AI Skills Hub - Browse 180,000+ Agent Skills

Complete ArgoCD API and CLI skill for GitOps automation. Use when working with ArgoCD for: (1) Managing Applications - create, sync, delete, rollback, get status, (2) ApplicationSets - templated multi-cluster deployments, (3) Projects - RBAC, source/destination restrictions, sync windows, (4) Repositories - add/remove Git repos, Helm charts, OCI registries, (5) Clusters - register, rotate credentials, manage multi-cluster, (6) Accounts - generate tokens, manage users, check permissions, (7) Any ArgoCD REST API calls or argocd CLI commands. Supports both REST API (curl/HTTP) and CLI wrapper approaches with bearer token authentication.

Enforces Zig coding conventions from the Zig Zero to Hero guide. Use when writing, reviewing, or refactoring Zig code. Applies naming conventions, error handling patterns, resource management, and module organization best practices.

Analyzes CPU profiles to identify performance bottlenecks and generate optimization recommendations

技術研修演習問題を執筆。概要・問題・解答形式・解答例の構造、:::stepディレクティブでハンズオン手順を記述。演習問題作成時に使用。

技術研修フライヤー要件を執筆。文字数制限付きのキャッチ文章、学習目標、カリキュラム、研修詳細を記述。フライヤー、チラシ作成時に使用。

Create skills that wrap MCP (Model Context Protocol) servers for use with mcp-skill-client. Use when user wants to create a new MCP-based skill, wrap an existing MCP server as a skill, or generate SKILL.md with tool documentation from an MCP server.

This skill should be used when performing local data exploration, profiling, quality analysis, or transformation tasks using DuckDB. It handles CSV, Parquet, and JSON files, provides automated data quality reports, supports complex JSON transformations, and generates interactive HTML reports for data analysis.

Tracks and monitors GitLab merge request activity including comments, status, and real-time updates

Generate hierarchical code maps from any codebase for AI agent consumption. Use when: (1) Analyzing or understanding a codebase structure, (2) Creating documentation of code architecture, (3) Mapping dependencies between files, (4) Extracting class hierarchies and call graphs, (5) Onboarding to a new project, (6) Preparing context for AI-assisted code modifications. Supports Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, Ruby, PHP, and 20+ languages via tree-sitter.

Defines target browser versions for CSS autoprefixing and JavaScript transpilation. Generates .browserslistrc configuration file.

Complete development guide for the NYCRAVES codebase. Use this skill when creating any new code - components, pages, features, data functions, or utilities. Ensures visual consistency (brutalist dark theme), code consistency (established patterns), and proper Next.js 16 architecture (caching, Server Components, loading states). Triggers on (1) Creating new components, (2) Building new pages, (3) Adding features, (4) Writing data functions, (5) Questions about patterns or conventions.

Create and manage Browser Use Cloud skills for browser automation. Use when creating new browser automation skills, checking skill status, or adding web scraping/interaction capabilities.

Deletes specific PDF documents from Qdrant vector database collection. Use when user wants to remove, delete, or clean up PDF documents from the vector database, Qdrant collection, or needs to manage document versions.

自動的にGitHub Issueを分析し、構造化された内容に改善するスキル。 雑なIssueや情報不足のIssueをAIが作業しやすい形式に自動補完・加筆訂正する。 タイトルの標準化、本文の構造化、適切なラベル付与、不足情報の指摘を行う。 「このIssueを改善して」「Issue内容を整えて」といった依頼で使用。

Generates audio narration from a text file using Chatterbox TTS. Use when the user wants to generate voiceover/audio from ANY text file.

Handle MetaMask signature and transaction popups during Web3 DApp testing - approve signatures, send transactions, call contracts. Detects popup type and handles gas errors.

Reserve allocation and follow-on optimization for the Phoenix fund model. Use

Multi-language code formatting and style enforcement with automatic linting fixes

Interact with and test local web apps using Playwright.

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.

Debugs and troubleshoots Mission Control health checks by analyzing check configurations, reviewing failure patterns, and identifying root causes. Use when users ask about failing health checks, mention specific health check names or IDs, inquire why a health check is failing or unhealthy, or need help understanding health check errors and timeouts.

Use when building React UIs for TheGP applications, migrating existing UIs to @gp/ui components, integrating Tailwind v4 with @gp/ui theme, or answering questions about available components, design tokens, icons, or setup. Activate when user mentions @gp/ui, TheGP design system, or asks about GP-specific UI patterns and components.

This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively validate that development work on localhost is being built appropriately and to support debugging browser-rendered content. Use this skill after making frontend changes to verify the output visually.

Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.

Guide for creating MCP (Model Context Protocol) servers. Use this when building integrations with external services, creating new MCP servers, or connecting Claude to APIs.

Create isolated git worktrees with smart directory selection and safety verification. Use this when starting feature work that needs isolation, parallel development, or safe experimentation.

使用 FastMCP 框架开发交易相关的 MCP 工具, 包括交易所 API 集成(币安/OKX等)、行情数据获取、订单管理等.当需要创建 MCP 服务器或交易工具时触发此技能.

Create paginated list UseCase (Request + UseCase + Response + Test). Use when listing entities with pagination. Generates Get{EntityPlural} pattern with page/itemsPerPage.

Use TDD workflow (Red-Green-Refactor-Validate) when creating or modifying any business logic, use cases, or domain code. MANDATORY for all implementations. Apply when user requests new features, bug fixes, or refactoring that involves testable code.

Create Value Object for domain modeling following DDD patterns. Use when you need to encapsulate primitive values with validation, business rules, and immutability. Creates reusable VOs like PriceField, EmailField, QuantityField with validation and domain logic.

Create Repository interface and Finder interface for domain entity persistence. Use when entity needs persistence layer with commands (save, delete) and queries (find, findAll). Generates both Repository (commands) and Finder (queries) following CQRS pattern.

Retrieve APPLICATION patterns (architecture, procedures, conventions) from AgentDB skills table. Use BEFORE implementing to ensure consistency.

Create functional test for HTTP controllers and LiveComponents. Use when testing web endpoints, form submissions, API responses, or LiveComponent interactions. Tests make HTTP requests and verify responses/DOM.

State-of-the-art debugging agent with hypothesis-driven analysis, automatic code instrumentation, git worktree isolation, and browser automation. Use when debugging errors, stack traces, unexpected behavior, performance issues, failed tests, race conditions, or hard-to-reproduce bugs.

Comprehensive validation of FTD analysis output files. Checks JSONL format, field completeness, score validity, and structural requirements for TALD scale evaluations.

CRITICAL development guide for Microsoft Agent Framework (MAF) in IPA Platform.

Provides comprehensive development rules and guidelines for Cursor project development. Use when working on Cursor projects, setting up development environments, or implementing coding standards.

Workflow for acquiring historical Ethereum blockchain data using Google BigQuery free tier. Empirically validated for cost estimation, streaming downloads, and DuckDB integration. Use when planning bulk historical data acquisition or comparing data source options for blockchain network metrics.

Troubleshoot and manage GCP e2-micro VM running eth-realtime-collector. Use when VM service is down, systemd failures occur, real-time data stream stops, or VM network issues arise. Keywords systemd, journalctl, eth-collector, gcloud compute.

Complete end-to-end WhatsApp media processing workflow. Processes audio/images AND integrates them into chat.md in a single step. Use when you want to do the complete daily media processing (transcribe + OCR + integrate into chat).

Automatically integrates processed media (audio transcriptions and image summaries) into chat.md files at the correct timestamp position. Use this when you want to merge processed .json audio files and .md image summaries into the daily chat.md conversation log.

Practical guidance for schema design, migrations, ops, testing, and performance in PostgreSQL for FastAPI + SQLAlchemy + Alembic projects. Includes safe-ops guardrails.

Debug CSRF token issues and authentication problems including 403 Forbidden errors, cookie issues, JWT tokens, OAuth flows, and session management. Use when troubleshooting CSRF verification failed, 403 errors on POST requests, login not working, or token refresh issues.

Analyze and optimize Django ORM queries including N+1 problems, missing indexes, slow queries, and migration issues. Use when troubleshooting slow API responses, database performance, query optimization, or migration errors.

Debug Django Channels WebSocket issues including connection failures, authentication, message handling, Redis pub/sub, and real-time streaming. Use when troubleshooting WebSocket not connecting, messages not received, connection dropped, or streaming not working.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Verify visual and structural parity between XHTML chapters and POD PDF files. Use to ensure print edition matches digital EPUB layout.

Run and interpret visual QA pipeline for EPUB XHTML files. Use when user asks about layout, screenshots, visual issues, or rendering problems in REBRANDED_OUTPUT.

Build Xcode projects or workspaces from the CLI, diagnose compile-time/build-time failures, and iterate fixes until the app builds. Use when asked to run xcodebuild, compile iOS/macOS apps, resolve compiler/linker/signing issues, or unblock build errors in .xcodeproj/.xcworkspace repositories.

useSWR/useSWRMutationでサーバーデータを管理します。データ取得、変更、SWRキー管理を含む、カスタムフックパターンを実装します。

useEffectEventを使用して非リアクティブなロジックを抽出し、Effectを最適化します。特定の値が変更されたときにEffectを再実行すべきでない場合（ログ、分析、タイマー）に使用します。

テスト実行・検証専門スキル。Unit テスト、E2E テスト、型チェック、ビルドテストを自動実行し、結果を解析して報告する。

クライアント状態をグローバル/URL状態で型安全に管理します。サイドバーやフィルタはuseSWRImmutable、ページネーションはnuqs。

Use when creating demo GIFs for Swift package READMEs, recording iOS simulator videos, or setting up demo apps for SwiftUI libraries

Select appropriate Segoe MDL2 Assets icons for WinUI Windows applications. Use when the user needs an icon for their WinUI app UI, asks for icon recommendations, needs a glyph for a button or control, or wants to find icons by visual appearance or use case. Provides Unicode points and icon names with visual descriptions and creative alternatives.

Automatically reviews DevPrep AI code for quality standards including ESLint compliance, TypeScript strict mode, 180-line file limits, complexity under 15, proper naming conventions, import patterns, and architectural compliance with the 6-folder structure

Verify claims against referenced sources. Checks if blog content accurately represents external resources, APIs, or documentation. Trigger phrases: "fact check", "verify", "check claims", "verify claims", "check sources", "verify sources"

Review test cases for ID Token validation. Covers ID Token structure, required/conditional claims, signature validation (RS256), and all validation rules per OIDC Core 1.0 Section 2 and 3.1.3.7.

Pre-publish validation and checklist for blog posts. Runs automated checks, optional research, and final review before publishing. Trigger phrases: "publish", "ship it", "ready to publish", "go live", "pre-publish", "publish post"

Comprehensive guide for creating effective Claude Code skills with security best practices, CLI-specific features, and structural patterns. Use when creating skills, needing security guidance, understanding skill architecture, or learning best practices.

Chrome DevTools MCP for browser automation. Five servers configured for parallel agents. Auto-select available server, cleanup when done.

Automatically helps debug PWA issues including service workers, caching, offline functionality, and storage problems in VSSK-shadecn

Automatically helps debug Web Audio API issues, audio playback problems, pitch preservation, and caching issues in the VSSK-shadecn music practice app

Create and execute git commit plans from YAML files - use when organizing changes into logical commits or when user wants help structuring their git history

Collaborative problem-solving protocols: write technical specifications (spec, or alspec), create implementation plans (plan, or alplan), or use Align-and-Do Protocol (AAD). Also generates PR/MR descriptions (aldescription).

Interact with Proxmox VMs - screenshots, keystrokes, network info (user)

Take and view screenshots of Hetzner Cloud servers via WebSocket VNC console

Complete autonomous DJ system for Traktor Pro 3 with MIDI control, intelligent track selection, energy flow management, and professional mixing workflows. Use when working on DJ automation, Traktor integration, autonomous music mixing, or building DJ agents that need real-time performance capabilities.

Write ServiceX queries in func_adl against ATLAS xAOD data (PHYSLITE/PHYS) and provide guidance for dataset selection, filtering, and deliver usage. Use when asked to build, edit, or debug ServiceX/func_adl queries, ATLAS xAOD skims, or rucio dataset fetches.

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Complete weekly stock analysis workflow: fetch end-of-week prices, calculate returns/momentum, and merge with fundamentals from Rice Data Portal. Self-contained for all weekly analysis tasks.

Lightweight Chromium DevTools automation via the bundled browser-tools.ts CLI (Puppeteer connect). Use when you need to launch a Chromium-based browser with a remote-debugging port, navigate pages, run JS in the active tab, capture screenshots, inspect DevTools sessions, or extract readable content without a full browser automation server.

Complete monthly stock analysis workflow: fetch end-of-month prices, calculate returns/momentum, and merge with fundamentals from Rice Data Portal. Self-contained for all monthly analysis tasks.

Visual regression testing for web pages. Compares screenshots to detect UI changes, generates overlay images highlighting differences. Use after making frontend changes to verify visual correctness, catch unintended side effects, or validate that changes look as expected.

Guide for creating effective tools for AI agents. Use when building MCP tools, agent APIs, or any tool interface that agents will consume. Focuses on token efficiency, meaningful context, and proper namespacing.

Manages Google Calendar through the Calendar API. Create, read, update, and delete events, manage multiple calendars, set reminders, handle recurring events, and sync with local schedules. Use when working with Google Calendar, scheduling events, checking availability, managing meetings, or automating calendar workflows.

Manages Google Drive files and folders through the Drive API. Search for files, read content, create and update documents, organize folders, manage permissions, and sync files. Use when working with Google Drive, uploading/downloading files, searching Drive content, or managing Drive organization.

World-building companion for the Aphebis platform that helps users explore, discuss, and extend fictional worlds. Use when users want to browse existing worlds/areas/locations, brainstorm world expansion ideas, create new worlds, or understand how fictional locations interconnect narratively. Provides collaborative world-building with discovery-first approach, creative philosophy guidance, and structured workflows for incremental building.

Manages Gmail through the Gmail API. Search and read emails, send messages, manage labels and filters, handle attachments, and automate email workflows. Use when working with Gmail, reading/sending emails, searching inbox, managing email organization, or processing email data.

Creates a new GameMaker enemy that can switch between melee and ranged attacks based on distance, formation role, cooldowns, and line of sight. Use when the user asks to create an enemy with both melee and ranged capabilities, context-based attack switching, or tactical combat behavior.

Transforms product or technical specifications into concrete implementation plans and task notes within Obsidian. Parses spec documents, extracts requirements, creates structured implementation plans with linked tasks, and manages development workflow from requirements to completion using markdown files and frontmatter.

Database operations for BAZINGA orchestration system. This skill should be used when agents need to save or retrieve orchestration state, logs, task groups, token usage, or skill outputs. Replaces file-based storage with concurrent-safe SQLite database. Use instead of writing to bazinga/*.json files or docs/orchestration-log.md.

t.wada流TDD（テスト駆動開発）。新機能実装、バグ修正、リファクタリング時に自動適用。Red-Green-Refactorサイクル、AAA構造、振る舞いテストの原則に従う。テストを書く、テストファーストで実装する、テストコードをレビューする際に使用。

Git branching strategy and versioning workflow. Use when creating branches, PRs, or releasing versions.

Implement, refactor, or review worker-based multithreading in TypeScript/JavaScript apps (browser or Node). Use when offloading CPU-heavy loops to Web Workers, setting up a worker pool, moving data across threads, or diagnosing worker crashes, slowdowns, or synchronization bugs.

Vitest testing conventions and patterns for @j0kz/mcp-agents including test organization, naming, assertion patterns, mocking strategies, and coverage targets (75%). Use when writing tests, organiz...

Systematic troubleshooting for MCP tools including installation issues, runtime errors, config problems, and debugging strategies. Use when MCP tools not working, debugging errors, or helping users...

Prevents Git Bash path conversion issues when running Anubis commands on Windows. Use when building targets with `cargo run` or `anubis.exe` that use `//` target paths.

Debug OpenAI/Gemini image generation failures for Sketch Magic. Use when `/api/convert` returns 500, when models are unsupported, when outputs are empty, or when provider timeouts/quota errors appear.

Run and manage a single-instance Chrome DevTools MCP server on this machine, including start/stop/status/dedupe workflows and safe cleanup to prevent multiple chrome-devtools-mcp processes from running concurrently. Use when you need a singleton MCP server for Chrome DevTools or when EMFILE/process-spawn issues require enforcing exactly one chrome-devtools-mcp instance.

Upload pipeline troubleshooting for Sketch Magic. Use when HEIC uploads fail, previews don’t render, files are too large, or upload validation errors appear.

Azure CLI (az) operations for resource groups, deployments (ARM/Bicep), app services/container apps, ACR images, Key Vault secrets, role assignments, and operational checks. Use when a request involves `az` commands, Azure deployments, secrets/app settings, or Azure resource management.

Local development workflow for nostrstack, including running API/gallery with logs, regtest stack usage, MCP Chrome DevTools verification, QA fallback, and environment/setup troubleshooting. Use when starting dev, debugging, reproducing issues, or validating UI/console/network behavior in the nostrstack repo.

Chrome DevTools QA workflow for the Sketch Magic kid-first UI. Use when validating Console/Network/Performance, investigating “tap doesn’t work”, /api/convert failures, mobile touch issues, or when a proof video must be backed by DevTools evidence.

Gyazo APIを使用して最新の画像を取得して表示するスキル

Work with pytest-recording (VCR.py) for recording and replaying HTTP interactions in tests. Use when writing VCR tests, managing cassettes, configuring VCR options, filtering sensitive data, or debugging recorded HTTP responses.

Use when reviewing plugin quality, auditing plugins, analyzing the marketplace, checking plugins against Anthropic standards, or evaluating plugin architecture - provides systematic analysis methodology with validation framework

Convex CLI expert for serverless backend and real-time database. Use when users need to deploy functions, manage environments, or import/export data.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup