A collection of AI agent skills following the Agent Skills open format. These skills extend AI coding agents with specialized capabilities and domain knowledge.
概要
A collection of AI agent skills following the Agent Skills open format. These skills extend AI coding agents with specialized capabilities and domain knowledge.
README
Agent Skills Collection
A collection of AI agent skills following the Agent Skills open format. These skills extend AI coding agents with specialized capabilities and domain knowledge.
Available Skills
Curated Skills
| Skill | Description |
|---|---|
| code-simplifier | Code simplification skill for improving clarity, consistency, and maintainability while… |
| debug | Comprehensive debugging methodology for finding and fixing bugs |
| design-review | Structured UI design review — existing code (React/JSX, CSS, Tailwind) and, when behaviour… |
| deterministic-metric-design | Inventing deterministic metrics — turning a fuzzy property like ‘maintainability’, ‘risk’, or… |
| expo-ui | Library reference for @expo/ui SwiftUI components on iOS — covers Host boundaries, modifier… |
| expo | Expo React Native performance optimization guidelines |
| feature-arch | React feature-based architecture guidelines for scalable applications |
| implementation-design-patterns | Implementation guide for the 22 Gang of Four design patterns in TypeScript, distilled from… |
| implementation-functional-patterns | TypeScript’s functional answers to the 22 Gang of Four classes — factory functions (Factory… |
| ios-taste | Designs iOS 18+ SwiftUI experiences with real taste — starting from user goals, not pixels |
| msw | MSW (Mock Service Worker) best practices for API mocking in tests |
| mui-base | MUI Base UI style guidelines for building headless React component libraries |
| nextjs | Next.js 16 App Router performance, caching, server components, server actions, routing, and… |
| nuqs-codemod-runner | Migrates a nuqs codebase off pre-v2.5 patterns — deprecated throttleMs, hand-rolled… |
| nuqs-scaffolder | Scaffolds URL-state filters for a Next.js page — typed searchParams.ts parser map and a… |
| nuqs | nuqs (type-safe URL query state) best practices for Next.js and other React frameworks |
| playwright | Playwright testing best practices for Next.js applications |
| python | Python 3.11+ performance optimization guidelines |
| radical-simplification | Cognitive moves for collapsing complexity — reframe, clarify, reduce, decompose, invert,… |
| rails-dev | Ruby on Rails performance and maintainability optimization guidelines for building backend APIs… |
| rails-testing | Ruby on Rails testing best practices for writing effective, maintainable test suites with RSpec |
| react-19-component-scaffolder | Scaffolds React 19 / React 19.2 code in TypeScript — components, Server Component pages, client… |
| react-hook-form-audit | Audits a Next.js (App Router, 14/15+) codebase for React Hook Form anti-patterns — watch() at… |
| react-hook-form | React Hook Form performance optimization for client-side form validation using useForm,… |
| react | React 19/19.2 modern patterns for concurrent rendering, Server Components, actions, ref-as-prop,… |
| refactor | Code refactoring best practices based on Martin Fowler’s catalog and Clean Code principles |
| restful-hateoas | RESTful API design guidelines following the Richardson Maturity Model through to Level 3… |
| ruby-optimise | Ruby performance optimization guidelines |
| ruby-refactor | Ruby refactoring guidelines from community best practices |
| rust-implement | "Write production-grade Rust code using a multi-pass approach |
| rust-refactor | Decision frameworks for Rust refactoring, simplification, module decomposition, and incremental… |
| rust-write-tests | Expert-level Rust testing — the “What Could Break?” framework, five transformations from… |
| shadcn | shadcn/ui component library best practices and patterns |
| skill-authoring | Design and development best practices for Claude Code skills, MCP tools, and AI agent capabilities |
| tailwind | Tailwind CSS v4 performance optimization and best practices guidelines |
| tanstack-query | TanStack Query v5 performance optimization for data fetching, caching, mutations, and query patterns |
| tdd | Test-Driven Development methodology and red-green-refactor workflow |
| terminal-ui | Terminal User Interface (TUI) performance and UX guidelines for TypeScript applications using… |
| think | Deep strategic thinking mode that finds the single highest-leverage, most innovative action by… |
| typescript | TypeScript performance, tsconfig, type errors, async patterns — triggered when the user asks to… |
| ui-design | UI/UX and frontend design best practices guidelines |
| vitest | Vitest testing framework patterns for test setup, async testing, mocking with vi.*, snapshots,… |
| web-taste | Designs React 19 + Next.js 16 + Tailwind CSS experiences with real taste — starting from user… |
| zod | Zod schema validation best practices for type safety, parsing, and error handling |
Experimental Skills
| Skill | Description |
|---|---|
| 12-factor-app | The Twelve-Factor App methodology for building scalable, maintainable cloud-native applications |
| 37signals-rails | 37signals Rails coding principles and conventions from DHH, Jorge Manrubia, and the… |
| acceptance-pipeline-catalog | Use when implementing, reviewing, or debugging a Gherkin acceptance-test pipeline with mutation… |
| acceptance-pipeline-feature-design | Designs new features, extensions, or modifications to Uncle Bob’s Acceptance Pipeline… |
| adversarial-beam | Use this skill to gate Elixir/OTP systems on BEAM runtime architecture with a pass/fail… |
| adversarial-ddd | Use this skill to gate DDD and ubiquitous-language quality with a pass/fail adversarial review —… |
| adversarial-elixir | Use this skill to gate Elixir, OTP, Ecto, and Phoenix code with a pass/fail adversarial review —… |
| adversarial-ios-design | Use this skill to gate iOS SwiftUI design and UX with a pass/fail adversarial review — a single… |
| adversarial-phoenix-liveview | Use this skill to gate Phoenix LiveView realtime UIs with a pass/fail adversarial review — a… |
| adversarial-python | Use this skill to gate Python code (floors 3.10+, rules verified through 3.14) with a pass/fail… |
| adversarial-reactor | Use this skill to gate Elixir code built on the Reactor orchestration library (~> 1.0) with a… |
| adversarial-rust | Use this skill when reviewing or refactoring existing Rust code that carries an alien mental… |
| adversarial-swift-ui | Use this skill to gate SwiftUI code with a pass/fail adversarial review — a single blind… |
| adversarial-swift | Use this skill to gate Swift language code with a pass/fail adversarial review — a single blind… |
| adversarial-tanstack | Use this skill to gate TanStack Start plus TypeScript web-app changes with a pass/fail… |
| adversarial-ts-patterns | Use this skill to gate TypeScript and React application code with a pass/fail adversarial review… |
| adversarial-zod | Use this skill to gate Zod 4 schema code in TypeScript and TanStack Start apps with a pass/fail… |
| algorithmic-complexity-review | Algorithmic complexity (Big-O) review — finding nested loops, N+1 queries, exponential… |
| app-planner | Produces a design-plan (living document like an exec-plan) that maps an app domain to feature… |
| ast-grep-typescript-react | Use this skill when writing, debugging, or reviewing ast-grep patterns, YAML rules, or codemods… |
| ast-grep | ast-grep rule writing and usage best practices |
| audio-voice-recovery | Audio forensics and voice recovery guidelines for CSI-level audio analysis |
| base-ui-migrator | Migrates React UI code to Base UI (@base-ui/react) — replacing bespoke modals, custom… |
| better-auth-scaffold | Scaffolds a Better Auth setup in a Next.js (App Router) + Drizzle project — lib/auth.ts,… |
| better-auth | Better Auth in TypeScript — setting up the auth instance, picking adapters, wiring framework… |
| bug-review | Multi-pass PR bug review — 5 parallel passes, majority voting, independent Opus validation, and… |
| build-mcp-server | Entry point for MCP server development — interrogates the user about their use case, determines… |
| chat-apps-ui-sdk | Interactive UI rendered inside ChatGPT or Claude — OpenAI Apps SDK apps, MCP Apps (the… |
| chrome-extension-ui | Chrome Extensions UX/UI design and implementation guidelines for popups, side panels, content… |
| chrome-extension | Chrome Extensions (Manifest V3) performance and code quality guidelines |
| clean-architecture | Clean Architecture principles and best practices from Robert C |
| clean-code-ts-react | Use when writing, reviewing, or refactoring TypeScript or React code for craftsmanship — naming,… |
| clean-code | Use when writing, reviewing, or refactoring code for maintainability and readability |
| cli-for-agents | Designing CLIs that AI agents will invoke — non-interactive flags, layered --help with examples,… |
| cli-review-runner | Black-box CLI grading harness — runs a test suite against a target CLI and reports per-rule… |
| code-distill | On-demand pattern extraction from a specific GitHub codebase, given a focused query — "how does… |
| code-map-visualization | Rendering and perception layer for codebase-as-geohash-map visualisations — choosing what to… |
| codebase-comprehension-algorithms | Mapping an unfamiliar codebase into feature/business domains — answering “what is this about”,… |
| codemod-react-pipeline | Guided, scripted pipeline for running JSX/TSX/React codemods safely across large legacy codebases |
| codemod | Codemod (JSSG, ast-grep, workflows) best practices for writing efficient, safe, and maintainable… |
| codex-goals | Patterns and anti-patterns for using OpenAI Codex Goals — the persistent objectives feature… |
| complexity-optimizer | Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or… |
| computer-science-algorithms | Choosing or implementing an algorithm or data structure — asymptotic complexity, data-structure… |
| datadog-dashboards | Corrects the wrong defaults a model has when building Datadog dashboards, verified against… |
| design-to-react-algorithms | Reverse-engineering a Sketch file (or Figma export with similar shape) into pixel-perfect React… |
| dev-rfc | Create well-structured RFCs and technical proposals for software projects |
| diagram-quality | "PlantUML diagram quality on the agent-uml collaborative canvas — three tiers: rendering safety… |
| diataxis | Use whenever writing, editing, restructuring, or reviewing technical documentation — READMEs,… |
| django-recommender-search-backend-patterns | Django backend patterns for recommendation services (AWS Personalize, Databricks Model Serving,… |
| dockerfile-optimise | Dockerfile optimization guidelines from official Docker documentation |
| docs-search | Library-documentation lookup methodology — API behavior, version-specific changes, idiomatic… |
| domain-architect | Discovers business domains in a Swift codebase by tracing what users can DO — not by reading… |
| drizzle-nextjs-postgres | Drizzle ORM against PostgreSQL inside a Next.js App Router app |
| drizzle-sqlite-scaffold | Scaffolds Drizzle ORM + SQLite boilerplate — a new drizzle.config.ts, a singleton client with… |
| drizzle-sqlite | Drizzle ORM targeting SQLite (better-sqlite3, libsql/Turso, bun:sqlite, Cloudflare D1,… |
| dx-harness | Developer-experience friction auditing and fixing — slow onboarding, repeated manual setup… |
| effect-ts | Effect-TS library usage in TypeScript — Effect.gen generators, Schema.Struct/Schema.Class… |
| elixir-meta-programming | Use this skill when building an Elixir macro or a declarative DSL — a schema/spec/route/workflow… |
| emilkowal-animations | Emil Kowalski’s animation best practices for web interfaces |
| eval-mcp | Measures whether Claude uses an MCP server’s tools correctly — tests tool selection accuracy,… |
| exec-plan | Manage the lifecycle of ExecPlans — self-contained, living specifications for multi-step work |
| expo-design-system-scaffolder | Scaffolds Expo / React Native design system components that obey the expo-design-system rules by… |
| expo-design-system | Airbnb-DLS-aligned design system engineering for Expo / React Native apps targeting both web and… |
| expo-ios-hig-verify | Static scan of an Expo / React Native iOS app for non-native patterns — Material component kits,… |
| expo-ios-hig | Expo / React Native iOS interface conforming to Apple Human Interface Guidelines (iOS 26) —… |
| expo-ios-screen-scaffolder | Scaffolds Expo (React Native) iOS screens that follow Apple Human Interface Guidelines by… |
| expo-react-native-coder | Comprehensive Expo React Native feature development guide |
| expo-react-native-performance | Expo React Native performance optimization guidelines |
| feature-arch-gate | Adversarial pass/fail review gate that enforces the feature-arch skill’s React feature-based… |
| feature-spec | Feature specification and planning guidelines for software engineers |
| fog-of-war-js-ts | Fog of war, field of view, line of sight, and tile visibility in JavaScript or TypeScript games… |
| framer-motion | Framer Motion performance optimization guidelines |
| geohash-spatial-code-maps | Geohash encoding/decoding in TypeScript or Rust — bit interleaving, the base32 alphabet,… |
| go-process-cli | Write Go CLIs that manage processes and workloads — daemons, supervisors, job runners, deploy… |
| graph-schema | Graph database schema design and data modeling expert |
| harness-engineering | Set up or update the agent-first engineering harness for any repository |
| human-copywrite | "User-facing copy — UI strings, documentation, marketing, release notes, error messages,… |
| humanize | Remove signs of AI-generated writing from text |
| implementation-design-patterns-python | Implementation guide for the 22 Gang of Four design patterns in idiomatic modern Python (3.10+),… |
| inngest-nextjs-patterns | Inngest event-driven functions in a Next.js (App Router) project — creating the client, the… |
| io-bound-data-processing | Processing, transforming, or moving datasets that may exceed RAM on a single low-compute box —… |
| ios-animations | Clinic-architecture-aligned iOS animation craft guidelines for SwiftUI (iOS 26 / Swift 6.2)… |
| ios-chaos-monkey | Crash-hunter skill for iOS 26 / Swift 6.2 clinic-architecture codebases that finds and fixes… |
| ios-design-system | Clinic-architecture-aligned iOS design system engineering for SwiftUI (iOS 26 / Swift 6.2)… |
| ios-design | SwiftUI interface implementation patterns aligned with the iOS 26 / Swift 6.2 clinic modular… |
| ios-hig | Apple Human Interface Guidelines for iOS 26 / Swift 6.2 clinic-architecture apps |
| ios-navigation | Opinionated SwiftUI navigation enforcement for iOS 26 / Swift 6.2 clinic modular MVVM-C apps |
| ios-storyboard | Legacy interoperability skill for Storyboard and Interface Builder maintenance in iOS 26 / Swift… |
| ios-testing | Testing practices for iOS 26 / Swift 6.2 clinic modular MVVM-C applications |
| ios-ui-refactor | Principal-level SwiftUI UI review and refactoring patterns for iOS 26 / Swift 6.2… |
| ios-xcode | Xcode setup and tooling guidance for iOS 26 / Swift 6.2 clinic modular MVVM-C projects covering… |
| js-google | JavaScript style and best practices based on Google’s official JavaScript Style Guide |
| jscodeshift | jscodeshift codemod development best practices from Facebook/Meta |
| knip-deadcode | Knip dead code detection best practices for JavaScript and TypeScript projects |
| language-spec-author | "Turn a rough idea for a language into a complete, implementable specification — a DSL, query,… |
| library-reference-distillation | Methodology for starting a new library-reference distillation skill — one that turns an external… |
| linguistic-semantic-algorithms | Mapping out an unfamiliar codebase via NLP and graph algorithms — 40 algorithms across topic… |
| marketplace-personalisation | Personalisation and recommendation systems for a two-sided trust marketplace built on AWS… |
| marketplace-pre-member-personalisation | Pre-member journey of a two-sided trust marketplace — from anonymous landing through onboarding,… |
| marketplace-recsys-feature-engineering | Feature engineering for marketplace recommenders — what to extract from raw marketplace assets… |
| marketplace-search-recsys-planning | Search and recommendation system planning for a two-sided trust marketplace built on OpenSearch… |
| metric-validation-harness | Empirically validates a software metric before trusting or optimizing it — point it at any… |
| migrate-js-to-modern-typescript | Migrating a JavaScript codebase to TypeScript — converting .js files to .ts, adding types to… |
| nextjs-bundle-optimizer | "Next.js 16 bundle-size and build-time optimization — runs a data-driven iteration loop: measure… |
| nextjs-ppr-patterns | Next.js 16 App Router pages mixing static and dynamic content — Partial Prerendering (PPR) under… |
| nginx-c-module-debug | nginx C module debugging guidelines based on the official nginx development guide |
| nginx-c-module-design | nginx C module directive design guidelines for creating admin-friendly configuration interfaces |
| nginx-c-module-perf | nginx C module performance optimization and reliability guidelines based on the official nginx… |
| nginx-c-modules | nginx C module development guidelines based on the official nginx development guide |
| openai-codex-rust-patterns | OpenAI Codex Rust coding patterns distilled from the codex-rs workspace |
| opencode-ts | Write and refactor TypeScript code in repos that use Effect-TS services, Effect Schema,… |
| opensearch-function-scoring-algorithms | Search relevance and ranking on OpenSearch/Elasticsearch for a two-sided marketplace — candidate… |
| opensearch-personalize-caching-strategies | Caching strategies in front of AWS OpenSearch (Elasticsearch) or AWS Personalize — search,… |
| opinionated-nextjs-patterns | Opinionated, backend-agnostic Next.js 16 (App Router) architecture — authorization at the data… |
| orval | Orval OpenAPI TypeScript client generation best practices |
| pt-irs-runbook | Portuguese personal income tax (IRS / Código do IRS) and Modelo 3 filing — determining tax… |
| pulumi | Pulumi infrastructure as code performance and reliability guidelines |
| python-pep-author | "Drafting Python Enhancement Proposals (PEPs) — proposing a Python language feature, a standard… |
| rails-application-ui-blocks | Compose new Rails backend pages and refactor existing Rails UI to use premium blocks from… |
| rails-design-system | Ruby on Rails design system guidelines for building consistent, maintainable UI with minimal… |
| rails-hotwire | Ruby on Rails Hotwire best practices for building interactive applications with Turbo Drive,… |
| react-fetch-cache-patterns | React data-fetching patterns at scale — recommender carousels, infinite feeds, pages with many… |
| react-native-elements | React Native Elements UI component library best practices for performance, theming, and proper… |
| react-optimise | Application-level React performance optimization covering React Compiler mastery, bundle… |
| react-refactor | Architectural refactoring guide for React applications covering component architecture, state… |
| react-testing-library | React Testing Library best practices for writing maintainable, user-centric tests |
| relational-data-modeling | Corrects the wrong defaults a model has when designing a relational schema — the DDL decisions… |
| relational-database-design | Distills a logical relational-database design methodology into rules an agent applies while… |
| same-results-less-code | Same behaviour in fewer, clearer lines — covers the judgment gaps that linters cannot catch… |
| search-ios26-docs | Search and inspect local iOS 26 SDK documentation and Swift interfaces, especially SwiftUI and… |
| search-macos26-docs | Search and inspect local macOS 26 SDK documentation and Swift interfaces, especially SwiftUI,… |
| shell | Shell scripting best practices for writing safe, portable, and maintainable bash/sh scripts |
| sonarqube-ai-slop-gate | Corrects the wrong defaults a model has when standing up self-hosted SonarQube Server as a… |
| staff-level-elixir | Use this skill when writing, reviewing, or refactoring Elixir, OTP, Ecto, or Phoenix/LiveView code |
| storybook | Use whenever creating, configuring, or extending Storybook for a TS/React component library —… |
| stripe-inspired-api-design-rules | JSON HTTP API design rules distilled from Stripe — resource modeling, identifier schemes, URL… |
| swift-data | SwiftData persistence and data-layer architecture for iOS 26 / Swift 6.2 clinic modular MVVM-C apps |
| swift-optimise | Swift 6.2 and SwiftUI performance optimization for iOS 26 clinic architecture codebases |
| swift-refactor | Swift and SwiftUI refactoring patterns aligned with the iOS 26 / Swift 6.2 clinic modular MVVM-C… |
| swift-ui-architect | Opinionated SwiftUI architecture enforcement for iOS 26 / Swift 6.2 clinic modular MVVM-C apps… |
| tailwind-refactor | Tailwind CSS code refactoring patterns for v4 migration and anti-pattern cleanup |
| tailwind-responsive-ui | Responsive UI transformation patterns for Tailwind CSS applications |
| tailwind-ui-refactor | Refactoring UI design patterns for Tailwind CSS applications |
| theory-of-constraints | Apply the Theory of Constraints (Goldratt’s Five Focusing Steps) to find and fix the single… |
| threat-model | Security threat modeling, attack surface mapping, and trust boundary analysis on a codebase |
| threat-patch | Remediate security findings by producing minimal, surgical code patches |
| trpc | Corrects the wrong defaults a model has for tRPC v11 (verified against 11.18.0) |
| ts-google | Google TypeScript style guide for writing clean, consistent, type-safe code |
| typescript-advanced-patterns | Advanced TypeScript — type-level programming, library/DSL APIs, declaration merging, modern… |
| typescript-refactor | TypeScript and TSX refactoring and modernization guidelines from a principal specialist… |
| uniwind | Uniwind best practices for React Native styling with Tailwind CSS |
| unix-cli | UNIX command-line interface guidelines for building tools that follow POSIX conventions, proper… |
| vhs | VHS terminal recording best practices from Charmbracelet |
| vite | Vite performance optimization guidelines |
| web-rules | Strict design and UX rules for React 19 + Next.js 16 (App Router) + Tailwind CSS 4 |
| webpack-plugin-authoring | Writing webpack 5 plugins — hook selection (compiler vs compilation, tap vs tapAsync,… |
| webpack-plugin-recipes | Use whenever you face a webpack-build problem that ends with needing to write a plugin — 26… |
| write-design-docs | Write, revise, or review software design documents using Malte Ubl’s “Design Docs at Google”… |
| wxt-browser-extensions | WXT browser extension performance optimization guidelines |
| yjs-nextjs | Corrects the wrong defaults a capable model has when building Yjs collaborative editing into a… |
| zustand | Zustand state management best practices for React applications |
Installation
Install skills using Vercel’s add-skill CLI:
# Install all skills
npx add-skill pproenca/dot-skills
# List available skills
npx add-skill pproenca/dot-skills --list
# Install a specific skill
npx add-skill pproenca/dot-skills --skill
# Install globally (across all projects)
npx add-skill pproenca/dot-skills --global
Supported Agents
Skills are installed to agent-specific directories:
| Agent | Installation Path |
|---|---|
| Claude Code | .claude/skills// |
| Cursor | .cursor/skills// |
| Codex | .codex/skills// |
| OpenCode | .opencode/skill// |
| Antigravity | .agent/skills// |
Creating Skills
See CONTRIBUTING.md for guidelines on creating new skills.
Quick Start
- Copy the template:
cp -r skills/.template skills/my-skill - Rename the template file:
mv skills/my-skill/SKILL.md.template skills/my-skill/SKILL.md - Edit
SKILL.mdwith your skill’s frontmatter and instructions - Add scripts, references, or assets as needed
- Test with
npx add-skill . --list
Skill Structure
skills/
├── my-skill/
│ ├── SKILL.md # Required: Skill definition and instructions
│ ├── scripts/ # Optional: Executable scripts
│ ├── references/ # Optional: Additional documentation
│ └── assets/ # Optional: Static resources
├── .curated/ # Vetted, production-ready skills
├── .experimental/ # Work-in-progress skills
└── .template/ # Skill template (SKILL.md.template)
License
MIT
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add pproenca/dot-skills