset4,776,086 bytesreferences/data-residency.mddoc1,954 bytesreferences/diagram-patterns.mddoc2,900 bytesreferences/flowchart-quality.mddoc3,360 bytesreferences/layout-and-export.mddoc2,680 bytesreferences/troubleshooting.mddoc1,145 bytesreferences/xml-and-mermaid.mddoc3,977 bytesscripts/brand-symbols.mjsruns4,181 bytesscripts/diagram-lint.mjsruns9,942 bytesscripts/diagram-url.mjsruns3,480 bytesscripts/drawio-export.mjsruns4,479 bytesscripts/layout-graph.mjsruns4,476 bytesscripts/png-embed-fix.mjsruns1,102 bytesscripts/scan-go-packages.mjsruns1,846 bytesscripts/scan-js-modules.mjsruns2,254 bytesscripts/scan-python-classes.mjsruns1,440 bytesscripts/scan-python-modules.mjsruns2,227 bytesscripts/scan-rust-modules.mjsruns1,777 bytesscripts/scan-ts-modules.mjsruns357 bytesscripts/shape-query.mjsruns3,561 bytesscripts/studio-core.mjsruns4,479 bytesstyles/built-in/corporate.jsonasset1,471 bytesstyles/built-in/default.jsonasset1,454 bytesstyles/built-in/handdrawn.jsonasset1,474 bytesstyles/schema.jsonasset3,949 bytes
Read SKILL.md
# Editable technical chart workflow
## Purpose
Generate, verify and export draw.io / diagrams.net technical diagrams that can be edited further.
## Procedure
1. Determine the chart route
- Simple diagrams in Markdown that need long-term maintenance, Mermaid is preferred.
- Use this workflow when you need official icons, swimlanes, complex layouts, layers/tags/metadata, editable PNG/SVG/PDF or `.drawio` sources.
- When you need fast browser opening or sharing, use [diagram-url.mjs](scripts/diagram-url.mjs) to generate the URL; when you need local auditable delivery, always save the `.drawio` source.
- If the user already has Mermaid or CSV content, they can use `diagram-url.mjs --create --type mermaid|csv` to import it to diagrams.net; when long-term maintenance or precise shape is required, convert it to XML.
- If the draw.io MCP App/Tool has been configured on the current host, it can be used as a preview or editing entrance; this skill does not require the installation of MCP server.View the complete source on GitHubfec-e2e-testing
When your agent uses it
Use when creating, maintaining, debugging, or reviewing real-browser end-to-end tests with Playwright or Cypress, including Page Object models, CI artifacts, traces, flaky tests, cross-page visual regression, and critical user journeys such as login, payment, permissions, or CRUD. For layer planning or tests close to UI components, choose the matching testing workflow first; Chinese triggers include E2E, end-to-end testing, Playwright, Cypress.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
716 tokensWhen the skill is activated
Reference documents
1,927 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore3,522 bytesreferences/e2e-ci-reporting.mddoc1,470 bytesreferences/e2e-special-scenarios.mddoc1,869 bytesreferences/e2e-visual-regression.mddoc2,208 bytesreferences/playwright-patterns.mddoc2,301 bytes
Read SKILL.md
# E2E Test Specification
## Purpose
Validate key user journeys with real browsers and uncover integration risks not covered by unit tests.
## Procedure
1. Clarify the key journeys: cross-page processes such as login, purchase, creation, search, permissions, payment, etc. are given priority; if you only choose the test level, do the test hierarchical planning first.
2. New projects will be given priority by Playwright; existing Cypress projects will continue to use Cypress and will not be migrated for the sake of migration.
3. Use Page Object or fixtures to encapsulate login, page locator and shared data, and avoid naked selectors in the spec.
4. Assert that the user can see the results, relying on Locator automatic waiting, network response or visible status, without using fixed sleep.
5. CI must upload HTML report, screenshots, trace or video; Flaky use cases must be isolated, reproduced, marked with sources and associated with issues.
6. When debugging fails, read the trace, console, network and screenshots first, and then change the test; do not misjudge real product defects as flaky.View the complete source on GitHubfec-form-handling
When your agent uses it
Use when building or reviewing substantial forms with React Hook Form, Zod schemas, typed validation, dynamic fields, controlled third-party inputs, file upload, multi-step flows, dependent validation, or form performance. Do not use for trivial 1-3 field forms without validation; Chinese triggers include form, form validation, dynamic fields.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
838 tokensWhen the skill is activated
Reference documents
1,068 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- React Quick Start
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore3,986 bytesreferences/advanced-form-patterns.mddoc4,945 bytes
Read SKILL.md
# Form processing
## Purpose
Manage form status, verification and submission to avoid lags in complex form input.
## Procedure
1. First identify the framework, existing form library of the project, schema verification library, component library and complexity; then introduce special form solutions when there are 10+ fields, dynamic fields, linkage verification, file upload, multi-step process or input lag.
2. Select according to project stack: React can consider React Hook Form + Zod; Vue can consider vee-validate / FormKit + Zod, Yup or Valibot; simple forms can use the framework's native state and basic verification.
3. Use runtime schema or explicit validation functions to guard external input boundaries; TypeScript types can be deduced from the schema, but don’t just write TS types.
4. Clarify default values, field registration, controlled/uncontrolled boundaries and component library adaptation; use `aria-invalid`, `aria-describedby` and `role="alert"` for error prompts.
5. Handle loading, server-side errors, repeated submissions and resets when submitting; use local subscriptions and sub-component isolation to control re-rendering of large forms.
View the complete source on GitHubfec-image-generation
When your agent uses it
Use when generating or editing diagrams, charts, visual assets, posters, UI mockups, product images, infographics, academic figures, comics, avatars, storyboards, brand boards, or image-edit workflows, especially when exported PNGs need visual QA and bounded self-repair. Prefer deterministic Mermaid/SVG/HTML/canvas sources for text-heavy diagrams; use HTML technical diagrams for browser-ready system blueprints, architecture, deployment topology, agent runtime, memory flow, before-after architecture, workflow, sequence, data-flow, lifecycle, runbook, PII/data-lineage, and state-machine diagrams. Do not use for ordinary UI polish without generated imagery.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
2,352 tokensWhen the skill is activated
Reference documents
6,681 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
- Technical diagram quality and tool routing
Scripts executed separately
scripts/diagram-browser.mjsscripts/diagram-layout.mjsscripts/export-diagram.mjsscripts/interactive-diagram-server.mjsscripts/mermaid-render.mjsscripts/png-qa.mjsscripts/tech-diagram-render.mjs
Files
SKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesSKILL.mdcore11,162 bytesassets/interactive-diagram.htmlasset16,545 bytesassets/quality-examples/README.mddoc2,066 bytesassets/quality-examples/architecture.jsonasset2,359 bytesassets/quality-examples/invalid-explicit.jsonasset640 bytesassets/quality-examples/sequence.jsonasset1,036 bytesassets/quality-examples/sequence.mmdasset616 bytesassets/quality-examples/workflow.jsonasset1,831 bytesassets/quality-examples/workflow.mmdasset382 bytesreferences/artifact-routing.mddoc4,381 bytesreferences/diagram-workflows.mddoc6,984 bytesreferences/html-technical-diagrams.mddoc13,734 bytesreferences/png-qa-autofix.mddoc2,960 bytesscripts/diagram-browser.mjsruns7,798 bytesscripts/diagram-layout.mjsruns11,134 bytesscripts/export-diagram.mjsruns13,100 bytesscripts/interactive-diagram-server.mjsruns22,650 bytesscripts/mermaid-render.mjsruns4,615 bytesscripts/png-qa.mjsruns19,638 bytesscripts/tech-diagram-render.mjsruns65,222 bytes
Read SKILL.md
# Image generation and chart workflow
## Purpose
Generate or edit diagrams, visual assets, and image workflows, and perform reviewable self-checks and repair iterations on exported PNGs.
## Procedure
1. Determine product type
- When accuracy of text, structure, and connections is a priority, use Mermaid, SVG, HTML/CSS, canvas, or a graphics library to generate editable sources and then export as PNG.
- Use HTML technical diagrams when the user needs a browser-ready single file with dark/light theme support for system blueprints, architecture, deployment topology, agent runtime, memory flow, before-after architecture, workflow, sequence, data-flow, lifecycle, runbook, state-machine, or PII/data-lineage diagrams.
- Use the compatible HTML `workflow` route when Mermaid is unavailable or browser-specific lane/style delivery is required for process maps, approvals, automation runs, exception paths, and cyclical operating flows that need readable start/end, decision, actor, numbered-step, and summary treatment without requiring diagrams.net.
- Use themed HTML technical diagrams when a system, agent, memory, data, or tool-call map needs semantic node shapes, flow-aware arrows, and a browser-ready source that can still be exported and QA-checked.
- Use the interactive live diagram route when the user benefits from watching nodes and edges appear incrementally in a local browser, or when they want to drag, relabel, remove, zoom, and export a quick diagram during the session.View the complete source on GitHubfec-implement-from-design
When your agent uses it
Use when implementing UI from Figma, Sketch, MasterGo, Pixso, Modao, MockingBot, screenshots, design selections, design tokens, or design-to-code tasks for production frontend components/pages; Chinese triggers include design draft, implementation by design.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
1,440 tokensWhen the skill is activated
Reference documents
160 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Supported design tools
- Target
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore7,058 bytesSKILL.mdcore7,058 bytesSKILL.mdcore7,058 bytesSKILL.mdcore7,058 bytesreferences/design-plan-template.mddoc693 bytes
Read SKILL.md
# Implement according to design draft
## Purpose
Based on the design context of design tools (Figma, Sketch, MasterGo, Pixso, Mokou, Mock), high-fidelity implementation of pages or components emphasizes component reuse, design token mapping, accessibility, and production-oriented front-end implementation.
## Supported design tools
| Tools | MCP Integration | How to obtain design data |
| -------- | ------------------------- | ----------------------------------------- |
| Figma | `figma` / `figma-desktop` | API to obtain design structure and variable definitions |
| Sketch | `sketch` | MCP Get screenshot of design selection |
| MasterGo | `mastergo` | API to get DSL structure data |
| Pixso | `pixso` | Local MCP gets frame data and code |View the complete source on GitHubfec-legacy-to-modern-migration
When your agent uses it
Use when planning or implementing an intentional migration from JavaScript, jQuery, HTML/CSS, server-rendered templates, MPA legacy frontend code, or older framework code toward a modern frontend stack while preserving behavior. Do not use for routine legacy bug fixes that stay in the old stack; Chinese triggers include legacy projects, technology stack upgrades, jQuery migration.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
954 tokensWhen the skill is activated
Reference documents
2,630 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore5,036 bytesreferences/migration-execution-checklist.mddoc8,631 bytesreferences/migration-report-template.mddoc751 bytesreferences/migration-strategy-and-mapping.mddoc3,428 bytes
Read SKILL.md
# Migration from traditional front-end to modern framework
Suitable for scenarios where you are gradually migrating JavaScript + jQuery + HTML/CSS multi-page applications (MPA), server-side template rendering projects, or legacy framework code to React, Vue, Next.js, Nuxt, TypeScript, or retaining MPA form but modernizing modules, builds, types, and tests.
## Purpose
Guide the gradual migration of traditional front-end projects to the target modern stack, provide migration strategies, concept mapping, phased steps and implementation constraints to ensure functional equivalence and controllable risks.
## Procedure
1. First identify the target stack, migration boundaries and whether to retain the MPA/server template form.
2. Load [references/migration-strategy-and-mapping.md](references/migration-strategy-and-mapping.md), select a progressive or one-time rewrite strategy, and clarify the mapping of legacy patterns to the target stack.
3. Load [references/migration-execution-checklist.md](references/migration-execution-checklist.md) to complete inventory inventory, dependency analysis, prioritization and phased migration plan.
4. When writing a migration analysis or migration plan report, load [references/migration-report-template.md](references/migration-report-template.md).View the complete source on GitHubfec-legacy-web-standard
When your agent uses it
Use when maintaining or safely modifying existing non-framework frontend code: vanilla JavaScript, jQuery, HTML/CSS, MPA pages, server-rendered templates, legacy plugins, or long-lived code that should stay in its current stack. Use migration skill when planning a move to React/Vue/TypeScript; Chinese triggers include traditional frontend, native JS, jQuery.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
456 tokensWhen the skill is activated
Reference documents
426 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,290 bytesreferences/legacy-patterns.mddoc1,767 bytes
Read SKILL.md
# Traditional front-end project specifications (JS + jQuery + HTML)
## Purpose
Safely maintain vanilla JS, jQuery, HTML/CSS and server-side template projects without rewriting the technology stack.
## Procedure
1. First confirm whether this change is to maintain the old stack or migrate; switch to the modern migration workflow when migrating to React/Vue/TypeScript.
2. Use the existing architecture and coding style, prioritize fixing problems, and do not introduce multiple modernizations in one change.
3. JavaScript uses IIFE/namespace to reduce global pollution, and event binding is delegated to reasonable containers first.
4. DOM updates cache selectors, batch operations, and escapes user input; Ajax must handle loading, error, empty status, and prevention of repeated submissions.
5. HTML/CSS maintains semantics, label, alt, BEM/existing naming and low selector depth.
6. Key security checks: `.html()`, `innerHTML`, URL parameter rendering, CSRF token and file upload.View the complete source on GitHubfec-list-virtualization
When your agent uses it
Use when optimizing or reviewing large lists, virtual scrolling, windowing, react-window, TanStack Virtual, variable-height rows, dynamic measurement, infinite scroll, grid virtualization, or scroll performance; Chinese triggers include virtual lists, large list optimization, scroll performance.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
462 tokensWhen the skill is activated
Reference documents
922 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,320 bytesSKILL.mdcore2,320 bytesreferences/virtualization-patterns.mddoc4,446 bytes
Read SKILL.md
# List virtualization optimization
## Purpose
Only the visible area is rendered through windowing, which solves the problem of excessive DOM and stuck scrolling in large lists.
## Procedure
1. First confirm the list size and bottleneck: 500+ items, scrolling frame drops, too many DOM nodes, or memory surge before introducing virtualization.
2. First follow the existing framework, dependencies and design system constraints of the project, and then select the library according to the scenario: React can consider `react-window` or TanStack Virtual; Vue/Solid/Svelte, dynamic measurement, grid or cross-framework scenarios give priority to TanStack Virtual; the legacy `react-virtualized` is only maintained and not added.
3. Clarify item size, overscan, container height, key, rolling container and resize behavior.
4. Separate data paging and DOM virtualization during infinite scrolling; data acquisition can be combined with the data acquisition workflow.
5. Verify DOM node count, scrolling FPS, keyboard/screen reader experience, and Ctrl+F/SEO limitations.
View the complete source on GitHubfec-monorepo-project-standard
When your agent uses it
Use when creating, reviewing, or restructuring frontend monorepos with pnpm workspace, Turborepo, Nx, multi-package dependency boundaries, task orchestration, package naming, or package publishing; Chinese triggers include monorepo, workspace, multi-package.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,213 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Tool selection
- Directory structure
- Dependency management
- Turborepo task orchestration
- Nx task orchestration
- Package naming
- Constraints
- Expected Output
Files
SKILL.mdcore5,433 bytesSKILL.mdcore5,433 bytes
Read SKILL.md
# Monorepo Project Specifications
For multi-package front-end repositories using pnpm workspace, Turborepo or Nx.
## Purpose
Standardize the directory structure, dependency management, task orchestration and package release process of the Monorepo project to ensure the build efficiency and version consistency of multi-package collaboration.
## Procedure
1. First confirm whether the repository has used pnpm workspace, Turborepo or Nx, and continue to use the existing package naming and task conventions.
2. Place applications in `apps/` and shared libraries, configuration and tools in `packages/` or existing equivalent directories.
3. Internal dependencies use `workspace:*` to drive the build sequence through the dependency graph.
4. Configure cacheable, parallelizable, and incremental root tasks for build, lint, and test, and specify input, output, and environment variables.View the complete source on GitHubfec-motion-interaction
When your agent uses it
Use when designing, implementing, or reviewing frontend interaction motion, page transitions, scroll animation, Framer Motion, GSAP, Lottie, CSS animation, motion intensity, animation performance, reduced-motion behavior, or cinematic but accessible UI motion. Do not use for SVG-only path drawing, Canvas/WebGL rendering, or ordinary hover states; Chinese triggers include motion design, interactive effects, page transitions, scroll animation, Framer Motion, GSAP.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
1,406 tokensWhen the skill is activated
Reference documents
669 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore7,166 bytesreferences/motion-patterns.mddoc2,565 bytes
Read SKILL.md
# Interactive effects
It is suitable for front-end animation tasks that need to design page transitions, scrolling narratives, component introductions, micro-interactions and feedback rhythms into maintainable, degradable and verifiable forms. Load [motion-patterns.md](references/motion-patterns.md) when a specific implementation pattern is required.
## Purpose
Choose the right animation tools, intensity, and quality gates for your front-end interface.
## Procedure
1. Determine animation responsibilities
- First write down the user intention of the dynamic effect service: positioning, feedback, level changes, status confirmation, narrative guidance or brand memory.
- The tool-based interface is restrained by default, and priority is given to ensuring scanning efficiency; the marketing page and work page can increase the rhythm, but cannot block the main information.
- If animation is merely decorative and does not improve understanding, feedback or brand recognition, it should be deleted or replaced with a static visual treatment.View the complete source on GitHubfec-nextjs-project-standard
When your agent uses it
Use when creating or reviewing Next.js 14+ App Router projects, file routes, layouts, server/client component boundaries, SSR/SSG/ISR, streaming, metadata, middleware, server actions, or Next-specific data fetching. For generic client React component architecture, apply the project's React conventions separately; Chinese triggers include Next.js, App Router.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,557 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Project structure
- Rendering mode
- Data acquisition
- Routing and layout
- Middleware
- Metadata and SEO
- Constraints
- Division of labor with client UI mode
- Expected Output
Files
SKILL.mdcore6,996 bytes
Read SKILL.md
# Next.js project specifications
For repositories using Next.js 14+ with App Router.
## Purpose
Standardize engineering practices for App Router, SSR/SSG/ISR rendering modes, data acquisition, route layout, middleware and SEO metadata in Next.js 14+ projects to ensure server-side priority, performance optimization and maintainability.
## Procedure
1. First identify whether the target belongs to App Router, layout, server data, middleware, metadata or client interaction.
2. Default server-side components take precedence; use `'use client'` only when browser API, interactive state or event handling is required.
3. Clarify SSR / SSG / ISR / CSR rendering mode and Next fetch/cache strategy.
4. Complete the server-side boundaries of `loading.tsx`, `error.tsx`, `not-found.tsx`, metadata and sensitive logic for routing.View the complete source on GitHubfec-nuxt-project-standard
When your agent uses it
Use when creating or reviewing Nuxt 3 projects, file routes, pages, layouts, SSR/SSG/SPA behavior, Nuxt data fetching, route middleware, plugins, modules, server routes, or Nuxt-specific Vue 3 conventions. For generic Vue component architecture, apply the project's Vue conventions separately; Chinese triggers include Nuxt, Nuxt 3.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
1,158 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Project structure
- Rendering mode
- Data acquisition
- Routing and layout
- Middleware
- Plug-ins and modules
- Constraints
- Expected Output
Files
SKILL.mdcore4,760 bytes
Read SKILL.md
# Nuxt 3 Project Specifications
For repositories using Nuxt 3 + Vue 3 + TypeScript.
## Purpose
Standardize the engineering practices of SSR/SSG rendering mode, combined API, automatic import, data acquisition, routing middleware and module plug-ins in the Nuxt 3 project to ensure conventional development and type safety.
## Procedure
1. First identify whether the target belongs to Nuxt pages/layouts, rendering mode, data acquisition, route middleware, plugin/module or server route.
2. Clarify SSR / SSG / SPA selection to avoid server-side executable code relying on `window` or `document`.
3. For data acquisition, Nuxt’s `useFetch` / `useAsyncData` is used first, and the hydration consistency is checked.
4. Route authentication, redirection and permission issues are aligned with the route protection workflow.View the complete source on GitHubfec-performance-optimization
When your agent uses it
Use when diagnosing or improving frontend performance, Core Web Vitals, bundle size, runtime rendering cost, network waterfalls, memory leaks, long tasks, Lighthouse findings, or performance budgets; Chinese triggers include performance optimization, page freeze, slow first screen, bundle volume, Web Vitals.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,164 tokensWhen the skill is activated
Reference documents
1,243 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Budgets
- Checks
- Constraints
- Detailed reference
- Expected Output
Files
SKILL.mdcore6,035 bytesSKILL.mdcore6,035 bytesSKILL.mdcore6,035 bytesSKILL.mdcore6,035 bytesreferences/framework-performance-patterns.mddoc4,232 bytesreferences/report-template.mddoc1,816 bytes
Read SKILL.md
# Front-end performance optimization
## Purpose
Use measurable methods to locate front-end performance bottlenecks, and converge optimization suggestions to the user's main path, build products, and runtime evidence.
## Procedure
1. Lock in experience goals
- Clarify whether the problem is first screen loading, interaction delay, scrolling lag, memory increase, network waterfall, packet size, or visual stability.
- Document routes, devices, network conditions, browsers, replication steps, and currently available metrics.
- When there are no indicators, establish a baseline first and do not directly give generalized suggestions of "optimizing everything".
2. Establish a measurement baselineView the complete source on GitHubfec-pwa-implementation
When your agent uses it
Use when adding or reviewing Progressive Web App capabilities such as installability, manifest metadata, Service Worker registration, Workbox caching, offline fallback, app update prompts, maskable icons, or iOS PWA compatibility. Do not use for general API caching or non-installable performance tuning; Chinese triggers include PWA, offline, Service Worker.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
510 tokensWhen the skill is activated
Reference documents
846 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,617 bytesreferences/manifest-and-icons.mddoc1,331 bytesreferences/service-worker-workbox.mddoc2,071 bytes
Read SKILL.md
# PWA implementation
## Purpose
Make web applications installable, offline and controllable to update.
## Procedure
1. Confirm whether PWA is worth doing: priority is given to mobile/desktop installations, weak network offline, and repeated access scenarios; do not force PWA when it is purely internal backend, has strong real-time streaming media, or only requires ordinary caching.
2. First complete the manifest, icon, theme color and HTML reference; the icon covers at least 192/512, Android needs to be maskable, and iOS needs apple touch icon.
3. Register the Service Worker and design an update prompt; do not forcefully refresh the user page after silently `skipWaiting()`.
4. Use Workbox or framework plug-in to manage precache/runtime cache; sensitive requests such as login, payment, and permission changes must go through the network.
5. Provide offline fallback page and installation prompt UI, and verify initial loading, offline access, update activation, uninstallation and reinstallation.
View the complete source on GitHubfec-react-project-standard
When your agent uses it
Use when designing or reviewing React + TypeScript project structure, feature/module boundaries, component architecture, hooks organization, routing composition, state/API/error/styling defaults, or repository-wide React conventions. Prefer narrower skills for forms, data fetching, tests, accessibility, virtualization, animation, or security deep dives; Chinese triggers include React project specification, React component architecture.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,274 tokensWhen the skill is activated
Reference documents
5,686 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore6,813 bytesreferences/react-performance-patterns.mddoc1,978 bytesreferences/react-project-structure.mddoc7,974 bytesreferences/react-quality-patterns.mddoc6,161 bytesreferences/react-runtime-patterns.mddoc10,263 bytes
Read SKILL.md
# React project specifications
Suitable for medium and large module construction, page reconstruction and engineering structure design in React + TypeScript warehouse.
## Purpose
Provide engineering structure, module boundaries and default implementation conventions for React + TypeScript projects to ensure clear architecture and maintainable code.
## Procedure
This skill mainly solves the problem of "how to design and implement" React engineering tasks, without repeating the basic coding bottom line. When handling React engineering tasks, perform them in the following order:
1. Identify the warehouse and have an agreement
- Directory organizationView the complete source on GitHubfec-refactor-clean
When your agent uses it
Use when safely removing dead frontend code, unused exports, stale components, obsolete routes, unused dependencies, or cleanup targets found by tools such as knip, depcheck, ts-prune, TypeScript, ESLint, or manual review. Do not use for feature rewrites that change behavior; Chinese triggers include dead code, clean up unused, refactor clean, dependency cleanup, delete useless code.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
780 tokensWhen the skill is activated
Reference documents
287 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Frontend-Specific Checks
- Constraints
- Detailed reference
- Expected Output
- Structural Refactoring Boundary
Files
SKILL.mdcore3,955 bytesreferences/report-template.mddoc1,288 bytes
Read SKILL.md
# Refactoring and cleaning
## Purpose
Identify and clean up unused front-end code under validation protection, reducing technical debt while avoiding accidentally deleting dynamic references, routing entries, configuration files, and runtime conventions.
## Procedure
1. Establish a baseline first: run or confirm the current status of lint, type-check, test, and build.
2. Collect candidates:
- Prioritize the use of existing tools in the warehouse, such as knip, depcheck, ts-prune, eslint, and TypeScript.
- When tools are not available, use `rg` to check references, exports, routes, registration points and document entries.
3. Classification by risk:
- SAFE: test fixtures, unreferenced tool functions, explicitly unexported private components.View the complete source on GitHubfec-refactoring
When your agent uses it
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.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
1,080 tokensWhen the skill is activated
Reference documents
1,783 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Core Contract
- Procedure
- Risk Classification
- Diff Budget
- References
- Constraints
- Expected Output
Files
SKILL.mdcore5,340 bytesreferences/principles.mddoc3,147 bytesreferences/refactoring-vs-feature-change.mddoc1,743 bytesreferences/when-to-refactor.mddoc1,548 bytesreferences/workflow.mddoc2,883 bytes
Read SKILL.md
# Skill: Behavior-Preserving Refactoring
## Purpose
Restructure live frontend code in small, evidence-backed steps while preserving the behavior users, callers, tests, routes, and integrations can observe.
## Core Contract
Every execution follows these rules:
1. **Behavior Preservation** — pure refactoring intentionally changes structure, not observable behavior.
2. **Green Baseline First** — record available verification before editing.
3. **One Refactoring at a Time** — one primary structural intent per step.
4. **Verify Every Step** — run the narrowest meaningful check immediately after each step.View the complete source on GitHubfec-refactoring-api
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on function API shape, flags, dependencies, mutability, construction, or command/function trade-offs, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
280 tokensWhen the skill is activated
Reference documents
4,441 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,476 bytesreferences/api-refactorings.mddoc22,060 bytes
Read SKILL.md
# API Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [API Refactorings](references/api-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 10 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-catalog
When your agent uses it
Use when selecting or composing behavior-preserving refactoring techniques after structural evidence is known, especially when multiple candidate transformations, preconditions, or ordering choices must be compared.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
305 tokensWhen the skill is activated
Reference documents
4,282 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Workflow
- Selection Rules
- Quick Reference
Files
SKILL.mdcore1,597 bytesreferences/catalog-index.mddoc10,039 bytesreferences/composition-guide.mddoc2,733 bytesreferences/selection-guide.mddoc3,931 bytes
Read SKILL.md
# Refactoring Catalog Selection
## Overview
Use the complete catalog as a decision aid, not as a list of automatic recipes. Select the smallest technique whose preconditions fit the evidence and behavior contract.
## Workflow
1. Locate the standard technique in [the catalog index](references/catalog-index.md).
2. If starting from a smell or symptom, use [the selection guide](references/selection-guide.md) to compare causes and alternatives.
3. If several transformations are needed, use [the composition guide](references/composition-guide.md) to order only the prerequisites that fit the current code.
4. Load the referenced family detail only when the technique is selected.
## Selection Rules
- A smell can have several valid candidates; determine the actual cause first.
- Prefer reversible, local transformations over broad redesign.View the complete source on GitHubfec-refactoring-control
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on conditional complexity, repeated branches, guards, special cases, or internal invariants, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
280 tokensWhen the skill is activated
Reference documents
2,665 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,506 bytesreferences/conditional-refactorings.mddoc13,663 bytes
Read SKILL.md
# Conditional Logic Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [Conditional Logic Refactorings](references/conditional-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 6 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-data
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on variable meaning, field naming, derived state, or reference/value identity, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
275 tokensWhen the skill is activated
Reference documents
2,058 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,456 bytesreferences/data-refactorings.mddoc10,684 bytes
Read SKILL.md
# Data Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [Data Refactorings](references/data-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 5 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-encapsulation
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on record, collection, value, responsibility, delegation, or algorithm boundaries, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
281 tokensWhen the skill is activated
Reference documents
3,852 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,496 bytesreferences/encapsulation-refactorings.mddoc19,610 bytes
Read SKILL.md
# Encapsulation Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [Encapsulation Refactorings](references/encapsulation-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 9 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-functions
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on function structure, naming, parameters, shared context, or phase boundaries, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
275 tokensWhen the skill is activated
Reference documents
5,008 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,475 bytesreferences/function-refactorings.mddoc24,139 bytes
Read SKILL.md
# Function Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [Function Refactorings](references/function-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 11 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-inheritance
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on legacy OO hierarchies, subtype responsibilities, superclass extraction/collapse, or delegation, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
281 tokensWhen the skill is activated
Reference documents
4,761 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,505 bytesreferences/inheritance-refactorings.mddoc24,376 bytes
Read SKILL.md
# Inheritance Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [Inheritance Refactorings](references/inheritance-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 11 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-move-features
When your agent uses it
Use when behavior-preserving frontend refactoring focuses on behavior/data ownership, statement placement, loops, or dead-code knowledge, and the selected technique needs family-specific mechanics, risks, and JavaScript/TypeScript/React/Vue adaptation.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
281 tokensWhen the skill is activated
Reference documents
3,945 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Procedure
- Quick Reference
- Common Mistakes
Files
SKILL.mdcore1,488 bytesreferences/moving-refactorings.mddoc19,912 bytes
Read SKILL.md
# Moving Feature Refactorings
## Overview
Use this family after evidence identifies a fitting structural transformation. Apply one primary technique at a time and verify immediately.
## Procedure
1. Confirm the selected technique and its preconditions in [Moving Feature Refactorings](references/moving-refactorings.md).
2. Record affected behavior and a diff budget.
3. Apply only the selected technique's smallest viable step.
4. Verify the step before composing another transformation.
5. Stop and reassess when public contracts, lifecycle, state identity, or actual scope exceed expectations.
## Quick Reference
The family reference contains 9 canonical techniques with intent, signals, avoid conditions, mechanics, preservation checkpoints, smell links, composition hints, JavaScript/TypeScript notes, React/Vue notes, adaptation guidance, and original frontend examples.View the complete source on GitHubfec-refactoring-validation
When your agent uses it
Use when proving that a frontend refactoring preserved existing behavior, selecting an appropriate safety net, validating each structural step, or assigning a PASS, PARTIAL, or NOT PROVEN preservation verdict.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
586 tokensWhen the skill is activated
Reference documents
708 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Safety-Net Levels
- Frontend Contract Checklist
- References
- Constraints
- Expected Output
Files
SKILL.mdcore2,975 bytesreferences/behavior-preservation.mddoc1,853 bytesreferences/refactoring-test-checklist.mddoc1,820 bytes
Read SKILL.md
# Skill: Refactoring Validation
## Purpose
Define the observable contract and the smallest credible evidence needed to prove that structural edits preserved existing frontend behavior.
## Procedure
1. Record the relevant behavior contract before substantial edits.
2. Classify safety-net coverage as A, B, or C.
3. Run and record the pre-change baseline.
4. Match verification to the current refactoring risk and affected boundary.
5. After every structural step, run the narrowest sufficient check immediately.
6. If a newly introduced failure appears, revert that step before broader repair.View the complete source on GitHubfec-responsive-layout
When your agent uses it
Use when designing, implementing, or reviewing responsive frontend layouts, mobile-first breakpoints, container queries, fluid grids, data-dense tables, touch targets, safe areas, orientation changes, viewport overflow, or cross-device UI behavior; Chinese triggers include responsive layouts, mobile-side adaptation, breakpoints, container queries, horizontal and vertical screens, touch targets.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
572 tokensWhen the skill is activated
Reference documents
706 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore2,932 bytesreferences/responsive-layout-patterns.mddoc3,290 bytes
Read SKILL.md
# Responsive layout
Suitable for front-end tasks that require pages, tool interfaces, tables, dashboards or components to work stably on multiple devices. Load [references/responsive-layout-patterns.md](references/responsive-layout-patterns.md) when layout patterns and checklists are required.
## Purpose
Design responsive layouts in a content-first, mobile-first, and container-aware manner to avoid relying solely on fixed breakpoints to fix overflow.
## Procedure
1. Clarify the priority of information: On small screens, core tasks, key operations and feedback are retained first; secondary information is folded, postponed or moved to the detail layer.
2. Choose a layout strategy: use mobile-first breakpoints for simple pages; give priority to container query for nested components, card grids and sidebars.
3. Design flow size: use `minmax()`, `clamp()`, `aspect-ratio`, `max-width`, `min-width: 0` and stable grid track to control scaling.
4. Handle data-intensive interfaces: tables, lists, boards, and editors need to explicitly support horizontal scrolling, column prioritization, frozen columns, or mobile summary views.View the complete source on GitHubfec-route-protection
When your agent uses it
Use when implementing or reviewing frontend route protection, auth guards, RBAC, permission routes, login state handling, redirects, middleware, React Router, Next.js, Vue Router, or Nuxt route middleware; Chinese triggers include route protection, permission routing, login state.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
1,113 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore5,375 bytes
Read SKILL.md
#Route protection
## Purpose
Establish clear authentication, authorization and redirection boundaries for front-end applications to avoid unauthorized access and flickering rendering.
## When to Use
- The page needs to be logged in to access, or different roles can see different routes.
- Requires implementing route guards for React Router, Next.js, Nuxt or Vue Router.
- Login expiration, insufficient permissions, and organization/tenant switching need to be handled uniformly.
- Not used to replace server-side authorization; front-end routing protection can only improve the experience and cannot be used as the only security boundary.
## ProcedureView the complete source on GitHubfec-security-review
When your agent uses it
Use when reviewing frontend security risks such as XSS, CSRF, sensitive data exposure, unsafe DOM APIs, untrusted user input, authentication/token handling, payment flows, file upload, CSP, dependency risk, or third-party scripts; Chinese triggers include security review, security check.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
1,040 tokensWhen the skill is activated
Reference documents
840 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Review modes and coverage
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore5,499 bytesreferences/report-template.mddoc1,151 bytesreferences/security-checklist.mddoc2,453 bytes
Read SKILL.md
# Front-end security review
## Review modes and coverage
User-specified scope takes precedence over the default. Use the following three review modes:
- **Change review**: only when recent changes, current edits, staged changes, a PR or a commit are explicitly requested or clearly established by the active task, review those changes and necessary context. For local changes, inspect staged and unstaged diffs and relevant untracked project files within the requested scope; a staged-only request reviews only staged changes. If there are no changes, report that there is nothing to review; do not switch to recent commits or expand scope automatically.
- **Targeted review**: when files or directories are specified, inventory and review existing code in that scope, including unchanged code; no Git diff is required.
- **Project review (default)**: when no scope or change context is specified, or when the entire project is requested, inventory project-owned frontend code, related tests, configuration and dependency declarations, then review in module batches, including unchanged code; no Git diff is required.
Select scope before collecting diffs. A file/directory alone means full review of that scope; a path combined with an explicit change request restricts incremental review to that path. An unqualified invocation defaults to project review even if Git changes exist. At review start, state the selected mode and target scope. When automatically delegating review after edits, pass the current change scope explicitly; do not trigger project review merely because the reviewer was called.
Exclude dependency directories, build outputs, caches, generated files and third-party code by default, and record exclusions. Keep the frontend responsibility boundary; this is not a backend audit. A nonexistent target or a scope with no relevant files must be reported explicitly, not replaced with another scope.
View the complete source on GitHubfec-source-driven-development
When your agent uses it
Use when frontend decisions depend on framework, library, browser, runtime, package, API, or platform behavior that may have changed, including official documentation checks, version-sensitive patterns, migration choices, or public interface assumptions; Chinese triggers include Check official documentation, source code shall prevail, source-driven, version differences.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,246 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Local Knowledge Retrieval
- Source Priority
- Constraints
- Expected Output
Files
SKILL.mdcore6,754 bytesSKILL.mdcore6,754 bytesSKILL.mdcore6,754 bytesSKILL.mdcore6,754 bytesSKILL.mdcore6,754 bytesSKILL.mdcore6,754 bytesSKILL.mdcore6,754 bytes
Read SKILL.md
# Source driven development
## Purpose
Prioritize the use of in-project facts, official documentation, and current version behavior in front-end implementation, review, and architecture decisions, and avoid relying on outdated experience or unverified assumptions.
## Procedure
1. Determine whether it is necessary to check the source
- Source checking is required when new versions of frameworks, routing, rendering modes, caches, build tools, browser APIs, package publishing formats, authentication protocols, or public interfaces are involved.
- When it comes to project commitments, read the README, configuration, templates, existing implementations, testing and migration records of this warehouse first.
- Use the project's existing schema as a source of truth when simply stabilizing the language syntax or significantly partial refactoring.
2. Collect authoritative materialsView the complete source on GitHubfec-state-management
When your agent uses it
Use when choosing, implementing, reviewing, or refactoring frontend state ownership across React, Vue, Next.js, Nuxt, URL state, server state, form state, browser persistence, or global stores. Prefer narrower skills for TanStack Query cache details, browser storage persistence, or form validation internals; Chinese triggers include state management, state ownership, store selection.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
1,211 tokensWhen the skill is activated
Reference documents
743 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore5,581 bytesreferences/state-patterns.mddoc3,339 bytes
Read SKILL.md
# Front-end status management
## Purpose
Determine clear ownership of front-end state to avoid global store bloat, duplicate caching, and derived state synchronization errors.
## Procedure
### 1. Classify status sources first
Don't choose Redux, Zustand, Pinia or Context first. First mark each state to its unique owner, and then decide on the tool.
| Status Type | Typical Example | Default Attribution |
| ---------------- | ------------------------------------ | ------------------------ |View the complete source on GitHubfec-storybook-component-doc
When your agent uses it
Use when setting up or reviewing Storybook component documentation, design-system presentation, isolated component state previews, stories, addons, decorators, MDX docs, component-state interaction checks, visual baselines, or Chromatic. For real-browser cross-page journeys or broader coverage planning, choose the matching testing workflow first; Chinese triggers include Storybook, component documentation, Design System, visual regression.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
539 tokensWhen the skill is activated
Reference documents
615 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,959 bytesSKILL.mdcore2,959 bytesreferences/story-patterns.mddoc2,487 bytes
Read SKILL.md
# Storybook component documentation
## Purpose
Establish documentation, design system display and isolated state preview environment for UI components; interaction and visual testing only cover component states within the Storybook scene.
## Procedure
1. Initialize or identify an existing Storybook configuration, inheriting the project framework adapter, stories globs, themes, and build commands.
2. Each component's Story covers default state, main variant, size, semantic tone, disabled, loading, error, empty, selected, invalid and key edge states.
3. Components that rely on Router, Store, i18n, and ThemeProvider are wrapped with decorators and do not copy the application entry in Story.
4. Use MDX to supplement complex components with usage instructions, Props, slots/children, variant matrices, status examples, accessibility requirements and source code display.
5. When automation is required, connect interaction tests, addon-a11y, Chromatic or Storybook Test Runner; these capabilities serve component documentation and design system display and do not undertake cross-page business journeys.
6. Design system components should record token sources, Tailwind/class variants, dark modes, responsive sizes, and unsupported combinations to avoid consumers guessing at assembly.View the complete source on GitHubfec-svg-animation
When your agent uses it
Use when implementing or reviewing SVG animation, path drawing, icon motion, logo animation, illustration motion, micro-interactions, CSS/SMIL/Framer Motion/GSAP choices, motion accessibility, or fallback behavior; Chinese triggers include SVG animation, path stroke, animation.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,276 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- When to Use
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore5,406 bytes
Read SKILL.md
# SVG animation implementation
## Purpose
Provide maintainable, accessible, and performance-controllable animation solutions for SVG icons, illustrations, and data visualizations.
## When to Use
- SVG icon, logo, illustration or path stroke animation needs to be implemented.
- Framer Motion, GSAP or CSS animation needs to be connected to React/Vue components.
- Need to provide motion reduction according to `prefers-reduced-motion`.
- Not used for complex 3D/WebGL scenes; for such scenes, Canvas / Three.js workflow is preferred.
## ProcedureView the complete source on GitHubfec-tailwind-design-system
When your agent uses it
Use when designing, implementing, or reviewing Tailwind CSS design systems, token mapping, theme extension, utility class governance, component variants, dark mode, responsive utilities, safelists, or maintainable class composition; Chinese triggers include Tailwind, design Token, component variants, dark mode, class management.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
575 tokensWhen the skill is activated
Reference documents
691 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore2,992 bytesreferences/tailwind-system-patterns.mddoc3,385 bytes
Read SKILL.md
#Tailwind Design System
Suitable for front-end tasks hosting product design systems, component variations, and theme rules with Tailwind CSS. Load [references/tailwind-system-patterns.md](references/tailwind-system-patterns.md) when specific configuration, variant, class organization and migration details are needed.
## Purpose
Make the tokens, themes, component variations, and responsive styles in the Tailwind project maintainable instead of scattering one-off utility classes into business code.
## Procedure
1. Identify the current situation: Confirm Tailwind version, configuration location, dark mode strategy, component library, CSS variables, design token and class merging tool.
2. Establish token boundaries: color, spacing, rounded corners, shadow, font, z-index and breakpoints are first derived from the project token or `theme.extend`.
3. Design component variants: Basic components such as buttons, input boxes, cards, pop-up windows, and tables use centralized variant APIs to express size, semantics, status, and density.
4. Control class complexity: Repeated combinations are precipitated into components, slots, variants or local helpers; do not copy long class strings to multiple pages.View the complete source on GitHubfec-tdd-workflow
When your agent uses it
Use when implementing new observable frontend behavior or fixing a behavior-changing bug where a failing test can describe the missing or incorrect behavior first. Apply to components, hooks/composables, utilities, API clients, route guards, or user workflows; pure behavior-preserving refactoring uses an already-green contract instead.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
728 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Pure Refactoring Boundary
- Prove-It Pattern
- Frontend Test Selection
- Constraints
- Expected Output
Files
SKILL.mdcore3,649 bytes
Read SKILL.md
# Front-end TDD workflow
## Purpose
Use the rhythm of "write failing tests first, then implement the minimum code, and then refactor" to deliver front-end functions to avoid supplementing coverage only after implementation.
## Procedure
1. Identify observable behaviors: UI, component contracts, hook/composable return values, route guard results, API client output or error status that users can see.
2. First write a minimum failure test:
- Pure logic first unit testing.
- Prioritize component interaction Testing Library / Vue Test Utils.
- Prioritize critical processes across pages Playwright/Cypress.
3. Run the test and confirm that the failure reason is correct and should come from behavior that has not yet been implemented, rather than a syntax, import, or test environment error.View the complete source on GitHubfec-testing-strategy
When your agent uses it
Use when planning or reviewing a frontend testing strategy, selecting the right test layer by risk, mapping coverage across static checks, unit tests, component tests, integration tests, E2E, Storybook/visual regression, a11y, security, performance, or CI gates. Do not use to write individual component/E2E tests or merely run existing validation commands; Chinese triggers include test strategy, test layering, test plan, coverage matrix.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
802 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore4,065 bytes
Read SKILL.md
# Front-end testing strategy
## Purpose
Choose your testing approach by “closeness to code/level of risk coverage” to avoid cramming all risks into component tests or E2E.
## Procedure
1. Identify the type of change: pure logic, UI components, cross-module processes, browser capabilities, visual stability, dedicated quality risks, or release gates.
2. Establish a test level matrix, at least distinguish:
- Static checking: TypeScript, ESLint, format, dependency security, build.
- Unit testing: utils, hooks/composables, state logic, schema, pure functions.
- Component testing: props/emits, user interaction, loading/error/empty, mock boundaries.
- Lightweight integration testing: form + API mock + routing/Store/Provider context.View the complete source on GitHubfec-typescript-project-standard
When your agent uses it
Use when creating, configuring, reviewing, or debugging TypeScript project standards across frontend apps, libraries, SDKs, CLIs, monorepo packages, tsconfig, strictness, module/moduleResolution, path aliases, project references, declaration files, package exports, public API types, DTOs, advanced generics, discriminated unions, type guards, type narrowing, or type-level regressions. Prefer framework project skills for React/Vue/Next/Nuxt component architecture; Chinese triggers include TypeScript project specification, TS project specification, TypeScript type safety, type modeling, generics, discriminative unions, type narrowing, tsconfig, declaration files.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,106 tokensWhen the skill is activated
Reference documents
1,601 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Files
SKILL.mdcore5,535 bytesSKILL.mdcore5,535 bytesSKILL.mdcore5,535 bytesreferences/type-safety-patterns.mddoc2,727 bytesreferences/type-safety.mddoc4,290 bytes
Read SKILL.md
# TypeScript project specifications
## Purpose
Unify project configuration, type boundaries, and release product rules for the TypeScript layer. Works with front-end applications, component libraries, SDKs, CLIs, monorepo packages, and pure TypeScript tool libraries, but does not take over the framework architecture responsibilities of React, Vue, Next.js, Nuxt, or Vite.
## Procedure
1. Identify TypeScript context
- Application projects: Prioritize checking of `tsconfig` layering, strictness, path aliases, type checking scripts and framework generation types.
- Component library or SDK: Prioritize checking public API, declaration files, package exports, peer dependencies type boundaries and pre-release pack verification.
- CLI or Node tools: Prioritize checking Node target versions, ESM/CJS policies, `moduleResolution`, shebang artifacts, and `process.env` type boundaries.
- Monorepo package: Prioritize checking whether project references, composite builds, inter-package import boundaries, and workspace path aliases leak into release products.
- The component architecture, routing organization, and state management of frameworks such as React, Vue, Next.js, and Nuxt belong to the corresponding framework skills; this process only deals with cross-framework TypeScript contracts and project boundaries.View the complete source on GitHubfec-ui-design
When your agent uses it
Use when building, reviewing, or improving frontend UI that needs product-specific design direction, design-system generation, Master/Page overrides, distinctive visual identity, anti-generic interface choices, first-screen hierarchy, UI polish, chart UX, interaction states, responsive behavior, or visual QA. Interface polishing, interactive state.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
2,645 tokensWhen the skill is activated
Reference documents
2,249 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Scripts executed separately
scripts/design-system.mjs
Files
SKILL.mdcore13,467 bytesSKILL.mdcore13,467 bytesdata/product-rules.jsonasset6,228 bytesdata/stack-ui-rules.jsonasset2,642 bytesdata/style-archetypes.jsonasset6,919 bytesdata/ux-quality-rules.jsonasset4,860 bytesreferences/design-intelligence.mddoc6,614 bytesreferences/master-page-overrides.mddoc1,441 bytesreferences/pre-delivery-checklist.mddoc2,744 bytesscripts/design-system.mjsruns21,324 bytes
Read SKILL.md
#UI design
Suitable for UI tasks that require advancing the front-end interface to be "in line with the product context, scannable, trustworthy, recognizable, and stable in details". When systematic design suggestions are needed, load [design-intelligence.md](references/design-intelligence.md); when long-term precipitation of the design system is required, load [master-page-overrides.md](references/master-page-overrides.md); when doing UI/UX QA before going online, load [pre-delivery-checklist.md](references/pre-delivery-checklist.md).
The executable design system generator is located at [design-system.mjs](scripts/design-system.mjs), and its original knowledge package includes [product-rules.json](data/product-rules.json), [style-archetypes.json](data/style-archetypes.json), [ux-quality-rules.json](data/ux-quality-rules.json) and [stack-ui-rules.json](data/stack-ui-rules.json).
## Purpose
Establish design direction for pages, components, dashboards and tool interfaces, and complete implementable visual and interactive polish.
## Procedure
1. Clarify the work of the interface
- Start by saying what task it helps the user accomplish, rather than choosing a color or layout first.View the complete source on GitHubfec-validation-fix
When your agent uses it
Use when running existing project validation commands and fixing failures after code changes, including lint, type-check, unit/integration test, build, CI, or local script failures. Do not use when the task is to design or author new component/E2E tests; Chinese triggers include validation, check failures, fix failures, CI failures.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
527 tokensWhen the skill is activated
Reference documents
268 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Failure Triage
- Constraints
- Detailed reference
- Expected Output
Files
SKILL.mdcore2,687 bytesreferences/report-template.mddoc1,203 bytes
Read SKILL.md
# Verify and fix
## Purpose
Automatically execute existing verification commands, analyze the reasons for failure and safely repair them to ensure that quality access control meets standards.
## Procedure
1. Identify available commands from package.json or repository documentation.
2. Prioritize execution in the following order:
- lint
- type-check
- unit/integration tests
- buildView the complete source on GitHubfec-vite-project-standard
When your agent uses it
Use when creating, configuring, reviewing, or debugging Vite-based frontend projects, vite.config.ts, env variables, dev server proxy, HMR, plugin ordering, library mode, dependency pre-bundling, bundle splitting, or Vite build performance. Use framework-specific skills for React/Vue component architecture; Chinese triggers include Vite configuration, vite.config, Vite build, Vite performance.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
993 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Minimal Config
- Constraints
- Expected Output
Files
SKILL.mdcore4,588 bytes
Read SKILL.md
# Vite Project Specifications
Design and review of Vite applications, component libraries, development servers, and build configurations.
## Purpose
Standardize Vite configurations, security boundaries, and build performance to avoid common pitfalls of development environments and production builds.
## Procedure
1. Identify the project type
- Application projects check `root`, `base`, `server.proxy`, `envPrefix`, `build` and framework plugins first.
- Component library projects check `build.lib`, type products, peer dependencies external and export entries first.
- Monorepo additional checks for `server.fs.allow`, path aliases and package dependency boundaries.View the complete source on GitHubfec-vue3-project-standard
When your agent uses it
Use when designing or reviewing Vue 3 + TypeScript project structure, SFC/component boundaries, composables organization, route composition, Pinia ownership, API/error/styling defaults, directives, or repository-wide Vue conventions. Prefer narrower skills for forms, data fetching, tests, accessibility, virtualization, animation, or security deep dives; Chinese triggers include Vue 3 project specification, Vue component architecture.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
963 tokensWhen the skill is activated
Reference documents
4,611 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore4,912 bytesreferences/vue3-composables-routing.mddoc5,391 bytesreferences/vue3-performance-patterns.mddoc604 bytesreferences/vue3-project-structure.mddoc8,234 bytesreferences/vue3-state-api-quality.mddoc6,444 bytes
Read SKILL.md
# Vue 3 project specifications
For repositories using Vue 3 + TypeScript.
## Purpose
Provides project structure, component boundaries, Composables, and default implementation conventions for Vue 3 + TypeScript projects to ensure conventional development and type safety.
## Procedure
1. Identify the existing Vue conventions in the warehouse: directory, routing, Pinia, request layer, style system, component library and test framework.
2. Demarcate the boundaries between pages, business components, common components, composables, stores, services and utils.
3. Prioritize the existing automatic import/module export conventions of `<script setup lang="ts">`, composite API and warehouse.
4. Complete state ownership, API layer, error handling, style isolation and special skill offloading when outputting.View the complete source on GitHubfec-web-video-presentation
When your agent uses it
Use when turning an article, talk script, lesson, product demo, or narrated explanation into a recordable 16:9 web presentation with step-driven scenes, optional narration alignment, theme tokens, and screen-recording guidance; Chinese triggers include web video, dynamic demonstration, spoken script to video, screen-recordable demonstration, 16:9 demonstration.
What it loads into context
Frontmatter
80 tokensAlways available to the agent
SKILL.md
986 tokensWhen the skill is activated
Reference documents
1,061 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Constraints
- Expected Output
Scripts executed separately
scripts/create-video-presentation.mjs
Files
SKILL.mdcore4,925 bytesSKILL.mdcore4,925 bytesSKILL.mdcore4,925 bytesdata/starter-themes.jsonasset1,822 bytesreferences/chapter-craft.mddoc1,734 bytesreferences/content-plan.mddoc1,354 bytesreferences/recording-and-audio.mddoc1,052 bytesreferences/theme-system.mddoc1,032 bytesscripts/create-video-presentation.mjsruns10,857 bytes
Read SKILL.md
# Web video demonstration
## Purpose
Convert articles, oral presentations, courses, product explanations or technology sharing into screen-recordable 16:9 web presentations. The product should be like a clickable video stage: each step carries a spoken rhythm, the visual design serves the content rhythm, and can be stably recorded using the browser.
## Procedure
1. Determine the input form
- When the user submits an article or long text, it is first split into a spoken draft and an outline.
- When the user broadcasts the manuscript to the ready-made script, the original order is retained and only the outline, chapters and steps are added.
- When the user only provides a topic but no content, first ask for materials, outlines or key points; do not make up the entire content for the user.
2. Generate a content planView the complete source on GitHubfec-web-workers
When your agent uses it
Use when moving expensive browser work off the main thread with Web Workers, SharedWorker, worker pools, Comlink, transferable objects, Vite/Webpack worker integration, or UI responsiveness fixes. Do not use for lightweight synchronous work or DOM manipulation; Chinese triggers include Web Worker, background thread, main thread blocking.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
473 tokensWhen the skill is activated
Reference documents
785 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Procedure
- Detailed reference
- Constraints
- Expected Output
Files
SKILL.mdcore2,482 bytesSKILL.mdcore2,482 bytesreferences/advanced-workers.mddoc1,540 bytesreferences/basic-worker.mddoc1,722 bytes
Read SKILL.md
# Web Workers
## Purpose
Move expensive calculations off the main thread and keep input, scrolling, and animations responsive.
## Procedure
1. Confirm the bottleneck first: consider workers only if the task exceeds about 10ms, user input delay is obvious, FPS drops, or large file parsing/image processing/encryption calculation.
2. Choose a communication model: use `postMessage` for simple tasks, use Comlink for functional RPC, use Worker pool for a large number of parallel small tasks, and use SharedWorker for cross-Tab synchronization.
3. Design the message protocol: request/response types, error types, cancellation or timeout strategies must be clear.
4. Prioritize Transferable Objects when transferring large objects; don’t let structured cloning swallow up the benefits brought by Worker.
5. `terminate()` when a component or page is unloaded and verify main thread improvements through Profiler, Performance panel or FPS metrics.
View the complete source on GitHubSkills included
- fec-accessibility-check
- fec-alchemy
- fec-api-integration
- fec-backend-requirements-handoff
- fec-browser-storage
- fec-canvas-threejs
- fec-code-review
- fec-code-smells
- fec-component-testing
- fec-data-fetching
- fec-debug-framework
- fec-dependency-upgrade
- fec-doc-sync
- fec-drawio-studio
- fec-e2e-testing
- fec-form-handling
- fec-image-generation
- fec-implement-from-design
- fec-legacy-to-modern-migration
- fec-legacy-web-standard
- fec-list-virtualization
- fec-monorepo-project-standard
- fec-motion-interaction
- fec-nextjs-project-standard
- fec-nuxt-project-standard
- fec-performance-optimization
- fec-pwa-implementation
- fec-react-project-standard
- fec-refactor-clean
- fec-refactoring
- fec-refactoring-api
- fec-refactoring-catalog
- fec-refactoring-control
- fec-refactoring-data
- fec-refactoring-encapsulation
- fec-refactoring-functions
- fec-refactoring-inheritance
- fec-refactoring-move-features
- fec-refactoring-validation
- fec-responsive-layout
- fec-route-protection
- fec-security-review
- fec-source-driven-development
- fec-state-management
- fec-storybook-component-doc
- fec-svg-animation
- fec-tailwind-design-system
- fec-tdd-workflow
- fec-testing-strategy
- fec-typescript-project-standard
- fec-ui-design
- fec-validation-fix
- fec-vite-project-standard
- fec-vue3-project-standard
- fec-web-video-presentation
- fec-web-workers
- fec-accessibility-check
- fec-alchemy
- fec-api-integration
- fec-backend-requirements-handoff
- fec-browser-storage
- fec-canvas-threejs
- fec-code-review
- fec-code-smells
- fec-component-testing
- fec-data-fetching
- fec-debug-framework
- fec-dependency-upgrade
- fec-doc-sync
- fec-drawio-studio
- fec-e2e-testing
- fec-form-handling
- fec-image-generation
- fec-implement-from-design
- fec-legacy-to-modern-migration
- fec-legacy-web-standard
- fec-list-virtualization
- fec-monorepo-project-standard
- fec-motion-interaction
- fec-nextjs-project-standard
- fec-nuxt-project-standard
- fec-performance-optimization
- fec-pwa-implementation
- fec-react-project-standard
- fec-refactor-clean
- fec-refactoring
- fec-refactoring-api
- fec-refactoring-catalog
- fec-refactoring-control
- fec-refactoring-data
- fec-refactoring-encapsulation
- fec-refactoring-functions
- fec-refactoring-inheritance
- fec-refactoring-move-features
- fec-refactoring-validation
- fec-responsive-layout
- fec-route-protection
- fec-security-review
- fec-source-driven-development
- fec-state-management
- fec-storybook-component-doc
- fec-svg-animation
- fec-tailwind-design-system
- fec-tdd-workflow
- fec-testing-strategy
- fec-typescript-project-standard
- fec-ui-design
- fec-validation-fix
- fec-vite-project-standard
- fec-vue3-project-standard
- fec-web-video-presentation
- fec-web-workers
Repository facts
- License
- MIT
- Created
- Mar 17, 2026
- Last pushed
- Nov 6, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 184 notes
hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedhooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteshooks/hooks.json:1Plugin-wide analysis incomplete; see repository noteslocalized/zh-CN/skills/fec-drawio-studio/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedlocalized/zh-CN/skills/fec-drawio-studio/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 148 network referencesin 37 files: fec-image-generation/scripts/interactive-diagram-server.mjs:46 fec-image-generation/scripts/interactive-diagram-server.mjs:46 fec-drawio-studio/scripts/diagram-url.mjs:19 and 34 more
- No hidden or obfuscated text
- No instruction overrides
- 70 executable scriptsin 46 files: skills/fec-image-generation/scripts/png-qa.mjs:1 skills/fec-web-video-presentation/scripts/create-video-presentation.mjs:1 skills/fec-drawio-studio/scripts/png-embed-fix.mjs:1 and 43 more
- No access to secrets
- No requests to vote in Hot
Show all 218 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 24
"email": "pengbaowen@msn.com" }, "homepage": "https://github.com/bovinphang/frontend-craft", - Network accessline 25
}, "homepage": "https://github.com/bovinphang/frontend-craft", "repository": "https://github.com/bovinphang/frontend-craft", - Network accessline 26
"homepage": "https://github.com/bovinphang/frontend-craft", - Network accessline 27
"repository": "https://github.com/bovinphang/frontend-craft",
localized/zh-CN/skills/fec-api-integration/references/integration-patterns.md
- Network accessline 17
init: RequestInit = {}, ): Promise<T> { const response = await fetch(`${import.meta.env.VITE_API_URL}${path}`, { - Network accessline 18
): Promise<T> { const response = await fetch(`${import.meta.env.VITE_API_URL}${path}`, { ...init, - Network accessline 19
const response = await fetch(`${import.meta.env.VITE_API_URL}${path}`, {
localized/zh-CN/skills/fec-debug-framework/SKILL.md
- Network accessline 135
- curl 独立复现(排除前端干扰)
localized/zh-CN/skills/fec-drawio-studio/data/brand-icons.json
- Network accessline 2
"package": "@lobehub/icons-static-svg", "version": "1.91.0", "cdn": "https://unpkg.com/@lobehub/icons-static-svg@1.91.0/icons/", - Network accessline 3
"version": "1.91.0", "cdn": "https://unpkg.com/@lobehub/icons-static-svg@1.91.0/icons/", "icons": [ - Network accessline 4
"cdn": "https://unpkg.com/@lobehub/icons-static-svg@1.91.0/icons/",
localized/zh-CN/skills/fec-drawio-studio/scripts/brand-symbols.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 38
const slug = SIMPLE.get(squish(query)); if (slug) { const url = `https://cdn.simpleicons.org/${slug}`; - Network accessline 39
if (slug) { const url = `https://cdn.simpleicons.org/${slug}`; results.push({ brand: squish(query), file: `simpleicons:${slug}`, w: size, h: size, style: STYLE_PREFIX + (options.embed ? await dataUri(url) : url) }); - Network accessline 40
const url = `https://cdn.simpleicons.org/${slug}`; - Network accessline 76
async function dataUri(url) { const response = await fetch(url); - Network accessline 77
const response = await fetch(url);
localized/zh-CN/skills/fec-drawio-studio/scripts/diagram-lint.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/diagram-url.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 19
export function viewerUrl(xml, options = {}) { const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://viewer.diagrams.net/"); - Network accessline 20
const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://viewer.diagrams.net/"); - Network accessline 24
export function editorUrl(xml, options = {}) { const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); - Network accessline 25
const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); - Network accessline 29
export function createUrl(content, options = {}) { const type = normalizeType(options.type); const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); - Network accessline 30
const type = normalizeType(options.type); const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); const params = new URLSearchParams(); - Network accessline 31
const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/");
localized/zh-CN/skills/fec-drawio-studio/scripts/drawio-export.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 12
"macOS: brew install --cask drawio", "Linux: install drawio from your package manager or snap install drawio", "Manual download: https://github.com/jgraph/drawio-desktop/releases", - Network accessline 13
"Linux: install drawio from your package manager or snap install drawio", "Manual download: https://github.com/jgraph/drawio-desktop/releases", ]; - Network accessline 14
"Manual download: https://github.com/jgraph/drawio-desktop/releases",
localized/zh-CN/skills/fec-drawio-studio/scripts/layout-graph.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/png-embed-fix.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/scan-go-packages.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/scan-js-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/scan-python-classes.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/scan-python-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/scan-rust-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/scan-ts-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/shape-query.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/scripts/studio-core.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-drawio-studio/styles/schema.json
localized/zh-CN/skills/fec-e2e-testing/references/playwright-patterns.md
- Network accessline 68
reporter: [["html"], ["junit", { outputFile: "playwright-results.xml" }]], use: { baseURL: process.env.BASE_URL || "http://localhost:3000", - Network accessline 69
use: { baseURL: process.env.BASE_URL || "http://localhost:3000", trace: "on-first-retry", - Network accessline 70
baseURL: process.env.BASE_URL || "http://localhost:3000", - Network accessline 79
webServer: { command: "npm run dev", url: "http://localhost:3000", - Network accessline 80
command: "npm run dev", url: "http://localhost:3000", reuseExistingServer: !process.env.CI, - Network accessline 81
url: "http://localhost:3000",
localized/zh-CN/skills/fec-image-generation/SKILL.md
- Network accessline 40
```bash node skills/fec-image-generation/scripts/interactive-diagram-server.mjs --port 6100 curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"init","title":"Checkout Flow","direction":"TB"}' - Network accessline 41
node skills/fec-image-generation/scripts/interactive-diagram-server.mjs --port 6100 curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"init","title":"Checkout Flow","direction":"TB"}' curl -s "http://127.0.0.1:6100/cm - Network accessline 42
curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"init","title":"Checkout Flow","direction":"TB"}' - Network accessline 43
curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"node","id":"cart","label":"Review cart","type":"process"}'
localized/zh-CN/skills/fec-image-generation/assets/interactive-diagram.html
- Network accessline 113
const session = new URLSearchParams(location.search).get('s') || 'default'; const state = { title: '交互式图表', direction: 'TB', nodes: new Map(), edges: [], scale: 1, tx: 24, ty: 24, selected: null }; const ns = 'http://www.w3.org/2000 - Network accessline 115
const ns = 'http://www.w3.org/2000/svg'; - Network accessline 304
} async function restore() { const response = await fetch(`/state?s=${encodeURIComponent(session)}`); - Network accessline 305
async function restore() { const response = await fetch(`/state?s=${encodeURIComponent(session)}`); const commands = await response.json(); - Network accessline 306
const response = await fetch(`/state?s=${encodeURIComponent(session)}`);
localized/zh-CN/skills/fec-image-generation/references/diagram-workflows.md
- Network accessline 26
打开 `http://127.0.0.1:6100/?s=meaningful-session-id`,再向 `/cmd?s=meaningful-session-id` 发送命令。每张图都必须使用唯一 session id。先发送 `init`,再添加节点,最后添加连线;每条命令尽量小,让浏览器能持续增量更新。
localized/zh-CN/skills/fec-image-generation/scripts/diagram-browser.mjs
- Executable scriptline 1
Executable file - Network accessline 51
const page = path.join(dir, "diagram.html"), profile = path.join(dir, "profile"); fs.writeFileSync(page, html); const child = spawn(browser, ["--headless=new", "--disable-gpu", "--no-first-run", "--no-default-browser-check", "--hide-scr - Network accessline 52
fs.writeFileSync(page, html); const child = spawn(browser, ["--headless=new", "--disable-gpu", "--no-first-run", "--no-default-browser-check", "--hide-scrollbars", "--remote-debugging-port=0", "--remote-allow-origins=http://localhost", `- - Network accessline 53
const child = spawn(browser, ["--headless=new", "--disable-gpu", "--no-first-run", "--no-default-browser-check", "--hide-scrollbars", "--remote-debugging-port=0", "--remote-allow-origins=http://localhost", `--user-data-dir=${profile}`, path - Network accessline 70
let target; while (Date.now() < deadline) { const pages = await (await fetch(`http://127.0.0.1:${port}/json/list`, { signal: AbortSignal.timeout(Math.min(5000, options.timeoutMs)) })).json(); - Network accessline 71
while (Date.now() < deadline) { const pages = await (await fetch(`http://127.0.0.1:${port}/json/list`, { signal: AbortSignal.timeout(Math.min(5000, options.timeoutMs)) })).json(); target = pages.find(/** @param {{type:string,url - Network accessline 72
const pages = await (await fetch(`http://127.0.0.1:${port}/json/list`, { signal: AbortSignal.timeout(Math.min(5000, options.timeoutMs)) })).json();
localized/zh-CN/skills/fec-image-generation/scripts/diagram-layout.mjs
- Executable scriptline 1
Executable file
localized/zh-CN/skills/fec-image-generation/scripts/export-diagram.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-image-generation/scripts/interactive-diagram-server.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 46
listenWithFallback(server, options.port, options.host) .then((port) => { const status = { ok: true, host: options.host, port, url: `http://${options.host}:${port}/` }; - Network accessline 47
.then((port) => { const status = { ok: true, host: options.host, port, url: `http://${options.host}:${port}/` }; console.log(JSON.stringify(status)); - Network accessline 48
const status = { ok: true, host: options.host, port, url: `http://${options.host}:${port}/` }; - Network accessline 82
Starts a local interactive diagram server with session-scoped SSE updates. Open http://127.0.0.1:6100/?s=my-session and POST commands to /cmd?s=my-session.`); - Network accessline 83
Open http://127.0.0.1:6100/?s=my-session and POST commands to /cmd?s=my-session.`); - Network accessline 149
*/ async function route(req, res) { const url = new URL(req.url ?? "/", `http://${req.headers.host ?? "127.0.0.1"}`); - Network accessline 150
async function route(req, res) { const url = new URL(req.url ?? "/", `http://${req.headers.host ?? "127.0.0.1"}`); const sessionId = sanitizeSessionId(url.searchParams.get("s") ?? "default"); - Network accessline 151
const url = new URL(req.url ?? "/", `http://${req.headers.host ?? "127.0.0.1"}`); - Network accessline 578
const byId = new Map(model.nodes.map((node) => [node.id, node])); const edges = model.edges.map((edge) => renderSvgEdge(edge, byId)).join("\n"); return `<svg xmlns="http://www.w3.org/2000/svg" width="${width}" height="${height}" viewBox - Network accessline 579
const edges = model.edges.map((edge) => renderSvgEdge(edge, byId)).join("\n"); return `<svg xmlns="http://www.w3.org/2000/svg" width="${width}" height="${height}" viewBox="0 0 ${width} ${height}"> <style>text{font-family:Arial,sans-serif; - Network accessline 580
return `<svg xmlns="http://www.w3.org/2000/svg" width="${width}" height="${height}" viewBox="0 0 ${width} ${height}">
localized/zh-CN/skills/fec-image-generation/scripts/mermaid-render.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-image-generation/scripts/png-qa.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-image-generation/scripts/tech-diagram-render.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 673
height = Math.ceil(Math.max(height, ...routeObstacles.map((b) => b.y + b.height + 40), ...textBounds.map((b) => b.y + b.height + 40), ...occupiedRoutes.flat().map((p) => p[1] + 40))); finalCanvas = { width, height }; return `<svg class= - Network accessline 674
finalCanvas = { width, height }; return `<svg class="tech-diagram" data-theme="light" data-visual-style="default" data-export-root="1" role="img" viewBox="0 0 ${width} ${height}" xmlns="http://www.w3.org/2000/svg"> <defs> - Network accessline 675
return `<svg class="tech-diagram" data-theme="light" data-visual-style="default" data-export-root="1" role="img" viewBox="0 0 ${width} ${height}" xmlns="http://www.w3.org/2000/svg">
localized/zh-CN/skills/fec-monorepo-project-standard/SKILL.md
localized/zh-CN/skills/fec-react-project-standard/references/react-runtime-patterns.md
localized/zh-CN/skills/fec-ui-design/scripts/design-system.mjs
- Executable scriptline 1
#!/usr/bin/env node
localized/zh-CN/skills/fec-vite-project-standard/SKILL.md
localized/zh-CN/skills/fec-vue3-project-standard/references/vue3-composables-routing.md
localized/zh-CN/skills/fec-web-video-presentation/scripts/create-video-presentation.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-api-integration/references/integration-patterns.md
- Network accessline 17
init: RequestInit = {}, ): Promise<T> { const response = await fetch(`${import.meta.env.VITE_API_URL}${path}`, { - Network accessline 18
): Promise<T> { const response = await fetch(`${import.meta.env.VITE_API_URL}${path}`, { ...init, - Network accessline 19
const response = await fetch(`${import.meta.env.VITE_API_URL}${path}`, {
skills/fec-debug-framework/SKILL.md
- Network accessline 135
- curl independent reproduction (excluding front-end interference)
skills/fec-drawio-studio/data/brand-icons.json
- Network accessline 2
"package": "@lobehub/icons-static-svg", "version": "1.91.0", "cdn": "https://unpkg.com/@lobehub/icons-static-svg@1.91.0/icons/", - Network accessline 3
"version": "1.91.0", "cdn": "https://unpkg.com/@lobehub/icons-static-svg@1.91.0/icons/", "icons": [ - Network accessline 4
"cdn": "https://unpkg.com/@lobehub/icons-static-svg@1.91.0/icons/",
skills/fec-drawio-studio/scripts/brand-symbols.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 38
const slug = SIMPLE.get(squish(query)); if (slug) { const url = `https://cdn.simpleicons.org/${slug}`; - Network accessline 39
if (slug) { const url = `https://cdn.simpleicons.org/${slug}`; results.push({ brand: squish(query), file: `simpleicons:${slug}`, w: size, h: size, style: STYLE_PREFIX + (options.embed ? await dataUri(url) : url) }); - Network accessline 40
const url = `https://cdn.simpleicons.org/${slug}`; - Network accessline 76
async function dataUri(url) { const response = await fetch(url); - Network accessline 77
const response = await fetch(url);
skills/fec-drawio-studio/scripts/diagram-lint.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/diagram-url.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 19
export function viewerUrl(xml, options = {}) { const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://viewer.diagrams.net/"); - Network accessline 20
const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://viewer.diagrams.net/"); - Network accessline 24
export function editorUrl(xml, options = {}) { const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); - Network accessline 25
const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); - Network accessline 29
export function createUrl(content, options = {}) { const type = normalizeType(options.type); const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); - Network accessline 30
const type = normalizeType(options.type); const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/"); const params = new URLSearchParams(); - Network accessline 31
const baseUrl = normalizeBaseUrl(options.baseUrl ?? "https://app.diagrams.net/");
skills/fec-drawio-studio/scripts/drawio-export.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 12
"macOS: brew install --cask drawio", "Linux: install drawio from your package manager or snap install drawio", "Manual download: https://github.com/jgraph/drawio-desktop/releases", - Network accessline 13
"Linux: install drawio from your package manager or snap install drawio", "Manual download: https://github.com/jgraph/drawio-desktop/releases", ]; - Network accessline 14
"Manual download: https://github.com/jgraph/drawio-desktop/releases",
skills/fec-drawio-studio/scripts/layout-graph.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/png-embed-fix.mjs
skills/fec-drawio-studio/scripts/scan-go-packages.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/scan-js-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/scan-python-classes.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/scan-python-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/scan-rust-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/scan-ts-modules.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/shape-query.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/scripts/studio-core.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-drawio-studio/styles/schema.json
skills/fec-e2e-testing/references/playwright-patterns.md
- Network accessline 68
reporter: [["html"], ["junit", { outputFile: "playwright-results.xml" }]], use: { baseURL: process.env.BASE_URL || "http://localhost:3000", - Network accessline 69
use: { baseURL: process.env.BASE_URL || "http://localhost:3000", trace: "on-first-retry", - Network accessline 70
baseURL: process.env.BASE_URL || "http://localhost:3000", - Network accessline 79
webServer: { command: "npm run dev", url: "http://localhost:3000", - Network accessline 80
command: "npm run dev", url: "http://localhost:3000", reuseExistingServer: !process.env.CI, - Network accessline 81
url: "http://localhost:3000",
skills/fec-image-generation/SKILL.md
- Network accessline 40
```bash node skills/fec-image-generation/scripts/interactive-diagram-server.mjs --port 6100 curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"init","title":"Checkout Flow","direction":"TB"}' - Network accessline 41
node skills/fec-image-generation/scripts/interactive-diagram-server.mjs --port 6100 curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"init","title":"Checkout Flow","direction":"TB"}' curl -s "http://127.0.0.1:6100/cm - Network accessline 42
curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"init","title":"Checkout Flow","direction":"TB"}' - Network accessline 43
curl -s "http://127.0.0.1:6100/cmd?s=checkout-flow" -d '{"cmd":"node","id":"cart","label":"Review cart","type":"process"}'
skills/fec-image-generation/assets/interactive-diagram.html
- Network accessline 113
const session = new URLSearchParams(location.search).get('s') || 'default'; const state = { title: 'Interactive Diagram', direction: 'TB', nodes: new Map(), edges: [], scale: 1, tx: 24, ty: 24, selected: null }; const ns = 'http://w - Network accessline 115
const ns = 'http://www.w3.org/2000/svg'; - Network accessline 304
} async function restore() { const response = await fetch(`/state?s=${encodeURIComponent(session)}`); - Network accessline 305
async function restore() { const response = await fetch(`/state?s=${encodeURIComponent(session)}`); const commands = await response.json(); - Network accessline 306
const response = await fetch(`/state?s=${encodeURIComponent(session)}`);
skills/fec-image-generation/references/diagram-workflows.md
- Network accessline 26
Open `http://127.0.0.1:6100/?s=meaningful-session-id`, then send commands to `/cmd?s=meaningful-session-id`. Always use a unique session id for each diagram. Start with `init`, add nodes before edges, and keep each command small enough that
skills/fec-image-generation/scripts/diagram-browser.mjs
- Executable scriptline 1
Executable file - Network accessline 51
const page = path.join(dir, "diagram.html"), profile = path.join(dir, "profile"); fs.writeFileSync(page, html); const child = spawn(browser, ["--headless=new", "--disable-gpu", "--no-first-run", "--no-default-browser-check", "--hide-scr - Network accessline 52
fs.writeFileSync(page, html); const child = spawn(browser, ["--headless=new", "--disable-gpu", "--no-first-run", "--no-default-browser-check", "--hide-scrollbars", "--remote-debugging-port=0", "--remote-allow-origins=http://localhost", `- - Network accessline 53
const child = spawn(browser, ["--headless=new", "--disable-gpu", "--no-first-run", "--no-default-browser-check", "--hide-scrollbars", "--remote-debugging-port=0", "--remote-allow-origins=http://localhost", `--user-data-dir=${profile}`, path - Network accessline 70
let target; while (Date.now() < deadline) { const pages = await (await fetch(`http://127.0.0.1:${port}/json/list`, { signal: AbortSignal.timeout(Math.min(5000, options.timeoutMs)) })).json(); - Network accessline 71
while (Date.now() < deadline) { const pages = await (await fetch(`http://127.0.0.1:${port}/json/list`, { signal: AbortSignal.timeout(Math.min(5000, options.timeoutMs)) })).json(); target = pages.find(/** @param {{type:string,url - Network accessline 72
const pages = await (await fetch(`http://127.0.0.1:${port}/json/list`, { signal: AbortSignal.timeout(Math.min(5000, options.timeoutMs)) })).json();
skills/fec-image-generation/scripts/diagram-layout.mjs
- Executable scriptline 1
Executable file
skills/fec-image-generation/scripts/export-diagram.mjs
skills/fec-image-generation/scripts/interactive-diagram-server.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 46
listenWithFallback(server, options.port, options.host) .then((port) => { const status = { ok: true, host: options.host, port, url: `http://${options.host}:${port}/` }; - Network accessline 47
.then((port) => { const status = { ok: true, host: options.host, port, url: `http://${options.host}:${port}/` }; console.log(JSON.stringify(status)); - Network accessline 48
const status = { ok: true, host: options.host, port, url: `http://${options.host}:${port}/` }; - Network accessline 82
Starts a local interactive diagram server with session-scoped SSE updates. Open http://127.0.0.1:6100/?s=my-session and POST commands to /cmd?s=my-session.`); - Network accessline 83
Open http://127.0.0.1:6100/?s=my-session and POST commands to /cmd?s=my-session.`); - Network accessline 149
*/ async function route(req, res) { const url = new URL(req.url ?? "/", `http://${req.headers.host ?? "127.0.0.1"}`); - Network accessline 150
async function route(req, res) { const url = new URL(req.url ?? "/", `http://${req.headers.host ?? "127.0.0.1"}`); const sessionId = sanitizeSessionId(url.searchParams.get("s") ?? "default"); - Network accessline 151
const url = new URL(req.url ?? "/", `http://${req.headers.host ?? "127.0.0.1"}`); - Network accessline 578
const byId = new Map(model.nodes.map((node) => [node.id, node])); const edges = model.edges.map((edge) => renderSvgEdge(edge, byId)).join("\n"); return `<svg xmlns="http://www.w3.org/2000/svg" width="${width}" height="${height}" viewBox - Network accessline 579
const edges = model.edges.map((edge) => renderSvgEdge(edge, byId)).join("\n"); return `<svg xmlns="http://www.w3.org/2000/svg" width="${width}" height="${height}" viewBox="0 0 ${width} ${height}"> <style>text{font-family:Arial,sans-serif; - Network accessline 580
return `<svg xmlns="http://www.w3.org/2000/svg" width="${width}" height="${height}" viewBox="0 0 ${width} ${height}">
skills/fec-image-generation/scripts/mermaid-render.mjs
- Executable scriptline 1
#!/usr/bin/env node
skills/fec-image-generation/scripts/png-qa.mjs
- Executable scriptline 1
#!/usr/bin/env node - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
Executable file; content unavailable - Executable scriptline 1
#!/usr/bin/env node
skills/fec-image-generation/scripts/tech-diagram-render.mjs
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 673
height = Math.ceil(Math.max(height, ...routeObstacles.map((b) => b.y + b.height + 40), ...textBounds.map((b) => b.y + b.height + 40), ...occupiedRoutes.flat().map((p) => p[1] + 40))); finalCanvas = { width, height }; return `<svg class= - Network accessline 674
finalCanvas = { width, height }; return `<svg class="tech-diagram" data-theme="light" data-visual-style="default" data-export-root="1" role="img" viewBox="0 0 ${width} ${height}" xmlns="http://www.w3.org/2000/svg"> <defs> - Network accessline 675
return `<svg class="tech-diagram" data-theme="light" data-visual-style="default" data-export-root="1" role="img" viewBox="0 0 ${width} ${height}" xmlns="http://www.w3.org/2000/svg">
skills/fec-monorepo-project-standard/SKILL.md
skills/fec-react-project-standard/references/react-runtime-patterns.md
skills/fec-ui-design/scripts/design-system.mjs
skills/fec-vite-project-standard/SKILL.md
skills/fec-vue3-project-standard/references/vue3-composables-routing.md
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 8 facts
- Contacts cdn.simpleicons.org, which SKILL.md, the README and the plugin manifest do not mentionfec-drawio-studio/scripts/brand-symbols.mjs:40High confidence
- Contacts github.com, which SKILL.md, the README and the plugin manifest do not mentionfec-drawio-studio/scripts/drawio-export.mjs:14High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionfec-image-generation/scripts/interactive-diagram-server.mjs:580High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionfec-image-generation/scripts/tech-diagram-render.mjs:675High confidence
- Contacts cdn.simpleicons.org, which SKILL.md, the README and the plugin manifest do not mentionfec-drawio-studio/scripts/brand-symbols.mjs:40High confidence
- Contacts github.com, which SKILL.md, the README and the plugin manifest do not mentionfec-drawio-studio/scripts/drawio-export.mjs:14High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionfec-image-generation/scripts/interactive-diagram-server.mjs:580High confidence
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionfec-image-generation/scripts/tech-diagram-render.mjs:675High confidence
Signal confidence: 190 facts
- Network access in code of documentationfec-api-integration/references/integration-patterns.md:17Low confidence
- Network access in code of documentationfec-api-integration/references/integration-patterns.md:18Low confidence
- Network access in code of documentationfec-api-integration/references/integration-patterns.md:19Low confidence
- Network access in prose of the SKILL.mdfec-debug-framework/SKILL.md:135Low confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/brand-symbols.mjs:1High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/brand-symbols.mjs:38High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/brand-symbols.mjs:39High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/brand-symbols.mjs:40High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/brand-symbols.mjs:76High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/brand-symbols.mjs:77High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/diagram-lint.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:1High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:19High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:20High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:24High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:25High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:29High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:30High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/diagram-url.mjs:31High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/drawio-export.mjs:1High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/drawio-export.mjs:12High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/drawio-export.mjs:13High confidence
- Network access in code of a file that runsfec-drawio-studio/scripts/drawio-export.mjs:14High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/layout-graph.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/png-embed-fix.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/scan-go-packages.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/scan-js-modules.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/scan-python-classes.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/scan-python-modules.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/scan-rust-modules.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/scan-ts-modules.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/shape-query.mjs:1High confidence
- Executable script in code of a file that runsfec-drawio-studio/scripts/studio-core.mjs:1High confidence
- Network access in code of documentationfec-e2e-testing/references/playwright-patterns.md:68Low confidence
- Network access in code of documentationfec-e2e-testing/references/playwright-patterns.md:69Low confidence
- Network access in code of documentationfec-e2e-testing/references/playwright-patterns.md:70Low confidence
- Network access in code of documentationfec-e2e-testing/references/playwright-patterns.md:79Low confidence
- Network access in code of documentationfec-e2e-testing/references/playwright-patterns.md:80Low confidence
- Network access in code of documentationfec-e2e-testing/references/playwright-patterns.md:81Low confidence
- Network access in prose of the SKILL.mdfec-image-generation/SKILL.md:40Low confidence
- Network access in prose of the SKILL.mdfec-image-generation/SKILL.md:41Low confidence
- Network access in prose of the SKILL.mdfec-image-generation/SKILL.md:42Low confidence
- Network access in prose of the SKILL.mdfec-image-generation/SKILL.md:43Low confidence
- Network access in prose of documentationfec-image-generation/references/diagram-workflows.md:26Low confidence
- Executable script in a comment of a file that runsfec-image-generation/scripts/diagram-browser.mjs:1Low confidence
- Network access in code of a file that runsfec-image-generation/scripts/diagram-browser.mjs:51High confidence
- Network access in code of a file that runsfec-image-generation/scripts/diagram-browser.mjs:52High confidence
- Network access in code of a file that runsfec-image-generation/scripts/diagram-browser.mjs:53High confidence
- Network access in code of a file that runsfec-image-generation/scripts/diagram-browser.mjs:70High confidence
- Network access in code of a file that runsfec-image-generation/scripts/diagram-browser.mjs:71High confidence
and 140 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest localized/zh-CN/templates/codex/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md localized/zh-CN/skills/fec-accessibility-check/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md localized/zh-CN/skills/fec-accessibility-check/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md localized/zh-CN/skills/fec-accessibility-check/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md localized/zh-CN/skills/fec-accessibility-check/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.