AI Skills Hub - Browse 180,000+ Agent Skills

Determine if a string value should be translated or left as-is. Use when filtering localization keys, validating translation files, or building translation task lists.

Lightweight Chrome automation toolkit with shared configuration, JSON-first output, and six focused scripts for starting, navigating, inspecting, capturing, evaluating, and cleaning up browser sessions.

Production-grade API architecture skill for REST, gRPC, GraphQL design, versioning, and security patterns

Production-grade event-driven architecture skill for Kafka, RabbitMQ, event sourcing, CQRS, and message patterns

Capture a web page as raw material (extracted text/Markdown) with metadata, storing it in the raw/ directory for later distillation.

Manage markdown work-session files in .agent/work-sessions to save, resume, search, and update progress across Copilot or LLM sessions.

Generate Draw.io network topology diagrams from Cisco router and switch configurations. Use when asked to visualize network topology, create network diagrams, map network infrastructure, or generate visual representations from Cisco device configs. Supports parsing show commands, configuration files, CDP/LLDP neighbor data, and routing protocol information to automatically create professional network diagrams.

Comprehensive guide for building production-ready agents with the Claude Agent SDK. Use when creating agents, designing tools, implementing subagents, managing sessions, integrating MCP servers, or understanding SDK-native features. Emphasizes documentation-first approach and using only SDK native capabilities.

Validate and debug Vercel AI SDK provider configurations including API keys, environment setup, model compatibility, and rate limiting. Use when encountering provider errors, authentication failures, API key issues, missing environment variables, model compatibility problems, rate limiting errors, or when user mentions provider setup, configuration debugging, or SDK connection issues.

Agent-to-Agent (A2A) executor implementation patterns for task handling, execution management, and agent coordination. Use when building A2A executors, implementing task handlers, creating agent execution flows, or when user mentions A2A protocol, task execution, agent executors, task handlers, or agent coordination.

Production deployment patterns for ElevenLabs API including rate limiting, error handling, monitoring, and testing. Use when deploying to production, implementing rate limiting, setting up monitoring, handling errors, testing concurrency, or when user mentions production deployment, rate limits, error handling, monitoring, ElevenLabs production.

ElevenLabs Speech-to-Text transcription workflows with Scribe v1 supporting 99 languages, speaker diarization, and Vercel AI SDK integration. Use when implementing audio transcription, building STT features, integrating speech-to-text, setting up Vercel AI SDK with ElevenLabs, or when user mentions transcription, STT, Scribe v1, audio-to-text, speaker diarization, or multi-language transcription.

Row Level Security policy templates for Supabase - multi-tenant patterns, user isolation, role-based access, and secure-by-default configurations. Use when securing Supabase tables, implementing RLS policies, building multi-tenant AI apps, protecting user data, creating chat/RAG systems, or when user mentions row level security, RLS, Supabase security, tenant isolation, or data access policies.

Configure pgvector extension for vector search in Supabase - includes embedding storage, HNSW/IVFFlat indexes, hybrid search setup, and AI-optimized query patterns. Use when setting up vector search, building RAG systems, configuring semantic search, creating embedding storage, or when user mentions pgvector, vector database, embeddings, semantic search, or hybrid search.

Validates Claude Agent SDK configuration files, environment setup, dependencies, and project structure

Web scraping templates, scripts, and patterns for documentation and content collection using Playwright, BeautifulSoup, and Scrapy. Includes rate limiting, error handling, and extraction patterns. Use when scraping documentation, collecting web content, extracting structured data, building RAG knowledge bases, harvesting articles, crawling websites, or when user mentions web scraping, documentation collection, content extraction, Playwright scraping, BeautifulSoup parsing, or Scrapy spiders.

Celery canvas patterns for workflow composition including chains, groups, chords, signatures, error handling, and nested workflows. Use when building complex task workflows, parallel execution patterns, task synchronization, callback handling, or when user mentions canvas primitives, workflow composition, task chains, parallel processing, or chord patterns.

Task routing and queue management patterns for Celery including priority queues, topic exchanges, worker-specific routing, and advanced queue configurations. Use when configuring task routing, managing queues, setting up priority queues, implementing worker routing, configuring topic exchanges, or when user mentions task routing, queue management, Celery routing, worker assignments, or message broker routing.

Production-ready Celery task templates with error handling, retries, rate limiting, time limits, and custom task classes. Use when creating Celery tasks, implementing retry logic, adding rate limiting, setting time limits, building custom task classes, validating task inputs with Pydantic, handling database operations, making API calls, or when user mentions task patterns, retry mechanisms, task templates, error handling, task best practices.

Clerk and Supabase integration patterns for user sync, JWT authentication, and RLS policies. Use when integrating Clerk authentication with Supabase, syncing user data between platforms, configuring RLS with Clerk JWT tokens, setting up webhooks for user events, implementing secure database access with Clerk identity, or when user mentions Clerk Supabase sync, user synchronization, JWT RLS, authentication webhooks, or database user management.

Guide for upgrading Astro projects from v5 to v6. Use when users mention upgrading Astro, Astro v6, Astro 6, or errors related to content collections, ViewTransitions, Astro.glob, Zod schemas, or Content Layer API.

Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building understanding through implementation with checkpoint questions.

Build MCP servers for integrating external APIs with AI agents

Generate FOSMVVM ViewModels - the bridge between server-side data and client-side Views. Use when creating new screens, pages, components, or any UI that displays data.

Bun package manager and runtime best practices

Security patterns for input validation, PII protection, and cryptographic operations

ElevenLabs voice cloning techniques, audio quality requirements, recording best practices, and training data optimization for professional-quality voice clones. Use when creating custom voices, cloning voices, or optimizing voice clone quality.

Workspace-first R statistics suite with subskills and agent-run metaskills (including run-demo for guided onboarding, explain-statistics for concept explanations, explain-results for interpreting outputs, format-document for NLSS format alignment, screen-data for diagnostics, check-assumptions for model-specific checks, and write-full-report for end-to-end reporting) that produce NLSS format tables/narratives and JSONL logs from CSV/SAV/RDS/RData/Parquet. Covers descriptives, frequencies/crosstabs, correlations, t-tests/ANOVA/nonparametric, regression/mixed models, SEM/CFA/mediation, EFA, power, reliability/scale analysis, assumptions, plots, missingness/imputation, data transforms, and workspace management.

**UNIVERSAL TRIGGER**: Use when user wants to READ/SEND/MANAGE email via IMAP/SMTP.

This skill orchestrates code review and plan validation using Google Gemini CLI. It should be used when users want to validate implementation plans, review completed code, or discuss architecture decisions with Gemini as a second opinion. Supports FastAPI, Next.js, and general tech stacks with specialized checklists. Uses gemini-3-pro-preview model with free tier (60 req/min, 1000 req/day).

Build and maintain effective CLAUDE.md files that improve Claude Code efficiency. Use when creating a new CLAUDE.md file, auditing/improving an existing one, setting up progressive disclosure with agent documentation, or optimizing context window usage for Claude Code projects.

This skill should be used when executing 2+ independent tasks in parallel - orchestrates git worktrees with terminal sessions (tmux/wezterm).

This skill should be used at conversation start when user mentions parallel, multiple tasks/features, worktrees, lists 2+ independent work items, or similar keywords - determines which polydev skill to use.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Generate professional PowerPoint pitch decks for startups and businesses. Use this skill when users request help creating investor pitch decks, sales presentations, or business pitch presentations. The skill follows standard 10-slide pitch deck structure and includes best practices for content and design.

Pre-merge security validation detecting secrets, user-specific paths, insecure SSH configurations, and security-weakening flags. Use before committing code/documentation, before creating PRs, or during QA validation. Supports automated scanning with severity-based enforcement (CRITICAL blocks merge, HIGH requires fixes).

Multi-agent debate with 3-phase workflow. Optional --deep mode for feedback loop.

Atlas skill for dynamic agent composition and management. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

Use this skill ONLY when adding a new technical indicator (e.g., Bollinger Bands, Stochastic, ATR). Do not use for strategies or agents.

Capability statement. Use when scenario-1, scenario-2, or scenario-3.

Queries Nx workspace metadata, project configurations, affected detection, generator schemas, and dependency graphs via unified Python CLI. Use when analyzing monorepo structure, inspecting project.json configurations, determining affected projects for CI optimization, discovering available generators, or visualizing workspace dependencies.

Search and reference Microsoft code samples and SDK documentation

Build, serve, and deploy the Hugo static site. Use when building the site, testing locally, checking for errors, or deploying to GitHub Pages.

Use when refactoring fat Rails models with repetitive prefixes like entropy_*, notification_*, or multi-association coordination. Extracts PORO wrappers that group operations around nouns/concepts.

Aggregate boundaries, relationships, lifecycle hooks, value objects

Debug Reploid agent issues. Use when investigating agent loop problems, tool execution failures, VFS issues, or state management bugs in the browser-based RSI substrate. (project)

Creates and manages C4 architecture diagrams using PlantUML. Use when the user wants to visualize software architecture, create context/container/component/sequence diagrams, document system design with the C4 model, or mentions architecture diagrams, system design, or PlantUML. Supports iterative diagram building through conversational workflow.

Enforce Claude Compass development standards and best practices. This skill should be used when writing or modifying code in the Claude Compass repository, including parsers, database migrations, graph builders, MCP tools, and core services. It ensures adherence to code quality principles, proper error handling, self-documenting code, and established architectural patterns.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Run the test suite for anyformat-backend services using Docker Compose. Use when you need to validate code changes, debug failing tests, or verify that implementations work correctly before committing.

Use when profiling native macOS or iOS apps with Instruments/xctrace. Covers correct binary selection, CLI arguments, exports, and common gotchas.

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.

{description from Notion}

Shared resource library for Google integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by gmail, google-docs, google-sheets, google-calendar, and future Google skills.

Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings

Cloudflare Workers development patterns including Workers AI, Durable Objects, KV storage, and Hono routing. Use when building serverless edge functions, AI-powered services, or stateful workflows on Cloudflare.

Swift language mastery skill covering advanced language features beyond UI. Use when working with macros, concurrency (async/await, actors), networking, Swift Testing, generics, memory optimization, or result builders. Not for SwiftUI patterns - see swift-ui.

SwiftUI implementation patterns for building polished iOS/macOS apps. Use when building views, managing state, creating layouts, implementing animations, or structuring app architecture in SwiftUI.

This skill should be used when writing, reviewing, or refactoring documentation that will be consumed as AI context. Optimizes documentation for LLM comprehension using principles of completeness, efficiency, and zero fluff—replacing prose with structured data, enforcing heading hierarchy, detecting meta-commentary, and validating that examples serve a purpose.

Reply to a specific message in a channel. Use this to respond to issues, answer questions, or continue threaded conversations.

Publish a message to a channel or DM. Use this to post updates, session summaries, issues, or direct messages to personas.

Test and validate agent skills against the Agent Skills Specification v1.0. Use before deploying skills to ensure spec compliance and catch structural issues.

Comprehensive Bitbucket pipeline automation using direct Node.js API calls. Monitor pipeline status, analyze failures, download logs, and trigger builds. Use this skill when the user asks to check pipeline status, find failing pipelines, download logs, trigger builds, or debug pipeline failures. No MCP approval prompts required - uses Bash tool with node commands.

Use when user wants to see all autonomy worktrees with their status

Use when user wants to inventory autonomy branches with custom sorting, grouping, or filtering

Keycloak identity and access management including realms, clients, authentication flows, themes, and user federation. Activate for OAuth2, OIDC, SAML, SSO, identity providers, and authentication configuration.

Comprehensive work session initialization orchestrator that validates environment, creates properly named branches, and prepares development environment for new tasks

Comprehensive work session initialization orchestrator that validates environment, creates properly named branches, loads GitHub Issues, and prepares development environment for new tasks

Browser automation and E2E testing via local Playwright Docker container

Git コミットの作成を支援する。以下の場合に発動: (1) ユーザーが /commit と入力した時、(2) コード変更が完了しコミットが適切と判断した時、(3) ユーザーがコミットを依頼した時。変更内容を分析し、適切なコミットメッセージを生成してコミットを作成する。

Work with Jira issues using the jira CLI. Use for listing, creating, viewing, editing, and deleting Jira issues. Supports CRUD operations, custom fields, JQL queries, and common workflows like finding your assigned issues, filtering by status, and bulk operations.

Perform SQL joins and multi-table analysis on DST data in DuckDB. Use when research requires combining multiple tables on common dimensions (time, region). Provides patterns for common DST dimension joins and multi-table comparisons.

Fetch actual data from Danmarks Statistik API and store in DuckDB. Use when user wants to download and store specific DST table data for analysis.

GitHub label and milestone management expertise. Auto-invokes when labels, milestones, taxonomies, issue organization, sprint planning, or phase tracking are mentioned. Handles label CRUD, bulk operations, milestone creation/tracking/progress, and issue grouping for releases and sprints.

Manage school lunch ordering for preschool with catered meals. Analyzes menus based on preferences (avoid rice, prefer BBQ and mac & cheese), helps select meals, processes orders from any source (PDF/screenshot/browser/verbal), and generates calendar reminders for days when lunch needs to be packed. Use when discussing school meals, menu selection, or packing lunch.

This skill should be used when creating icons for Odoo modules. It generates modern Material Design style PNG icons (128x128) with white background, colored circle, and composable colored primitives. Updates manifest files and automatically handles web_icon references in menu XML files. Use when user asks to create, generate, or add an icon to an Odoo module.

Convert JSON ABI files to TypeScript const exports with proper typing. Use when working with smart contract ABIs,

How to use the file-factory CLI to create new React components, hooks, context providers, Next.js pages along with associated tests and storybook stories. ALWAYS use this tool instead of manually creating new components/hooks/contexts/pages to ensure consistent file structure and conventions.

Validates that version strings in Dockerfiles match package.json dependencies and constraints. Use when updating Docker base images, Node.js versions, pnpm versions, turbo versions, or other tool versions in Dockerfiles. Ensures consistency between Dockerfile versions and package.json engines, devDependencies, and packageManager fields. Automatically runs on pre-commit for Dockerfile changes and in CI pipeline. Trigger keywords: Dockerfile, Docker version, Node version, pnpm version, turbo version, version mismatch, version sync, Docker update.

Claude Code hook creation and configuration. PAI event-driven automation.

Run verification commands and confirm output before claiming success

How to use Chrome DevTools MCP for browser debugging. Use when you need to inspect pages, take screenshots, debug UI issues, or verify visual changes.

Launch and control Chrome with AT-SPI2 accessibility for browser automation. Use when asked to start chrome, open browser, launch chrome, begin browser automation, or control web pages.

Format git commit messages correctly, avoiding HEREDOC syntax issues in favor of multiline strings

Fetch and compress blog articles from tech-lab.sios.jp into the doc/ directory with token usage statistics and OGP metadata

Extract structured metadata from documents using AI. Classify content types, extract topics and tools. Supports async batch processing.

Manage Kurt documents - list, query, retrieve content, delete, find duplicates. Use CLI commands, Python API, or direct SQL queries.

Tool discovery, routing, chaining, error handling, and composition for the 34+ MCP scheduling tools. Use when orchestrating complex multi-tool workflows, handling MCP errors, or discovering available capabilities.

Execute resident-requested swaps with safety checks, audit trails, rollback capabilities, and escalation procedures. Use when processing swap requests, validating against constraints, or managing swap lifecycle including rollbacks.

Define and run end-to-end test scenarios for medical residency scheduling. Use when validating complex scheduling logic, testing edge cases, verifying ACGME compliance under stress, or running regression scenarios. Includes 20+ pre-built scenarios covering N-1 failures, multi-swap operations, holiday conflicts, and moonlighting.

Use when answering complex questions about a codebase that require exploring multiple areas or understanding how components connect - coordinates parallel sub-agents to locate, analyze, and synthesize findings

Generate comprehensive changelogs from Git history with dual formats (client-accessible and technical) including working days calculation, feature consolidation, GitHub enrichment, and automated client-friendly translation

Use this skill when working with Graphite (gt) for stacked PRs, using execute-issue-jira-graphite agent, or when the user mentions Graphite, stacking, or gt commands. Ensures proper use of gt commands instead of raw git for stack-aware operations.

Manages the specification-driven development workflow. Use this skill when the user runs /orbit, requests to "define feature", "create plan", "implement", or needs workflow guidance. It detects the current phase from artifacts and executes the appropriate action.

Creates new Claude Code skills following best practices. Guides through skill structure, naming, descriptions, and progressive disclosure. Use when user wants to create a skill, build a skill, make a new capability, or asks about skill best practices.

Creates Claude Code hooks for automation and workflow customization. Guides through hook events, configuration, and script creation. Use when user wants to create a hook, automate Claude Code, or asks about hook events.

Token-based design system with standardized CSS custom property names, multiple theme implementations (polished with light/dark mode, sketch), and optional component patterns. Use for themeable interfaces, design system compliance, or switching between visual fidelity levels without code changes.

Literate UI/UX for product teams - accelerate from idea to working prototype in minutes using markdown with embedded interactive React components. Use for fast iteration and async collaboration on product specs, wireframes, user flows, feature demos, and design documentation. Replaces Figma/Storybook with executable specs in version control.

Parse URLs in CSV files and extract query parameters as new columns. Use when working with CSV files containing URLs that need parameter extraction and analysis.

This skill should be used when creating artistic icon variations from images. It generates 10 different greyscale icon styles from a single image source, automatically compressing to under 20KB with high contrast appearance. Supports both URL and local file inputs.