A curated collection of 131 agent skills for Claude Code and compatible AI coding assistants. Each skill provides domain-specific knowledge, best practices, and guided workflows that enhance an agent's ability to perform specialized tasks.
Skills are structured instruction sets that give AI agents deep expertise in specific domains. Each skill lives in its own directory under skills/ and contains a SKILL.md file with metadata, procedures, and reference material. Skills follow the agentskills.io specification.
- react — Component architecture, hooks, state management, TypeScript integration, and testing
- tailwindcss — Tailwind CSS v4 patterns, design tokens, and tailwind-variants
- shadcn — Building UI components with shadcn/ui, Radix UI primitives, and design tokens
- shadcn-ui — Complete shadcn/ui component library patterns, forms with Zod/React Hook Form, and theming
- motion — React animations with Motion (formerly Framer Motion) -- gestures, scroll effects, spring physics
- motion-react — Full Motion for React guide including SVG, exit animations, and layout transitions
- fixing-motion-performance — Diagnose and fix animation performance issues in UI code
- zustand — Zustand state management patterns, store organization, and best practices
- xstate — XState v5 state machines, actors, @xstate/store, and TanStack Query integration
- storybook — Storybook story authoring and CSF 3.0 best practices
- storybook-stories — Create, update, or refactor Storybook stories following project patterns
- building-components — Accessible, composable UI components with design tokens and documentation
- tech-logos — Install official tech brand logos from the Elements registry via shadcn
- tanstack — Comprehensive TanStack ecosystem guide -- Query/DB, Form, and Router
- tanstack-query-best-practices — Data fetching, caching, mutations, and server state management
- tanstack-router-best-practices — Type-safe routing, data loading, search params, and navigation
- tanstack-start-best-practices — Full-stack React with server functions, middleware, SSR, and deployment
- vercel-composition-patterns — React composition patterns for refactoring boolean prop proliferation
- next-best-practices — Next.js best practices -- file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, and optimization
- vercel-react-best-practices — React/Next.js performance optimization from Vercel Engineering
- frontend-design — Distinctive, production-grade frontend interfaces with high design quality
- interface-design — Interface design for dashboards, admin panels, apps, and tools
- landing-page-design — High-converting landing pages with AI-generated visuals and conversion optimization
- bencium-innovative-ux-designer — Innovative UX design with design system templates, motion specs, and accessibility
- ui-ux-pro-max — 50 design styles, 21 palettes, 50 font pairings, and 9 tech stacks for web/mobile
- web-design-guidelines — Review UI code for Web Interface Guidelines compliance
- design-spec-extraction — Extract production-ready JSON design specs from visual inputs using a 7-pass architecture
- hono — Hono framework development with documentation search and API reference
- elysia — Type-safe APIs with Elysia including routing, validation, plugins, and error handling
- drizzle-orm — Drizzle ORM best practices -- schemas, queries, mutations, transactions, migrations
- drizzle-safe-migrations — Production-safe Drizzle migration workflows for schema changes
- postgres-drizzle — PostgreSQL and Drizzle ORM best practices for type-safe database apps
- better-auth-best-practices — Better Auth TypeScript authentication framework integration
- inngest — Serverless background jobs, event-driven workflows, and durable execution
- workflow — Durable, resumable workflows using Vercel's Workflow DevKit
- stripe-best-practices — Best practices for Stripe integrations across all use cases
- stripe-integration — PCI-compliant payment flows including checkout, subscriptions, and webhooks
- stripe-subscriptions — Subscription billing with feature flags, webhook handling, and billing portal
- stripe-webhooks — Receive and verify Stripe webhooks with signature debugging
- typescript-advanced — Advanced type system -- generics, conditional types, mapped types, template literals
- zod — Zod schema validation for type safety, parsing, and error handling
- es-toolkit — Modern utility library as a lodash replacement -- array, object, string operations
- effect-ts — Effect-TS code including setup, data modeling, error handling, and Context.Tag
- rust-engineer — Senior Rust engineer persona for memory-safe systems-level applications
- rust-best-practices — Idiomatic Rust based on Apollo GraphQL's best practices handbook
- rust-coding-guidelines — 50 core rules for Rust code style, naming, formatting, and best practices
- rust-async-patterns — Async programming with Tokio, async traits, error handling, and concurrency
- ratatui-tui — Terminal UIs with ratatui v0.30.0+ -- Elm Architecture, StatefulWidget, async events
- electron-dev — Electron development with Electron Vite and Builder -- main/renderer processes, IPC
- electron-builder — Electron packaging, code signing, auto-updates, and release workflows
- electron-release — Electron production builds, notarization, auto-updates, and releases
- tauri-v2 — Tauri v2 cross-platform apps with Rust backend, IPC, permissions, and builds
- devops-engineer — Dockerfiles, CI/CD pipelines, Kubernetes manifests, and Terraform/Pulumi templates
- kubernetes-specialist — Deploy and manage Kubernetes workloads -- manifests, Helm, RBAC, networking, GitOps
- argocd-expert — ArgoCD GitOps deployment, sync strategies, and production operations
- helm-chart-scaffolding — Design, organize, and manage Helm charts for Kubernetes applications
- k8s-security-policies — Kubernetes security policies -- NetworkPolicy, PodSecurityPolicy, and RBAC
- terraform-style-guide — Terraform HCL following HashiCorp's official style conventions
- cloudflare — Cloudflare platform -- Workers, Pages, storage, AI, networking, and security
- wrangler — Cloudflare Workers CLI for deploying and managing Workers, KV, R2, D1, and more
- hetzner-server — Create and manage Hetzner Cloud servers via the hcloud CLI
- sentry-cli — Sentry CLI for interacting with Sentry from the command line
- centrifugo — Centrifugo real-time messaging -- WebSocket PUB/SUB, channels, JWT auth, scaling
- evolution-api — Evolution API for WhatsApp messaging, instance management, and chatbot orchestration
- rivetkit — RivetKit backend and Rivet Actor runtime for long-lived, in-memory processes
- rivetkit-client-javascript — RivetKit JavaScript client for browser, Node.js, or Bun
- rivetkit-client-react — RivetKit React client with
@rivetkit/react - sync-provider — Sync upstream changes from cloned repos while preserving local customizations
- ai-sdk — Vercel AI SDK for building AI-powered features
- agent-identifier — Agent structure, system prompts, triggering conditions, and development best practices
- mastra — Mastra framework for building AI agents and workflows
- develop-ai-functions-example — Develop examples for AI SDK functions to validate provider support
- skills-best-practices — Author professional-grade agent skills following the agentskills.io spec
- skill-writter — Guide users through creating Agent Skills for Claude Code
- agent-md-refactor — Refactor bloated AGENTS.md/CLAUDE.md files into organized, linked documentation
- nano-banana-pro — Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro)
- nano-banana-prompting — Craft effective prompts for Nano Banana Pro image generation
- find-skills — Discover and install agent skills from the open agent skills ecosystem
- pal — Pal MCP toolkit for code analysis, debugging, planning, refactoring, and tracing
- sourcebot — Search external libraries and frameworks using Sourcebot MCP
- vitest — Fast unit testing with Vite -- Jest-compatible API, mocking, coverage, and fixtures
- a11y-testing — Automated accessibility testing with axe-core, Playwright, and jest-axe
- test-antipatterns — Prevent common testing anti-patterns like testing mock behavior
- qa-test-planner — Generate test plans, manual test cases, regression suites, and bug reports
- verification-before-completion — Run verification commands and confirm output before claiming success
- adversarial-review — Spawn opposing AI model reviewers to adversarially challenge work
- architectural-analysis — Deep architectural audit for dead code, duplication, anti-patterns, and code smells
- systematic-debugging — Root-cause investigation before proposing fixes for bugs or test failures
- no-workarounds — Enforce root-cause fixes over workarounds, hacks, and symptom patches
- receiving-code-review — Handle code review feedback with technical rigor and verification
- fix-coderabbit-review — End-to-end remediation workflow for PR review feedback
- git-rebase — Git rebase operations and merge conflict resolution with clean history
- find-rules — Discover project rules, coding standards, and architectural guidelines
- brainstorming — Explore intent, requirements, and design through collaborative dialogue
- creating-spec — Comprehensive technical specs for SDK gaps, features, or system centralization
- deep-research — Comprehensive research and analysis using multiple discovery tools
- executing-plans — Execute implementation plans in batches with review checkpoints
- dispatching-parallel-agents — Dispatch independent tasks to parallel agents to avoid bottlenecks
- crafting-effective-readmes — Templates and guidance for writing README files matched to audience and project
- requirements-clarity — Clarify ambiguous requirements through focused dialogue before implementation
- lesson-learned — Extract software engineering lessons from git history and recent code changes
- ship-learn-next — Transform learning content into actionable implementation plans
- firecrawl — Web scraping, search, crawling, and browser automation via the Firecrawl CLI
- exa-web-search-free — Free AI-powered web, code, and company search via Exa MCP
- perplexity — Web search and research using Perplexity AI
- agent-browser — Automate browser interactions for testing, form filling, and data extraction
- content-research-writer — Writing partner for research, outlining, drafting, and refining content
- copywriting — Conversion copywriting for marketing pages, CTAs, and headlines
- humanizer — Remove signs of AI-generated writing from text
- writing-clearly-and-concisely — Strunk's timeless rules for clearer, stronger, more professional prose
- professional-communication — Technical communication for emails, team messaging, and meeting agendas
- alex-hormozi-pitch — Create irresistible offers using Hormozi's $100M Offers methodology
- brand-storytelling — Craft compelling brand narratives and positioning
- fundraising — Plan and run early-stage fundraising with pitch narrative, investor pipeline, and outreach
- game-changing-features — Find 10x product opportunities and high-leverage improvements
- startup-validator — Comprehensive startup idea validation and market analysis
- sales-methodology-implementer — Implement proven sales methodologies (MEDDIC, BANT, Sandler, Challenger, SPIN)
- pitch-deck — Generate professional PowerPoint pitch decks for startups
- pitch-deck-visuals — Investor pitch deck visuals with slide-by-slide framework and design rules
- pitch-gen — Generate startup pitch deck content with AI
- pptx-creator — Create professional PowerPoint presentations from outlines or data
- ai-pdf-builder — AI-powered PDF generator for legal docs, pitch decks, and reports
- mermaid-diagrams — Software diagrams using Mermaid syntax -- class, sequence, flowcharts, ERD, C4
- promo-video — Create promotional videos using Remotion with AI voiceover and background music
- remotion-best-practices — Best practices for Remotion video creation in React
- google-ads — Query, audit, and optimize Google Ads campaigns
- hormozi-ad-factory — Generate 150-750+ ad variations using Hormozi's combinatorial Hook x Meat x CTA framework
- app-renderer-systems — Domain feature systems organized under a
systems/directory - organization-best-practices — Multi-tenant organizations, RBAC, teams, and permissions with Better Auth
- to-prompt — Transform code, issues, or context into a detailed prompt for another LLM
- outside-to-issue — Transform outside-of-diff review files into formatted issue files for a PR
Each skill follows a consistent directory layout:
skills/<skill-name>/
SKILL.md # Main skill definition (required)
references/ # Deep-dive reference material
examples/ # Usage examples and patterns
templates/ # Code templates and scaffolds
scripts/ # Automation scripts and validators
checklists/ # Step-by-step verification checklists
Copy or symlink the skills you need into your Claude Code configuration:
# Copy a single skill
cp -r skills/react ~/.claude/skills/react
# Or symlink the entire collection
ln -s $(pwd)/skills ~/.claude/skillsSkills are automatically picked up by Claude Code when placed in the ~/.claude/skills/ directory. The agent matches tasks to relevant skills based on the description field in each SKILL.md frontmatter.
To add a new skill:
- Create a directory under
skills/with a lowercase, hyphenated name - Add a
SKILL.mdwith proper frontmatter (nameanddescriptionfields) - Include reference material, examples, and templates as needed
- Follow the conventions documented in
skills/skills-best-practices/SKILL.md
See repository root for license information.