Curated skills for AI agents · skilld

[Skip to main content](#main-content)

[skilld](https://skilld.dev/)

[Skills](https://skilld.dev/skills) [Collections](https://skilld.dev/collections)

[Sign in](https://skilld.dev/login)

# What should your agent be better at?

A curated registry of skills for the npm packages and GitHub repos you actually use. Browse by what you're trying to do, install once, every agent uses it.

[Browse skills](https://skilld.dev/skills) [Browse collections](https://skilld.dev/collections)

Already know what you want?

`npx skilld add gh:<repo>`

## What are you trying to do?

Six things JS developers are tuning their agent for. Pick a problem, install a skill, restart your agent.

- [<h3>Plan before it codes</h3>

  I want my agent to brainstorm, plan, then execute step by step.

  /brainstorming · /writing-plans · /executing-plans

  31 skills · ~523k installs](https://skilld.dev/skills/plan)
- [<h3>Master your agent</h3>

  I want sub-agents, verification, and parallel execution — not a single chat.

  /using-superpowers · /subagent-driven-development · /verification-before-completion

  29 skills · ~259k installs](https://skilld.dev/skills/master-agent)
- [<h3>Help me write docs & specs</h3>

  I want READMEs, PRDs, and internal comms — without the AI slop.

  /doc-coauthoring · /internal-comms · /java-docs

  12 skills · ~53k installs](https://skilld.dev/skills/docs)
- [<h3>Review and refactor my code</h3>

  I want a second reviewer and clean refactors that keep behaviour stable.

  /requesting-code-review · /receiving-code-review · /improve-codebase-architecture

  26 skills · ~142k installs](https://skilld.dev/skills/review)
- [<h3>Debug like an engineer</h3>

  I want my agent to investigate before guessing — reproduce, isolate, then fix.

  /systematic-debugging · /browser-use · /automate-this

  8 skills · ~103k installs](https://skilld.dev/skills/debug)
- [<h3>Ship cleanly</h3>

  I want commits, branches, and releases that match how the team ships.

  /using-git-worktrees · /finishing-a-development-branch · /conventional-commit

  12 skills · ~52k installs](https://skilld.dev/skills/ship)

## By domain

Skills grouped by what part of dev work they level up.

### Testing

[View all](https://skilld.dev/skills?category=testing-strategy)

Unit, integration, and TDD workflows that keep behaviour stable.

- [

  /tdd![mattpocock](https://github.com/mattpocock.png?size=32)

  mattpocock36.7k

  Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development. /tdd by mattpocock](https://skilld.dev/gh/mattpocock/skills/tdd)
- [

  /test-driven-development![obra](https://github.com/obra.png?size=32)

  obra/superpowers22.8k

  Use when implementing any feature or bugfix, before writing implementation code /test-driven-development by obra](https://skilld.dev/gh/obra/superpowers/test-driven-development)
- [

  /terraform-test![hashicorp](https://github.com/hashicorp.png?size=32)

  hashicorp/agent-skills2.4k

  Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution. /terraform-test by hashicorp](https://skilld.dev/gh/hashicorp/agent-skills/terraform-test)
- [

  /flutter-add-widget-test![flutter](https://github.com/flutter.png?size=32)

  flutter1.8k

  Implement a component-level test using `WidgetTester` to verify UI rendering and user interactions (tapping, scrolling, entering text). Use when validating that a specific widget displays correct data and responds to events as expected. /flutter-add-widget-test by flutter](https://skilld.dev/gh/flutter/skills/flutter-add-widget-test)
- [

  /clerk-testing![clerk](https://github.com/clerk.png?size=32)

  clerk1.7k

  E2E testing for Clerk apps. Use with Playwright or Cypress for auth flow tests. /clerk-testing by clerk](https://skilld.dev/gh/clerk/skills/clerk-testing)
- [

  /validate-skills![callstackincubator](https://github.com/callstackincubator.png?size=32)

  callstackincubator/agent-skills1.7k

  Validates skills in this repo against agentskills.io spec and Claude Code best practices. Use via /validate-skills command. /validate-skills by callstackincubator](https://skilld.dev/gh/callstackincubator/agent-skills/validate-skills)

### Security

[View all](https://skilld.dev/skills?category=security)

Auditing, threat modelling, and finding vulnerabilities before shipping.

- [

  /gha-security-review![getsentry](https://github.com/getsentry.png?size=32)

  getsentry1.3k

  GitHub Actions security review for workflow exploitation vulnerabilities. Use when asked to "review GitHub Actions", "audit workflows", "check CI security", "GHA security", "workflow security review", or review .github/workflows/ for pwn requests, expression injection, credential theft, and supply chain attacks. Exploitation-focused with concrete PoC scenarios. /gha-security-review by getsentry](https://skilld.dev/gh/getsentry/skills/gha-security-review)
- [

  /mapbox-token-security![mapbox](https://github.com/mapbox.png?size=32)

  mapbox/mapbox-agent-skills614

  Security best practices for Mapbox access tokens, including scope management, URL restrictions, rotation strategies, and protecting sensitive data. Use when creating, managing, or advising on Mapbox token security. /mapbox-token-security by mapbox](https://skilld.dev/gh/mapbox/mapbox-agent-skills/mapbox-token-security)
- [

  /security-best-practices![openai](https://github.com/openai.png?size=32)

  openai475

  Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks. /security-best-practices by openai](https://skilld.dev/gh/openai/skills/security-best-practices)
- [

  /security-threat-model![openai](https://github.com/openai.png?size=32)

  openai340

  Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work. /security-threat-model by openai](https://skilld.dev/gh/openai/skills/security-threat-model)
- [

  /auth0-mfa![auth0](https://github.com/auth0.png?size=32)

  auth0/agent-skills318

  Use when adding MFA, 2FA, TOTP, SMS codes, push notifications, passkeys, or when requiring step-up verification for sensitive operations or meeting compliance requirements (HIPAA, PCI-DSS) - covers adaptive and risk-based authentication with Auth0. /auth0-mfa by auth0](https://skilld.dev/gh/auth0/agent-skills/auth0-mfa)
- [

  /security-ownership-map![openai](https://github.com/openai.png?size=32)

  openai233

  Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions. /security-ownership-map by openai](https://skilld.dev/gh/openai/skills/security-ownership-map)

### Performance

[View all](https://skilld.dev/skills?category=performance)

Profiling, optimisation, and shipping fast UIs.

- [

  /baoyu-compress-image![jimliu](https://github.com/jimliu.png?size=32)

  jimliu/baoyu-skills16.5k

  Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or reduce image file size. /baoyu-compress-image by jimliu](https://skilld.dev/gh/jimliu/baoyu-skills/baoyu-compress-image)
- [

  /fixing-motion-performance![ibelick](https://github.com/ibelick.png?size=32)

  ibelick/ui-skills13.5k

  Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance. /fixing-motion-performance by ibelick](https://skilld.dev/gh/ibelick/ui-skills/fixing-motion-performance)
- [

  /core-web-vitals![addyosmani](https://github.com/addyosmani.png?size=32)

  addyosmani/web-quality-skills5.5k

  Optimize Core Web Vitals (LCP, INP, CLS) for better page experience and search ranking. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts". /core-web-vitals by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/core-web-vitals)
- [

  /web-quality-audit![addyosmani](https://github.com/addyosmani.png?size=32)

  addyosmani/web-quality-skills5.3k

  Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website". /web-quality-audit by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/web-quality-audit)
- [

  /performance![addyosmani](https://github.com/addyosmani.png?size=32)

  addyosmani/web-quality-skills4.1k

  Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit". /performance by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/performance)
- [

  /swiftui-performance-audit![dimillian](https://github.com/dimillian.png?size=32)

  dimillian2.4k

  Audit and improve SwiftUI runtime performance from code review and architecture. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps, and to provide guidance for user-run Instruments profiling when code review alone is insufficient. /swiftui-performance-audit by dimillian](https://skilld.dev/gh/dimillian/skills/swiftui-performance-audit)

### Accessibility

[View all](https://skilld.dev/skills?category=accessibility)

Building interfaces that work for everyone.

- [

  /accessibility![addyosmani](https://github.com/addyosmani.png?size=32)

  addyosmani/web-quality-skills20k

  Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible". /accessibility by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/accessibility)
- [

  /fixing-accessibility![ibelick](https://github.com/ibelick.png?size=32)

  ibelick/ui-skills10.1k

  Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance. /fixing-accessibility by ibelick](https://skilld.dev/gh/ibelick/ui-skills/fixing-accessibility)
- [

  /rams![brianlovin](https://github.com/brianlovin.png?size=32)

  brianlovin/claude-config286

  Run accessibility and visual design review on components. Use when reviewing UI code for WCAG compliance and design issues. /rams by brianlovin](https://skilld.dev/gh/brianlovin/claude-config/rams)
- [

  /accessibility-audit![webflow](https://github.com/webflow.png?size=32)

  webflow/webflow-skills151

  Run comprehensive accessibility audit (WCAG 2.1) on Webflow pages - checks buttons, forms, links, focus states, headings, keyboard navigation, and generates detailed reports with fixes. Requires Webflow Designer connection. Excludes image alt text (covered by asset-audit skill). /accessibility-audit by webflow](https://skilld.dev/gh/webflow/webflow-skills/accessibility-audit)

### Design

[View all](https://skilld.dev/skills?category=design)

Broader design critique, taste, and visual direction work.

- [

  /frontend-design![anthropics](https://github.com/anthropics.png?size=32)

  anthropics/claude-plugins-official349.3k

  Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics. /frontend-design by anthropics](https://skilld.dev/gh/anthropics/claude-plugins-official/frontend-design)
- [

  /theme-factory![anthropics](https://github.com/anthropics.png?size=32)

  anthropics34.4k

  Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly. /theme-factory by anthropics](https://skilld.dev/gh/anthropics/skills/theme-factory)
- [

  /json-canvas![kepano](https://github.com/kepano.png?size=32)

  kepano/obsidian-skills17.1k

  Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian. /json-canvas by kepano](https://skilld.dev/gh/kepano/obsidian-skills/json-canvas)
- [

  /canvas-design![anthropics](https://github.com/anthropics.png?size=32)

  anthropics17k

  Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. /canvas-design by anthropics](https://skilld.dev/gh/anthropics/skills/canvas-design)
- [

  /design-md![google-labs-code](https://github.com/google-labs-code.png?size=32)

  google-labs-code/stitch-skills13.7k

  Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files /design-md by google-labs-code](https://skilld.dev/gh/google-labs-code/stitch-skills/design-md)
- [

  /brand-guidelines![anthropics](https://github.com/anthropics.png?size=32)

  anthropics12.3k

  Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. /brand-guidelines by anthropics](https://skilld.dev/gh/anthropics/skills/brand-guidelines)

## Featured skill sets

[View all](https://skilld.dev/collections)

Opinionated sets from developers worth trusting. Some are full stacks; some are one strong skill that earns the spotlight.

- [<h3>Frontend Design</h3>](https://skilld.dev/@harlan-zw/frontend-ui-stack)

  6 skills

  Concrete frontend UI polish: interface critique, baseline quality, responsive behavior, motion, accessibility fixes, and cleaner component work.
  - [

    /impeccable![pbakaus](https://github.com/pbakaus.png?size=32)

    pbakaus/impeccable

    Paul Bakaus's Impeccable gives agents stronger frontend judgment for critique, polish, accessibility, responsive behavior, motion, and design systems. /impeccable by pbakaus](https://skilld.dev/gh/pbakaus/impeccable/impeccable)
  - [

    /frontend-design![anthropics](https://github.com/anthropics.png?size=32)

    anthropics/skills

    Anthropic's official frontend-design skill (402K installs) is the broad baseline for distinctive, production-grade interfaces. /frontend-design by anthropics](https://skilld.dev/gh/anthropics/skills/frontend-design)
  - [

    /web-design-guidelines![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/agent-skills

    Vercel's web-design-guidelines (314K installs) is a leaderboard-top quality bar for typography, spacing, and modern web interfaces. /web-design-guidelines by vercel-labs](https://skilld.dev/gh/vercel-labs/agent-skills/web-design-guidelines)
  - [

    /theme-factory![anthropics](https://github.com/anthropics.png?size=32)

    anthropics/skills

    theme-factory generates cohesive color and typography systems when an interface needs a real brand instead of default Tailwind. /theme-factory by anthropics](https://skilld.dev/gh/anthropics/skills/theme-factory)
  - [

    /vercel-react-view-transitions![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/agent-skills

    View-transitions adds first-class browser transition patterns that lift the perceived quality of navigation and state changes. /vercel-react-view-transitions by vercel-labs](https://skilld.dev/gh/vercel-labs/agent-skills/vercel-react-view-transitions)
  - [

    /emil-design-eng![emilkowalski](https://github.com/emilkowalski.png?size=32)

    emilkowalski/skill

    Emil Kowalski's design engineering skill adds the invisible-details lens: micro-interactions, motion, and component polish that make software feel deliberate. /emil-design-eng by emilkowalski](https://skilld.dev/gh/emilkowalski/skill/emil-design-eng)
- [<h3>React stack</h3>](https://skilld.dev/@harlan-zw/react-stack)

  6 skills

  The most-installed React skills on skills.sh: production patterns from the Vercel team plus the canonical shadcn/ui component playbook.
  - [

    /vercel-react-best-practices![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/agent-skills

    Vercel's React best-practices skill is the #3 most-installed skill on skills.sh (393K) - the right default for modern React work. /vercel-react-best-practices by vercel-labs](https://skilld.dev/gh/vercel-labs/agent-skills/vercel-react-best-practices)
  - [

    /shadcn![shadcn](https://github.com/shadcn.png?size=32)

    shadcn/ui

    shadcn/ui's own skill (138K installs) covers component composition, theming, and the patterns the library was designed around. /shadcn by shadcn](https://skilld.dev/gh/shadcn/ui/shadcn)
  - [

    /vercel-react-native-skills![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/agent-skills

    Vercel's React Native pack (115K installs) extends the same React judgment to mobile when the stack reaches beyond the browser. /vercel-react-native-skills by vercel-labs](https://skilld.dev/gh/vercel-labs/agent-skills/vercel-react-native-skills)
  - [

    /next-best-practice![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/next-skills

    Vercel's Next best-practice skill is the canonical reference for App Router, server components, caching, and modern Next conventions. /next-best-practice by vercel-labs](https://skilld.dev/gh/vercel-labs/next-skills/next-best-practice)
  - [

    /react-component-performance![dimillian](https://github.com/dimillian.png?size=32)

    dimillian/skills

    React component performance focuses on render cost, memoization, and the invisible re-renders that quietly tank a UI. /react-component-performance by dimillian](https://skilld.dev/gh/dimillian/skills/react-component-performance)
  - [

    /react-best-practices![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/vercel-plugin

    The plugin-style React best-practices pack is the right companion when deployment runs through Vercel's platform. /react-best-practices by vercel-labs](https://skilld.dev/gh/vercel-labs/vercel-plugin/react-best-practices)
- [<h3>Architecture stack</h3>](https://skilld.dev/@harlan-zw/typescript-engineering-stack)

  6 skills

  Planning, architecture, testing strategy, and codebase diagnosis skills for agents making structural changes.
  - [

    /improve-codebase-architecture![mattpocock](https://github.com/mattpocock.png?size=32)

    mattpocock/skills

    Matt Pocock's architecture skill is the strongest fit for structural decisions, refactoring opportunities, testability, and AI-navigable TypeScript codebases. /improve-codebase-architecture by mattpocock](https://skilld.dev/gh/mattpocock/skills/improve-codebase-architecture)
  - [

    /test-driven-development![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    obra/superpowers TDD skill (80K installs) keeps architecture work grounded in red-green-refactor and regression coverage. /test-driven-development by obra](https://skilld.dev/gh/obra/superpowers/test-driven-development)
  - [

    /systematic-debugging![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    Systematic debugging (93K installs) gives agents a disciplined diagnosis loop when structural changes surface latent bugs. /systematic-debugging by obra](https://skilld.dev/gh/obra/superpowers/systematic-debugging)
  - [

    /domain-model![mattpocock](https://github.com/mattpocock.png?size=32)

    mattpocock/skills

    Domain modeling is the missing first step before refactors - it makes the boundaries explicit before the code moves. /domain-model by mattpocock](https://skilld.dev/gh/mattpocock/skills/domain-model)
  - [

    /ubiquitous-language![mattpocock](https://github.com/mattpocock.png?size=32)

    mattpocock/skills

    Ubiquitous-language keeps types, names, and docs aligned with the domain so the code stays readable as it grows. /ubiquitous-language by mattpocock](https://skilld.dev/gh/mattpocock/skills/ubiquitous-language)
  - [

    /writing-plans![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    Writing-plans turns vague architecture work into a sequenced plan an agent can execute and verify. /writing-plans by obra](https://skilld.dev/gh/obra/superpowers/writing-plans)
- [<h3>Performance stack</h3>](https://skilld.dev/@harlan-zw/web-quality-stack)

  7 skills

  Skills from Addy Osmani and frontend specialists for performance audits, Core Web Vitals, motion smoothness, accessibility, SEO, and modern web quality before you ship.
  - [

    /web-quality-audit![addyosmani](https://github.com/addyosmani.png?size=32)

    addyosmani/web-quality-skills

    Addy Osmani's web-quality-audit is the right umbrella skill for Lighthouse-style performance, accessibility, SEO, and best-practice review. /web-quality-audit by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/web-quality-audit)
  - [

    /core-web-vitals![addyosmani](https://github.com/addyosmani.png?size=32)

    addyosmani/web-quality-skills

    Core Web Vitals is the focused performance skill for LCP, INP, CLS, layout shifts, and page experience work. /core-web-vitals by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/core-web-vitals)
  - [

    /performance![addyosmani](https://github.com/addyosmani.png?size=32)

    addyosmani/web-quality-skills

    Performance covers JS, network, and rendering optimization for real-world pages. /performance by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/performance)
  - [

    /accessibility![addyosmani](https://github.com/addyosmani.png?size=32)

    addyosmani/web-quality-skills

    Accessibility gives the stack a dedicated WCAG and assistive-tech pass alongside the broader audit. /accessibility by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/accessibility)
  - [

    /seo![addyosmani](https://github.com/addyosmani.png?size=32)

    addyosmani/web-quality-skills

    SEO closes the discoverability gap that Lighthouse partly catches but undercounts in practice. /seo by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/seo)
  - [

    /best-practices![addyosmani](https://github.com/addyosmani.png?size=32)

    addyosmani/web-quality-skills

    Best Practices covers security, browser compatibility, and modern web quality checks that sit beside raw performance. /best-practices by addyosmani](https://skilld.dev/gh/addyosmani/web-quality-skills/best-practices)
  - [

    /modern-web-guidance![GoogleChrome](https://github.com/GoogleChrome.png?size=32)

    GoogleChrome/modern-web-guidance

    Modern Web Guidance is Chrome's expert-vetted skill for building accessible, performant, and secure web UIs with AI agents. /modern-web-guidance by GoogleChrome](https://skilld.dev/gh/GoogleChrome/modern-web-guidance/modern-web-guidance)
- [<h3>Frontend UX stack</h3>](https://skilld.dev/@harlan-zw/frontend-ux-stack)

  6 skills

  User-facing quality for shipped frontend work: speed, Core Web Vitals, accessibility, clarity, browser checks, and product-minded cleanup.
  - [

    /impeccable![pbakaus](https://github.com/pbakaus.png?size=32)

    pbakaus/impeccable

    Impeccable anchors UX in human-facing clarity, visual hierarchy, layout, flow, polish, responsive behavior, and whether the interface feels good to use. /impeccable by pbakaus](https://skilld.dev/gh/pbakaus/impeccable/impeccable)
  - [

    /fixing-accessibility![ibelick](https://github.com/ibelick.png?size=32)

    ibelick/ui-skills

    Fixing Accessibility gives the stack concrete WCAG, keyboard, focus, ARIA, contrast, and form-error coverage. /fixing-accessibility by ibelick](https://skilld.dev/gh/ibelick/ui-skills/fixing-accessibility)
  - [

    /rams![brianlovin](https://github.com/brianlovin.png?size=32)

    brianlovin/claude-config

    Brian Lovin's Rams skill adds pragmatic accessibility and visual design review on real components. /rams by brianlovin](https://skilld.dev/gh/brianlovin/claude-config/rams)
  - [

    /fixing-motion-performance![ibelick](https://github.com/ibelick.png?size=32)

    ibelick/ui-skills

    Fixing-motion-performance catches the janky transitions and animations that make even a good design feel cheap. /fixing-motion-performance by ibelick](https://skilld.dev/gh/ibelick/ui-skills/fixing-motion-performance)
  - [

    /baseline-ui![ibelick](https://github.com/ibelick.png?size=32)

    ibelick/ui-skills

    Baseline-ui pins down the minimum-viable visual quality bar so the rest of the polish is additive, not corrective. /baseline-ui by ibelick](https://skilld.dev/gh/ibelick/ui-skills/baseline-ui)
  - [

    /fixing-metadata![ibelick](https://github.com/ibelick.png?size=32)

    ibelick/ui-skills

    Fixing-metadata covers the social-share, favicon, and document-level details that quietly shape first impressions. /fixing-metadata by ibelick](https://skilld.dev/gh/ibelick/ui-skills/fixing-metadata)
- [<h3>Vue and Nuxt stack</h3>](https://skilld.dev/@harlan-zw/vue-nuxt-stack)

  6 skills

  A coherent Vue and Nuxt agent setup from framework people and ecosystem specialists.
  - [

    /vue-best-practices![antfu](https://github.com/antfu.png?size=32)

    antfu/skills

    Anthony Fu's Vue best-practices skill is the right default for Vue 3, script setup, TypeScript, SSR, Volar, and vue-tsc work. /vue-best-practices by antfu](https://skilld.dev/gh/antfu/skills/vue-best-practices)
  - [

    /nuxt![onmax](https://github.com/onmax.png?size=32)

    onmax/nuxt-skills

    Max's Nuxt skill adds Nuxt 4 server routes, file routing, middleware, composables, h3, Nitro, and current framework conventions. /nuxt by onmax](https://skilld.dev/gh/onmax/nuxt-skills/nuxt)
  - [

    /vue-testing-best-practices![hyf0](https://github.com/hyf0.png?size=32)

    hyf0/vue-skills

    Yunfei He's Vue testing skill rounds out the stack with Vitest, Vue Test Utils, component testing, mocking, and E2E patterns. /vue-testing-best-practices by hyf0](https://skilld.dev/gh/hyf0/vue-skills/vue-testing-best-practices)
  - [

    /vue![antfu](https://github.com/antfu.png?size=32)

    antfu/skills

    antfu/vue covers core composition, reactivity, and patterns that the best-practices skill assumes as background. /vue by antfu](https://skilld.dev/gh/antfu/skills/vue)
  - [

    /nuxt-ui![onmax](https://github.com/onmax.png?size=32)

    onmax/nuxt-skills

    nuxt-ui is the canonical component layer for Nuxt apps that need a real design system out of the box. /nuxt-ui by onmax](https://skilld.dev/gh/onmax/nuxt-skills/nuxt-ui)
  - [

    /nuxt-content![onmax](https://github.com/onmax.png?size=32)

    onmax/nuxt-skills

    nuxt-content covers markdown-first, file-based content - the standard answer when a Nuxt app also needs docs or a blog. /nuxt-content by onmax](https://skilld.dev/gh/onmax/nuxt-skills/nuxt-content)
- [<h3>Backend and data stack</h3>](https://skilld.dev/@harlan-zw/backend-data-stack)

  6 skills

  High-install backend skills for agents wiring up databases, auth, and realtime: Supabase Postgres, Firebase, Convex, and Better Auth.
  - [

    /supabase-postgres-best-practices![supabase](https://github.com/supabase.png?size=32)

    supabase/agent-skills

    Supabase's Postgres best-practices skill (161K installs) is the leaderboard-top pick for schema, RLS, migrations, and SQL patterns that hold up in production. /supabase-postgres-best-practices by supabase](https://skilld.dev/gh/supabase/agent-skills/supabase-postgres-best-practices)
  - [

    /firebase-basics![firebase](https://github.com/firebase.png?size=32)

    firebase/agent-skills

    Firebase Basics is the official entry point for agents wiring up Firestore, auth, and hosting. /firebase-basics by firebase](https://skilld.dev/gh/firebase/agent-skills/firebase-basics)
  - [

    /convex-quickstart![get-convex](https://github.com/get-convex.png?size=32)

    get-convex/agent-skills

    Convex Quickstart is the canonical fast path for an agent dropping a typed, reactive backend into a project. /convex-quickstart by get-convex](https://skilld.dev/gh/get-convex/agent-skills/convex-quickstart)
  - [

    /better-auth-best-practices![better-auth](https://github.com/better-auth.png?size=32)

    better-auth/skills

    Better Auth's best-practices skill is the right reference when agents are wiring up sessions, OAuth, and modern auth flows. /better-auth-best-practices by better-auth](https://skilld.dev/gh/better-auth/skills/better-auth-best-practices)
  - [

    /firebase-auth-basics![firebase](https://github.com/firebase.png?size=32)

    firebase/agent-skills

    firebase-auth-basics is the focused companion when the agent only needs Firebase for identity, not the whole stack. /firebase-auth-basics by firebase](https://skilld.dev/gh/firebase/agent-skills/firebase-auth-basics)
  - [

    /supabase![supabase](https://github.com/supabase.png?size=32)

    supabase/agent-skills

    The broader Supabase skill covers the client SDK, edge functions, and the parts that sit above raw Postgres. /supabase by supabase](https://skilld.dev/gh/supabase/agent-skills/supabase)
- [<h3>Agent workflow stack</h3>](https://skilld.dev/@harlan-zw/agent-workflow-stack)

  6 skills

  Skills for running an agent like an engineering workflow: careful changes, parallel review, systematic debugging, and shipping.
  - [

    /subagent-driven-development![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    obra/superpowers subagent-driven-development (69K installs) is the canonical loop for delegating discrete work to focused subagents. /subagent-driven-development by obra](https://skilld.dev/gh/obra/superpowers/subagent-driven-development)
  - [

    /dispatching-parallel-agents![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    Dispatching parallel agents (62K installs) covers running multiple read-only investigators in parallel before changing code. /dispatching-parallel-agents by obra](https://skilld.dev/gh/obra/superpowers/dispatching-parallel-agents)
  - [

    /verification-before-completion![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    Verification-before-completion forces the agent to prove the work landed before declaring done - the single best guard against overclaiming. /verification-before-completion by obra](https://skilld.dev/gh/obra/superpowers/verification-before-completion)
  - [

    /workflow![brianlovin](https://github.com/brianlovin.png?size=32)

    brianlovin/claude-config

    Brian Lovin's workflow skill ties the loop together with a practical planning, execution, and cleanup pattern. /workflow by brianlovin](https://skilld.dev/gh/brianlovin/claude-config/workflow)
  - [

    /using-superpowers![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    using-superpowers is the meta-skill that orchestrates the rest of the obra workflow set into one coherent loop. /using-superpowers by obra](https://skilld.dev/gh/obra/superpowers/using-superpowers)
  - [

    /executing-plans![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    executing-plans pairs with writing-plans so the agent actually moves through the steps instead of redesigning mid-flight. /executing-plans by obra](https://skilld.dev/gh/obra/superpowers/executing-plans)
- [<h3>Agent building stack</h3>](https://skilld.dev/@harlan-zw/agent-building-stack)

  6 skills

  Build your own agent capabilities: discovering skills, creating skills, wiring up MCP, and delegating work to subagents.
  - [

    /skill-creator![anthropics](https://github.com/anthropics.png?size=32)

    anthropics/skills

    Anthropic's skill-creator (202K installs) is the canonical skill for authoring new SKILL.md files that actually load and work. /skill-creator by anthropics](https://skilld.dev/gh/anthropics/skills/skill-creator)
  - [

    /find-skills![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/skills

    Vercel's find-skills (1.5M installs, #1 on skills.sh) is the discovery layer that points agents at the rest of the ecosystem. /find-skills by vercel-labs](https://skilld.dev/gh/vercel-labs/skills/find-skills)
  - [

    /mcp-builder![anthropics](https://github.com/anthropics.png?size=32)

    anthropics/skills

    mcp-builder (53K installs) gives agents the patterns for designing and wiring up a Model Context Protocol server. /mcp-builder by anthropics](https://skilld.dev/gh/anthropics/skills/mcp-builder)
  - [

    /writing-skills![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    obra/superpowers writing-skills covers the day-to-day craft of capturing reusable expertise as a SKILL.md. /writing-skills by obra](https://skilld.dev/gh/obra/superpowers/writing-skills)
  - [

    /template-skill![anthropics](https://github.com/anthropics.png?size=32)

    anthropics/skills

    template-skill is the official scaffolding starting point - the fastest way to a SKILL.md that loads correctly on first try. /template-skill by anthropics](https://skilld.dev/gh/anthropics/skills/template-skill)
  - [

    /using-superpowers![obra](https://github.com/obra.png?size=32)

    obra/superpowers

    using-superpowers shows how the authored skills actually get composed at runtime, which closes the build/use loop. /using-superpowers by obra](https://skilld.dev/gh/obra/superpowers/using-superpowers)
- [<h3>Browser automation stack</h3>](https://skilld.dev/@harlan-zw/browser-automation-stack)

  6 skills

  When an agent needs to drive a browser: scrape pages, click through flows, and pull structured content into the loop.
  - [

    /agent-browser![vercel-labs](https://github.com/vercel-labs.png?size=32)

    vercel-labs/vercel-plugin

    Vercel's agent-browser (265K installs on skills.sh) is the leaderboard-top headless-browser-for-agents skill. /agent-browser by vercel-labs](https://skilld.dev/gh/vercel-labs/vercel-plugin/agent-browser)
  - [

    /browser-use![browser-use](https://github.com/browser-use.png?size=32)

    browser-use/browser-use

    browser-use (74K installs) is the canonical open-source pick when agents need to drive a real browser through multi-step flows. /browser-use by browser-use](https://skilld.dev/gh/browser-use/browser-use/browser-use)
  - [

    /firecrawl![firecrawl](https://github.com/firecrawl.png?size=32)

    firecrawl/cli

    Firecrawl is the right tool when the goal is pulling clean structured content out of the web rather than clicking through a UI. /firecrawl by firecrawl](https://skilld.dev/gh/firecrawl/cli/firecrawl)
  - [

    /firecrawl-scrape![firecrawl](https://github.com/firecrawl.png?size=32)

    firecrawl/cli

    firecrawl-scrape is the focused single-URL fetch when an agent only needs one page rendered and converted. /firecrawl-scrape by firecrawl](https://skilld.dev/gh/firecrawl/cli/firecrawl-scrape)
  - [

    /firecrawl-crawl![firecrawl](https://github.com/firecrawl.png?size=32)

    firecrawl/cli

    firecrawl-crawl handles the multi-page traversal case so the agent doesn't reinvent breadth-first crawling. /firecrawl-crawl by firecrawl](https://skilld.dev/gh/firecrawl/cli/firecrawl-crawl)
  - [

    /open-source![browser-use](https://github.com/browser-use.png?size=32)

    browser-use/browser-use

    The open-source pack covers the self-hosted side of browser-use when SaaS isn't an option. /open-source by browser-use](https://skilld.dev/gh/browser-use/browser-use/open-source)

## Recently updated

[Browse all](https://skilld.dev/skills)

Skills whose SKILL.md changed lately. Watch a repo to get notified the next time it does.

- [![microsoft avatar](https://github.com/microsoft.png?size=80)

  microsoft/github-copilot-for-azure

  2 skills updated

  /microsoft-foundry · /vally-eval

  Updated today](https://skilld.dev/gh/microsoft/github-copilot-for-azure)
- [![posthog avatar](https://github.com/posthog.png?size=80)

  posthog/posthog

  10 skills updated

  /setting-up-devbox · /triaging-visual-review-runs · /debugging-ci-failures · /implementing-warehouse-sources · +6 more

  Updated today](https://skilld.dev/gh/posthog/posthog)
- [![boshu2 avatar](https://github.com/boshu2.png?size=80)

  boshu2/agentops

  11 skills updated

  /using-agentops · /using-agentops · /domain · /crank · +7 more

  Updated today](https://skilld.dev/gh/boshu2/agentops)
- [![jimliu avatar](https://github.com/jimliu.png?size=80)

  jimliu/baoyu-skills

  7 skills updated

  /baoyu-danger-gemini-web · /baoyu-danger-x-to-markdown · /baoyu-markdown-to-html · /baoyu-post-to-wechat · +3 more

  Updated today](https://skilld.dev/gh/jimliu/baoyu-skills)
- [![stripe avatar](https://github.com/stripe.png?size=80)

  stripe/ai

  3 skills updated

  /stripe-projects · /stripe-projects · /stripe-projects

  Updated today](https://skilld.dev/gh/stripe/ai)
- [

  /firecrawl-scrape![firecrawl](https://github.com/firecrawl.png?size=32)

  firecrawl/cli

  Updated yesterday

  Extract clean markdown from any URL, including JavaScript-rendered SPAs. Use this skill whenever the user provides a URL and wants its content, says "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", or "read this webpage". Handles JS-rendered pages, multiple concurrent URLs, and returns LLM-optimized markdown. Use this instead of WebFetch for any webpage content extraction. /firecrawl-scrape by firecrawl](https://skilld.dev/gh/firecrawl/cli/firecrawl-scrape)
- [![millionco avatar](https://github.com/millionco.png?size=80)

  millionco/react-doctor

  2 skills updated

  /react-doctor · /react-doctor

  Updated yesterday](https://skilld.dev/gh/millionco/react-doctor)
- [

  /to-prd![mattpocock](https://github.com/mattpocock.png?size=32)

  mattpocock

  Updated 2d ago

  Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context. /to-prd by mattpocock](https://skilld.dev/gh/mattpocock/skills/to-prd)
- [

  /firebase-auth-basics![firebase](https://github.com/firebase.png?size=32)

  firebase

  Updated 4d ago

  Guide for setting up and using Firebase Authentication. Use this skill when the user's app requires user sign-in, user management, or secure data access using auth rules. /firebase-auth-basics by firebase](https://skilld.dev/gh/firebase/skills/firebase-auth-basics)
- [![datadog-labs avatar](https://github.com/datadog-labs.png?size=80)

  datadog-labs/agent-skills

  4 skills updated

  /dd-apm · /dd-logs · /dd-monitors · /dd-pup

  Updated 4d ago](https://skilld.dev/gh/datadog-labs/agent-skills)
- [

  /openai-docs![openai](https://github.com/openai.png?size=32)

  openai

  Updated 4d ago

  Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restrict fallback browsing to official OpenAI domains. /openai-docs by openai](https://skilld.dev/gh/openai/skills/openai-docs)
- [

  /langfuse![langfuse](https://github.com/langfuse.png?size=32)

  langfuse

  Updated 4d ago

  Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods. /langfuse by langfuse](https://skilld.dev/gh/langfuse/skills/langfuse)

## Watch your stack for changes

Sign in with GitHub, pick the repos you depend on, get a weekly digest when their skills change.

[Sign in with GitHub](https://skilld.dev/login?return_to=/onboarding/discover)

## How it works

1. 01

   Install skills

   Run `npx -y skilld add npm:vue npm:nuxt` to install curated skills for your npm packages.
2. 02

   Follow curators

   Install a curator's collection with one command. Their skill set becomes your agent's context.
3. 03

   Stay current

   Skills update when packages release. Run `skilld update` to refresh from the registry.

[Stats](https://skilld.dev/skills/stats) [Accessibility](https://skilld.dev/accessibility)

[GitHub repository (opens in new tab)](https://github.com/harlan-zw/skilld)

Built by [Harlan Wilton](https://harlanzw.com)