AI Skills Hub - Browse 180,000+ Agent Skills

Package and prepare skills for Claude Code marketplace distribution. Use when generating marketplace.json files, validating skill structure for distribution, preparing skills for public sharing, or setting up a new Claude Code marketplace. Triggers on requests to package skills, create marketplace configs, validate skills for distribution, or configure skill repositories for sharing.

Databricks Apps deployment, debugging, and configuration management. Use when working with Databricks Apps issues including deployment failures, app configuration (app.yaml), checking logs, granting permissions to SQL warehouses or Unity Catalog resources, troubleshooting app errors, or managing app state (start/stop). Triggered by mentions of SESSION_APP_NAME, app.yaml, deployment errors, or permission issues with Apps.

Extract actionable clues from a Cain’s Jawbone page and update per-page Notes + global indices without ever changing page body text.

当需要基于已暂存的 git 变更或粘贴的 diff 生成 Conventional Commits 提交信息时使用。

Manage offline reference material in the `extra/` directory. Use when needing external documentation, library source code, screenshots, PDFs, or API specs. ALWAYS check `extra/` before web searches. HALT and ask the human when required material is missing - do NOT fall back to WebFetch/WebSearch.

Data validation with Malli schemas in Clojure. Use when working with: (0) malli, (1) data validation or coercion, (2) defining schemas for maps, collections, or domain models, (3) API request/response validation, (4) form validation, (5) runtime type checking, or when the user mentions malli, schemas, validation, data contracts, or data integrity.

Reference for Guardrails library with Malli in Clojure. Use when working with `>defn`, `>defn-`, `>def`, `>fdef` macros, gspec syntax, or function validation. Triggers on guardrails imports, `com.fulcrologic.guardrails.malli`, function specs with `=>` operator, or questions about runtime validation in Clojure.

Property-based testing with clojure.test.check. Use when writing generative tests, creating custom generators, or debugging shrinking behavior. Triggers on test.check imports, prop/for-all, gen/* usage, or questions about property-based testing in Clojure.

Attempts ONE alternative fix for a bug, tests it empirically, and reports results. ALWAYS explores a DIFFERENT approach from existing PR fixes. Use when CI or an agent needs to try independent fix alternatives. Invoke with problem description, test command, target files, and optional hints.

Verifies UI tests catch the bug. Supports two modes - verify failure only (test creation) or full verification (test + fix validation).

Systematic troubleshooting for industrial motion control systems. Use for servo/stepper motor issues, positioning problems, homing failures, communication errors, EMI, vibration. Triggers (CN): 故障診斷、馬達問題、原點復歸失敗、定位不準、通訊錯誤、伺服異常. Triggers (EN): troubleshoot, motor issue, homing fail, position error, servo alarm. Coordinated by: project-coordinator.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Help user START tasks with activation support for ADHD. Use when user is stuck, overwhelmed, or asking what to do next. Auto-triggers on phrases like "I'm stuck", "can't get started", "overwhelmed", "what should I do", "next step", "where do I start", "jag fastnar", "kan inte börja", "vad ska jag göra", "nästa steg".

Role and project workload overview. Use when user wants to see their current workload, role balance, or status across roles/projects. Auto-triggers on phrases like "how am I doing", "workload", "what's on my plate", "role balance", "project status", "hur ligger jag till", "arbetsbelastning", "rollbalans".

Generate card and room images via ComfyUI with proper prompts. Use when creating art, generating images, missing card images, or working with visual assets. Triggers: "generate image", "card art", "missing image", "ComfyUI", "room image", "create artwork", "batch images".

Generates AI-powered YouTube thumbnails with face from reference photo, custom expressions, backgrounds, and text overlays. Automatically resizes to YouTube's recommended 1280x720 format. Use when creating thumbnails for YouTube videos or updating existing video thumbnails.

Automatically detect data loss scenarios and recover from shadow.db backup.

This skill should be used when debugging Vue Flow canvas issues involving nested nodes, parent-child relationships, position coordinate systems, and containment detection. Triggers on nested group problems, section nodes jumping, parent-child synchronization bugs, position persistence issues, and coordinate transformation errors in Vue Flow implementations.

Shared utilities for invoking Fractary CLI from work plugin skills

Analyze and prioritize MultiQC module requests through automated triage. Calculate priority scores, assign labels, update project boards, and provide actionable feedback to contributors.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". 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.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Implement features using strict Test-Driven Development in isolated Git worktree environments. Use this skill when transitioning from PLANNING to implementation, building features, fixing bugs, or refactoring code with TDD practices.

Linear submission for Keboola PRD. Creates Project + Issue with PRD in description. Used by keboola-prd-coach agent.

Set up and configure a Dify-Creator project for the first time. Use during initial setup when configuring Dify credentials, environment variables, and Docker. Handles credential configuration, connection testing, and build setup.

Add interaction states like hover, focus, disabled, active, error to existing uxscii components when user wants to expand, enhance, or add states to components

Expert-level MODX Revolution CMS development, templating, and content management. Use this skill when building MODX websites, creating templates/chunks/snippets, configuring extras (pdoTools, MIGX, ClientConfig, SEO Suite, Image+, FormIt), writing MODX tag syntax, implementing schema markup, or troubleshooting MODX issues. Triggers include "MODX", "pdoResources", "pdoMenu", "MIGX", "ClientConfig", "FormIt", "Image+", "ImagePlus", "chunks", "snippets", "TVs", "template variables", or any MODX CMS development task.

This skill activates when the user asks about "code quality", "complexity", "maintainability", "code smells", "refactoring", "clean code", "technical debt metrics", "cyclomatic complexity", "dead code", "duplicate code", "TODO comments", or needs to measure and improve code quality.

Use this skill when the user asks about text-to-speech setup, voice cloning configuration, TTS troubleshooting, or wants to understand how the Chatterbox TTS integration works. Trigger phrases: "setup TTS", "configure voice", "TTS not working", "chatterbox", "voice cloning", "speak command", "notification voice", "MPS error", "float64 error"

Specialized workflow for company legalizations (ABERTURA, ALTERACAO, BAIXA) using Trello. Use when user mentions legalizacao, company opening, alteration, closure, or Brazilian company registration processes.

This skill should be used when the user asks to "create issue", "search issues", "update ticket", "check notifications", mentions "Backlog", "バックログ", "課題", "チケット", discusses project management with Nulab Backlog, or needs to interact with Backlog API for issue tracking.

Router skill for Nextflow to Galaxy conversions - directs to appropriate sub-skill

Convert a single Nextflow process to a Galaxy tool XML

Convert a complete Nextflow pipeline to Galaxy

Convert a Nextflow subworkflow to a Galaxy workflow

This skill should be used when creating Galaxy Hub news posts, writing content for galaxyproject.org/news, or converting content to Galaxy Hub markdown format.

Guide for creating effective skills. Use when creating new skills or updating existing ones to extend capabilities with specialized knowledge, workflows, or tool integrations.

Automate NotebookLM notebook creation from YouTube videos. Given a YouTube video URL, extract information about people featured in the video, research them online, create a new NotebookLM notebook with the video and research as sources, and generate an audio overview. Uses screenshot-first automation to reliably target UI elements.

Python 프로젝트 실행, 테스트, 문법 검사, 임포트 검증을 위한 스킬. `scripts\python-runner.bat`를 사용합니다.

Use when the user wants to run Langfuse experiments on datasets, apply LLM-as-judge prompts, compare runs, analyze failures, or evaluate prompt/model changes.

Use this skill when users want to add Langfuse tracing to their code, set up observability, instrument LLM calls, or add scoring to their pipelines. Helps users correctly structure traces, spans, and generations.

Use when the user needs to instrument code with Langfuse tracing, set up observability, add scoring, or debug Langfuse SDK configuration in a Python pipeline.

Use this skill when creating, scaffolding, or developing cli4ai CLI tool packages. Invoke when the user asks to create a new cli4ai tool, build a CLI package, add commands to a package, set up package structure, or work with cli4ai.json manifests. Also use when debugging package issues, understanding @cli4ai/lib usage, or converting scripts into cli4ai packages.

Build and maintain Knowledge Graphs from webpages using WordLift APIs. Use when importing pages from sitemaps via WordLift Sitemap Import API, creating product catalogs with GS1 Digital Link identifiers (GTIN-based), generating slug-based entity IDs for organizations/people/webpages, creating JSON-LD markup programmatically, or performing daily sync workflows with batch operations and PATCH updates. Handles entity lifecycle management with proper JSON-LD structure.

Automate browser testing using Playwright MCP tools. Use this skill when: (1) Testing web application flows interactively via browser automation (2) Exploratory testing of UI features with live browser interaction (3) Verifying tournament management flows (create tournament, add players, manage competitions, queue matches, score matches) (4) Testing authentication flows with magic links (5) Debugging UI issues by navigating and inspecting the live application (6) Testing external scoring interfaces with PIN-based access

List, search, and filter transaction records from the financial database. Trigger this skill whenever the user asks questions like “what is <merchant> categorized as?”, “show me transactions for <merchant/category/date>”, or otherwise wants specific rows from the ledger. Does NOT analyze or summarize - just retrieves raw transaction data.

Analyze spending patterns, trends, and anomalies to generate insights and reports. Use when user asks how much they're spending, wants spending breakdowns/summaries, needs to find subscriptions, analyze trends over time, or investigate unusual charges. Provides insights and aggregated analysis, not raw transaction lists.

Plan TfL journeys from start/end/time, resolve locations (prefer postcodes), and warn about disruptions; suggest alternatives when disrupted.

Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.

Ensures commits follow conventional commits specification with proper pre-commit handling and semantic versioning alignment. Use when staging/committing code changes.

Manages file-based todo tracking in the todos/ directory. Use for code review feedback, technical debt, feature requests, and work items with YAML frontmatter.

Guide for creating effective skills. Use when users want to create or update a skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Guidelines for creating Solution Blueprints (UX Flows, ROI, Risk Registers) for BRD preparation.

Organize files in a specified macOS folder into a "分类结果" directory with subfolders 表格/代码/视频/图片/文档/压缩包/安装包/演示文稿/其他 based on file extensions. Unclassified files are moved to "其他" folder by default. Default non-recursive. Always run a dry-run preview first, then apply only after user confirmation. Create missing folders, avoid overwriting by suffixing, write a CSV log, and support undo. Use when the user asks to 整理/归档/分类整理 a folder like Downloads/Desktop.

Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.

Download YouTube videos (MP4) or audio (MP3) using yt-dlp with automatic quality selection and format conversion. Use when you need to download videos for offline viewing, extract audio, or archive YouTube content in the files workspace.

Use when creating Git commits.

Use when creating, editing, evaluating, testing, or verifying ANY skill or skill-related file (SKILL.md, skill resources, skill scripts, or skill assets). If you're asked to evaluate or test a skill's effectiveness, use this skill.

Quarkusアプリケーションのエラーを分析し解決策を提供する。CDI/DI、データベース、REST/HTTP、Nativeビルド、Kotlin固有のエラーをカバー。Quarkusエラーのトラブルシューティング、デバッグ、ビルド問題の解決時に使用。io.quarkus、jakarta.*を含むスタックトレースが対象。

Microsoft Graph SDK + M365 Copilot API access. Use when the user needs to interact with Microsoft 365 services: (1) Email - read, send, search, organize messages, (2) Calendar - events, meetings, invitations, (3) Tasks - Microsoft To Do lists and tasks, (4) Files - OneDrive operations, (5) OneNote - notebooks, sections, pages, (6) Contacts - Outlook contacts, (7) Search - M365 content search, (8) Copilot Retrieval - search across SharePoint/OneDrive using Copilot API. Provides direct SDK access for ANY Graph API operation with full control over requests.

Deterministic calculation of specification completeness scores.

Set up and manage synchronization between GitHub repositories and Google Apps Script projects using clasp and GitHub Actions. Use when: (1) Creating a new Apps Script project with GitHub version control, (2) Setting up CI/CD for existing Apps Script projects, (3) Configuring stable deployment URLs that persist across updates, (4) Troubleshooting clasp authentication or deployment issues, (5) Managing Apps Script deployments from the command line.

Prepare complete PR content ready for creation via reedom-gh:pr-maker agent.

Manages E2B sandbox operations including code execution, debugging, and template building. Triggers when working/asking about sandboxes, code interpreters, or secure code execution environments.

Evaluates document relevance to queries using binary scoring (yes/no) with reasoning. Use when filtering retrieved documents, determining relevance for answer generation, or when the user mentions grading, filtering, or document quality.

Python-only LangGraph skill for building stateful agents and workflows with memory, human-in-the-loop, streaming, persistence, time travel, and deployment. Use when orchestrating agents in Python with LangGraph/LangChain/LangSmith; includes API reference, scenarios, and troubleshooting.

Design principle: progressive disclosure and concision. Keep core workflows and navigation here; load detailed samples and long docs from references and runnable scripts only when needed.

Build, configure, run, and test the Slurm Workload Manager from this repository. Trigger when asked to compile Slurm, generate slurm.conf/slurmdbd.conf, start daemons locally, submit or debug jobs, run the test suite, or answer how to use Slurm commands and plugins.

Evidence-first Orchard Core theming skill for shapes, alternates, placement, Razor/Liquid templates, content model access, assets/resources, and recipes. Use for theme adjustments, shape overrides, template discovery, content item/field access, placement.json rules, and recipe authoring in Orchard Core projects.

达梦数据库(DM8)工具集，用于连接数据库实例、列出所有表、查看表结构、执行 SQL 查询等操作。当需要操作达梦数据库、查询数据、分析表结构时使用此技能。支持通过命令行参数指定 host、port、user、password、database、schema 等连接信息，可代替 dm8 mcp 服务使用。支持 Windows、macOS 和 Linux 平台。

SQL Server (MSSQL) 数据库工具集，用于连接数据库实例、列出所有表、查看表结构、执行 SQL 查询等操作。当需要操作 SQL Server 数据库、查询数据、分析表结构时使用此技能。支持通过命令行参数指定 server、port、user、password、database 等连接信息，可代替 mssql mcp 服务使用。支持 Windows、macOS 和 Linux 平台。

在代码提交前自动执行多维度质量检查，确保提交代码符合项目标准。**核心原则**：检查不通过则阻断提交，避免问题代码进入版本控制。

清理项目中的临时文件、缓存和构建产物，释放磁盘空间。**核心原则**：预览模式确认后执行，避免误删重要文件。

Complete HarmonyOS app development guide with ArkTS, Stage model, and ArkUI. Use when: - Creating new HarmonyOS projects ("Set up a new HarmonyOS project") - Developing UI with ArkUI components and state management - Integrating system capabilities (window, file, background tasks) - Adding media services (audio, video, camera) - Deploying to multiple devices with responsive layouts - Building cross-device collaboration features Use with harmonyos-design-guidelines for complete design+development workflow.

Create AI-executable TASK/FIX GitHub issue bodies (and optionally create/link them as sub-issues) for SUM Platform work orders. Use when converting a WO/idea/report into a deterministic task ticket that an agent can execute without guessing, and when you want a “wording approval → create issue” workflow.

Infrastructure management using the device profile. Servers are stored in profile.servers[], deployments reference .env.local files via profile.deployments{}. Use when: managing server inventory, provisioning infrastructure, deploying to cloud providers.

Deploys infrastructure on Oracle Cloud Infrastructure (OCI) with ARM64 instances (Always Free tier eligible). Handles compartments, VCNs, subnets, security lists, and compute instances. Use when: setting up Oracle Cloud infrastructure, deploying ARM64 instances, troubleshooting OUT_OF_HOST_CAPACITY errors, optimizing for Always Free tier. Keywords: oracle cloud, OCI, ARM64, VM.Standard.A1.Flex, Always Free tier, OUT_OF_HOST_CAPACITY, oci compartment, oci vcn

Windows system administration with PowerShell 7.x. Profile-aware - reads your preferences for package managers (scoop vs winget vs chocolatey), paths, and installed tools. Use when: Windows-specific admin tasks, PowerShell automation, PATH configuration, environment variables, package installation, .wslconfig editing, bash-to-PowerShell translation. NOT for: WSL operations (use admin-wsl), macOS/Linux (use admin-unix). Keywords: powershell, pwsh, windows, winget, scoop, chocolatey, registry, PATH, environment variable, .wslconfig, windows terminal, Get-, Set-, New-, Remove-

Installs and manages Coolify, an open-source self-hosted PaaS for deploying applications with Docker. Provides a Heroku-like experience on your own infrastructure. Use when: installing Coolify, deploying Docker apps, setting up a self-hosted PaaS, or configuring the Traefik proxy. Keywords: coolify, self-hosted paas, docker deployment, traefik proxy, open source heroku

Testing patterns for PHPUnit and Playwright E2E tests. Use when writing tests, debugging test failures, setting up test coverage, or implementing test patterns for ActivityPub features.

Implements complete voice conversation features using OpenAI Whisper (STT), GPT models, and TTS with Vercel AI SDK for Expo + Convex apps. Use when adding voice recording, transcription, AI responses, or text-to-speech to any React Native application.

Deploy AI agents to Amazon Bedrock AgentCore using Strands Agents framework. Use when users want to (1) deploy an agent to AgentCore, (2) create a serverless AI agent on AWS, (3) build and deploy Strands agents to production, (4) set up AgentCore runtime for AI agents. Supports weather agents, chatbots, and any HTTP-based agent deployment.

Manage personal todo items with create, read, update, delete operations. Use when the user wants to manage their personal tasks, such as adding new todos ("add a todo to write documentation"), viewing their todo list ("show my todos"), marking tasks as complete ("complete todo 1"), updating task descriptions, deleting tasks, or clearing completed items. Stores todos locally in JSON format.

Test and verify local web applications using Playwright by interacting with pages, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Use this skill when testing frontend functionality, debugging web apps, verifying UI behavior, or automating browser interactions.

Background HTTP server rendering markdown files with calm, book-like reading experience.

Automates `googleai_dart` updates when the Google AI OpenAPI specification changes.

基于项目名生成稳定唯一的端口号，并自动更新项目配置。当用户需要为项目设置端口、启动开发服务器、解决端口冲突或初始化新项目配置时使用此 skill。

This skill should be used when the user asks "how do I configure Herald?", "how do I set up ElevenLabs?", "configure TTS", "change herald settings", "set up text-to-speech", "herald preferences", "elevenlabs api key", "herald not working", or needs help with Herald notification configuration, TTS providers, or troubleshooting.

Bags is a Solana token launchpad with programmable fee sharing. The API enables token creation, fee distribution among up to 100 wallets, partner key economics for platform builders, and trading.

Generate AGENTS.md files with progressive context loading for any folder. Analyzes folder contents, extracts context, and creates vendor-neutral context files following AGENTS.md best practices.

Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.

Official brand guidelines for Life360, including color palettes, typography, logo assets, UI layout principles, and photography style. Use this skill when designing emails, creating web content, or ensuring brand compliance for Life360 materials.

Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via Serena Memory, and monitors progress

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.