AI Skills Hub - Browse 180,000+ Agent Skills

Uses shared scripts from [openapi-toolkit](../../../../../.claude/shared/openapi-toolkit/README.md).

Uses shared scripts from [openapi-toolkit](../../../../../.claude/shared/openapi-toolkit/README.md).

Create a GitHub issue from an Epic document. Use when the user wants to create a GitHub issue from an epic.md file, sync an epic to GitHub, or link an epic document to a GitHub issue. The skill extracts the epic title and type from YAML frontmatter, creates an issue via `gh issue create`, and updates the frontmatter with the issue link.

Look up the latest version of any package using deps.dev API. Use this skill when checking package versions, updating dependencies, adding new packages to a project, or when the user asks about the current version of a library.

Use when running verification pipelines, checking test/lint/type status, or ensuring code quality gates pass before completing work

Test Clauduino Status API endpoints and verify LED functionality. Use when users need to: (1) Verify device is responding, (2) Test all LED states (red/yellow/green/waiting), (3) Check status endpoint, (4) Validate SSE stream (simulator only), (5) Debug API connectivity issues.

Deploy applications and websites to Vercel with a claimable preview. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment". No authentication required - returns preview URL and claimable deployment link.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Create Claude Code plugins with proper structure. Use when user requests "create a plugin" or needs to scaffold a new plugin with metadata, directories, and marketplace registration.

Batch-process web pages via headless Playwright browser, extract HTML, convert to markdown using Turndown, and save to timestamped scratchpad file. Use when user asks to "capture these pages as markdown", "save web content", "fetch and convert webpages", or needs clean markdown from HTML. All URLs from one prompt → single file at docs/web-captures/<timestamp>.md.

Use when encountering unfamiliar import statements; when exploring a dependency's API; when user asks "what's import X?", "what does import X do?", or about package documentation. - Generates comprehensive API documentation for Swift package dependencies on-demand. This skill helps you quickly obtain documentation for packages used in Xcode projects when you encounter unfamiliar module imports. Automatically resolves modules to packages and caches documentation for reuse. This is the primary tool for understanding individual `import` statements.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Use safe-rm command to safely 'remove' files by renaming them to .obsolete instead of permanent deletion. Reversible, collision-safe, hook-compliant.

小红书评论痛点挖掘工具。从指定帖子链接抓取评论，进行词频分析和情感分析，生成 Excel 数据表和 Markdown 调研报告。当用户需要分析小红书评论、挖掘用户痛点、进行用户调研时使用此技能。

Generate and use a codebase signature map JSON (signatures.json) for fast project navigation. Use when asked to create or refresh a signature map, inspect functions or methods across languages, or build a lightweight index of project APIs without manually scanning files. Works in repos that include scripts/generate-signatures.sh (for example B2Broker).

为舞蹈视频自动添加跟随音乐节奏的缩放运镜效果。当用户请求为视频添加节奏感、动态运镜、音乐同步缩放等效果时使用此技能。适用于 MP4 等视频格式,特别是舞蹈、健身、音乐类视频。

Manage Architecture Decision Records (ADRs) using git-adr, a CLI tool that stores ADRs in git notes instead of files. Execute commands (init, new, edit, list, show, search, sync, supersede, link, attach, stats, export, import), generate ADR content in any format (MADR, Nygard, Y-Statement, Alexandrian, Business Case, Planguage), and teach ADR best practices. Use when users ask about: ADRs, architecture decisions, decision records, git-adr commands, documenting technical decisions, or need help creating/managing ADRs in a git repository.

Builds and run project tests, delegating to sub-agents for fix recommendations upon failure.

Audit Flutter code for hardcoded strings, write clear user-friendly text following UX guidelines, and migrate strings to i18n files. Use when checking localization, finding hardcoded text, improving string clarity, writing error messages, button labels, or any user-facing text.

Implement in-app update prompts with version checking, force/soft updates, Android In-App Updates, and store redirects. Supports Supabase and Firebase Remote Config backends. Use when adding update dialogs, version management, or blocking outdated app versions.

Phone OTP authentication - country data, phone formatting, E.164 validation, rate limiting, retry patterns. Use when implementing phone verification flows. Supports Supabase and custom backends.

Local device authentication (biometric + device credentials). App unlock with configurable timeout, biometric change detection, optional app PIN, optional lock screen UI. Use when adding biometric login, app unlock, or secure action confirmation.

Network connectivity monitoring with global offline banner. Uses connectivity_plus with smart detection that considers actual API success. Use when adding offline detection, network monitoring, or connectivity-aware UI.

Deep linking with Universal Links (iOS) and App Links (Android). Platform setup, domain verification, GoRouter integration, path-based routing. Use when implementing deep links, URL handling, or app-to-web navigation.

Prepare Flutter apps for App Store and Play Store release. Use when setting up Android signing, iOS certificates, app icons, splash screens, or preparing for production deployment. Covers keystore creation, Xcode signing, store setup, and release builds.

Conventions and gotchas for writing portable, secure, and robust bash scripts. Use when creating automation scripts, CI workflows, or any bash tooling.

Validate project structure, dependencies, and configuration files. Use when setting up projects, checking project health, or troubleshooting configuration issues.

Displays progress dashboard showing phase completion, blocked tasks, and remaining work estimate. Provides at-a-glance view of implementation status. Run anytime to check progress.

Search and retrieve context from Airweave collections. Use when users ask about their data in connected apps (Slack, GitHub, Notion, Jira, Confluence, Google Drive, Salesforce, databases, etc.), need to find documents or information from their workspace, want answers based on their company data, or need you to check app data for context to complete a task.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Execute read-only SQL queries against multiple PostgreSQL databases. Use when: (1) querying PostgreSQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.

Comprehensive Typst copilot for semantic improvements, markdown conversion, compilation with visual debugging, and expert consultation. Use when working with Typst documents for (1) improving or refactoring Typst code, (2) converting Markdown to Typst, (3) compiling .typ files to PDF and debugging visual issues, (4) answering questions about Typst syntax, functions, or best practices, (5) creating or styling Typst documents, (6) troubleshooting Typst errors or layout problems.

Guide for managing terminal sessions with tmux via bash. Use when running long-lived processes, managing multiple concurrent terminal sessions, monitoring background tasks, or needing persistent shells that survive disconnection. Covers session/window/pane management, sending commands to background processes, and capturing output.

GistGetのWinGetパッケージリリースを支援。(1) 新バージョンのリリース、(2) WinGetマニフェスト作成・更新、(3) winget-pkgsへのPR作成。「WinGetにリリース」「winget-pkgsにPR」「マニフェスト作成」などのキーワードで使用。

Publish Doc-Smith generated documentation to online platforms. Use this skill when the user requests to publish, deploy, or release documentation.

Validate the structure and content integrity of Doc-Smith documentation. Use this skill to verify document structure YAML, check document content, and validate links and image paths. Can also be invoked by other doc-smith skills for validation.

Clear Doc-Smith site authorization and deployment configuration. Use this skill when the user requests to clear authorization, reset configuration, or remove deployment settings.

Generate images using AI. Use this skill to create technical diagrams, architecture diagrams, flowcharts, or update existing images. This is a general-purpose image generation capability for any scenario.

Automatically convert arXiv papers to well-structured Markdown documentation. Invoke with an arXiv ID to fetch materials (LaTeX source or PDF), convert to Markdown, and generate implementation-ready reference documentation with preserved mathematics and section structure.

View plans dashboard with progress tracking and timeline visualization. Use for kanban boards, plan status overview, phase progress, milestone tracking, project visibility.

Run a single-shot visual comparison between a Figma design node and an implementation URL (local app, Storybook iframe, or deployed page) using @uimatch/cli, then read the generated report to explain design fidelity and quality gate status. Use this skill when the user wants to check whether one specific UI component or page matches its Figma design or debug a particular mismatch.

Run a batch of visual comparisons defined in a uiMatch suite JSON file using @uimatch/cli, then read each report to summarize which components passed or failed their quality gates. Use this skill when the user wants to run many Figma-vs-implementation checks at once, such as CI-style validation for a component library or flow.

Native macOS/iOS app performance profiling via xctrace/Time Profiler and CLI-only analysis of Instruments traces. Use when asked to profile, attach, record, or analyze Instruments .trace files, find hotspots, or optimize native app performance without opening Instruments UI.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Initialize long-running agent projects with environment setup, feature list generation, and progress tracking. Use when starting a new implementation project or setting up an existing codebase for Claude-assisted development. Creates init.sh (dev server script), claude-progress.txt (work log), and docs/features.json (feature list with status tracking).

Capture a YouTube video transcript as raw material using `ytt`, storing it in the raw/ directory with minimal metadata for later distillation.

Commit staged changes only using Conventional Commit parameters (validates inputs).

Production-ready database schema patterns for AI applications including chat/conversation schemas, RAG document storage with pgvector, multi-tenant organization models, user management, and AI usage tracking. Use when building AI applications, creating database schemas, setting up chat systems, implementing RAG, designing multi-tenant databases, or when user mentions supabase schemas, chat database, RAG storage, pgvector, embeddings, conversation history, or AI application database.

Validate markdown documentation files for formatting issues, syntax errors, broken links, and quality standards. Use when checking .md files for compliance with documentation standards or after editing markdown files.

Generate web UI/UX icon assets (favicon.ico, apple-touch-icon, PWA icons incl. maskable) and optionally Unreal Engine packaging icons (Windows .ico, macOS .iconset/.icns, Linux .png) from a single source SVG/PNG; use when you need correct multi-size icon files, safe-area guidance, manifests/head tags, or automation.

Creates and configures Claude Code hooks for lifecycle automation. Use when implementing PreToolUse validation, PostToolUse formatting, PermissionRequest auto-approve, custom notifications, session management, or deterministic agent control.

Universal MCP client for connecting to any MCP server. Bundle scripts/mcp-client.py with your skill to enable dynamic tool discovery and execution without context bloat. Use when creating skills that need MCP server access.

Generate draw.io diagrams programmatically using Python. Creates flowcharts, architecture diagrams, tree structures, network diagrams, and more. Use when the user requests a .drawio file, diagram, flowchart, or visual documentation.

Claude Codeのイベント駆動型自動化とバリデーション用のhooksを作成します。tool呼び出し、ユーザーメッセージ、コミット前チェックなどのイベントに反応するhooksを実装します。自動化ワークフロー、バリデーション、イベント駆動処理が必要な場合に使用してください。

Guide for creating effective Claude Skills for the AgentStack Sovereign Platform. Use this skill when creating new skills, updating existing skills, or learning skill design patterns. Triggers on requests like "create a new skill", "build a skill for X", "skill design", "skill template", or "extend Claude's capabilities".

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you're designing a CLI spec (before implementation) or refactoring an existing CLI's surface area for consistency, composability, and discoverability.

Native macOS/iOS app performance profiling via xctrace/Time Profiler and CLI-only analysis of Instruments traces. Use when asked to profile, attach, record, or analyze Instruments .trace files, find hotspots, or optimize native app performance without opening Instruments UI.

List all agents in Beam AI workspace...

Shared resource library for HubSpot integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by hubspot-connect and individual HubSpot skills.

Complete Slack integration skill. Load when user wants to send messages, search Slack, manage channels, list users, upload files, add reactions, set reminders, or interact with Slack workspace.

Shared resource library for Slack integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by slack-connect and individual Slack skills.

Shared resource library for Beam AI integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by beam-connect and individual Beam skills.

Shared resource library for Notion integration skills. DO NOT load directly - this provides common references (setup, API docs, error handling, database schema) and scripts used by notion-connect, query-notion-db, import-skill-to-nexus, and export-skill-to-notion.

Create, validate, and work with Goose recipes - reusable AI agent configurations that package specific setups for tasks. Use when creating recipe.yaml/recipe.json files, configuring Goose extensions, parameters, retry logic, structured outputs, or debugging recipe validation errors.

Build multi-architecture container images in GitHub Actions. Matrix builds (public repos with native ARM64), QEMU emulation (private repos), or ARM64 larger runners (Team/Enterprise). Uses Podman rootless builds with push-by-digest pattern

Use when working with SQLite databases in DataPeeker analysis sessions - querying data, importing CSVs, exploring schemas, formatting output, or optimizing performance. Provides task-oriented guidance for effective SQLite CLI usage in data analysis workflows.

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you're designing a CLI spec (before implementation) or refactoring an existing CLI's surface area for consistency, composability, and discoverability.

Manages connections to Logseq graphs via HTTP API, CLI, or MCP Server. Auto-invokes when users mention connecting to Logseq, API tokens, graph paths, connection issues, or backend configuration. Handles backend detection, environment setup, and connectivity troubleshooting.

Expert in reading data from Logseq DB graphs via HTTP API or CLI. Auto-invokes when users want to fetch pages, blocks, or properties from Logseq, execute Datalog queries against their graph, search content, or retrieve backlinks and relationships. Provides the logseq-client library for operations.

Check WCAG color contrast ratios between two colors. Accepts any CSS color format (hex, rgb, rgba, hsl, hsla, named colors) and returns the contrast ratio along with WCAG compliance levels (AA/AAA for normal and large text).

Troubleshoot agent & tool failures in scheduling orchestration. Use when MCP tools fail, agent communication breaks, constraint engines error, or database operations timeout. Provides systematic incident response and root cause analysis.

Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files for Claude 4.5 models - applies documented Anthropic best practices systematically instead of inventing improvements

This skill should be used when working with the CRM PostgreSQL database for sales, contacts, companies, and opportunities. Use this skill when the user asks to insert, update, query, or analyze data in the CRM database (may be called crm or db), or when SQL queries need to be created for company_site, person, sales_opportunity, or event tables. This skill provides comprehensive schema knowledge and PostgreSQL-specific SQL examples tailored to the CRM data model.

This skill should be used when inserting files (images, PDFs, Excel files, documents) into the CRM database and linking them to companies, people, events, or sales opportunities. The skill handles base64 encoding, hash calculation, MIME type detection, and SQL insertion automatically through a Python script.

Mixpanel analytics tracking implementation + review skill for Django optimo_analytics: add events and audit for PII safety, schema design, and code quality.

dotnet CLI를 사용하여 .NET 솔루션/프로젝트를 빌드합니다. 컴파일, 종속성 복원 또는 아티팩트 빌드 작업 시 사용합니다.

[One-line description of what this skill solves]

Playwright를 사용하여 로컬 웹 애플리케이션과 상호작용하고 테스트하기 위한 툴킷입니다. 프런트엔드 기능 검증, UI 동작 디버깅, 브라우저 스크린샷 캡처 및 브라우저 로그 확인을 지원합니다.

dotnet CLI를 사용하여 .NET 테스트를 실행합니다. 유닛 테스트 실행, 코드 커버리지 리포트 생성 또는 벤치마크 수행 시 사용합니다.

Access configured sidecar providers (health, banking, government) via WebFetch.

Review skill files for best practices compliance (naming, description, structure, size). Use when checking SKILL.md quality or getting feedback before publishing. Static analysis only - does NOT execute the skill.

This skill should be used when working with Azure DevOps from the command line. Trigger when user mentions az devops, az repos, az pipelines, az boards, or asks about managing PRs, work items, pipelines, or repositories in Azure DevOps. Also trigger for questions about Azure DevOps CLI setup, authentication, or querying work items.

当用户用自然语言请求提交代码时触发（如「帮我提交」「commit 一下」「提交代码」）。自动应用 Git 提交规范，从分支名提取任务 ID，生成符合规范的提交信息。

Use this skill when you need to discover MCP tool parameters, understand naming conventions, or debug tool call errors

Use PROACTIVELY when setting up end-to-end testing, debugging UI issues, creating visual regression suites, or automating browser testing. Uses Playwright with LLM-powered visual analysis, screenshot capture, and fix recommendations. Zero-setup for React, Next.js, Vue, Node.js, and static sites. Not for unit testing, API-only testing, or mobile native apps.

Use PROACTIVELY when searching past Claude Code conversations, analyzing development patterns, or generating activity reports. Automatically processes conversation history from the project, enables RAG-powered semantic search, and generates insight reports with pattern detection. Provides optional dashboard for visualization. Not for real-time analysis or cross-project searches.

Use PROACTIVELY when validating Claude Code skills before sharing or public release. Automated testing framework using multiple isolation environments (git worktree, Docker containers, VMs) to catch environment-specific bugs, hidden dependencies, and cleanup issues. Includes production-ready test templates and risk-based mode auto-detection. Not for functional testing of skill logic or non-skill code.

Use PROACTIVELY when setting up OpenTelemetry monitoring for Claude Code usage tracking, cost analysis, or productivity metrics. Provides local PoC mode (full Docker stack with Grafana) and enterprise mode (centralized infrastructure). Configures telemetry collection, imports dashboards, and verifies data flow. Not for non-Claude telemetry or custom metric definitions.

Error handling with error classes, handlers, and interceptors. Use when handling API errors, displaying validation errors, configuring error handlers, or implementing error interceptors.

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output. Use when debugging applications, running interactive REPLs (Python, gdb, ipdb, psql, mysql, node), automating terminal workflows, or when user mentions tmux, debugging, or interactive shells.

Cross-platform audio feedback system for task completion and user prompts. Provides non-intrusive sound notifications to improve workflow awareness.

Use when building, improving, or reviewing command-line interfaces for better user experience - before implementing commands/output/errors, when users report confusion or frustration, or when CLI feels hard to use - provides UX principles, visual design techniques, and practical patterns for creating discoverable, delightful CLIs

Use when working with Buildkite CI - checking status, investigating failures, and reproducing issues locally. Provides workflows for monitoring builds, progressive failure investigation, and local reproduction strategies. Use when tempted to use GitHub tools instead of Buildkite-native tools, or when a Buildkite tool fails and you want to fall back to familiar alternatives.

Clean up Xcode disk space by removing derived data, old simulators, device support files, caches, and archives. Use when the user mentions running low on disk space, Xcode consuming too much storage, cleaning up after development, removing orphaned build artifacts, or freeing up space on Mac. Includes git worktree protection for derived data and confirmation prompts for simulators and devices.

项目重构工具，扫描代码库生成文档流，收纳测试脚本。

音频变声处理工具 - 使用 RVC AI 模型进行真实的声音转换

通用图片生成 Skill，支持多种 AI 模型（ModelScope、Gemini 等），可被其他 Skills 调用

音频关键字过滤工具 - 根据关键字配置自动识别并删除音频中的指定内容

Utility tool to create new git worktrees with proper setup for development environments. Automates creation, copying, symlinking, and ownership management for smooth developer onboarding or isolated task/feature work.

从多种来源安装Claude Code Skills的统一安装器。当用户请求安装skill、查找skill、列出已安装skills、查询支持哪些marketplace/来源、打包skill、编译skill、或提到skill名称/URL时触发。支持：(1)官方仓库 github.com/anthropics/skills，(2)第三方Marketplace（skillsmp.com、skillhub.club、smithery.ai等），(3)GitHub搜索，(4)直接Git/HTTP URL，(5)本地路径，(6)打包skill为.skill文件。