AI Skills Hub - Browse 180,000+ Agent Skills

Implement agent evaluation and safety gates using MLflow 3.x. Use for creating LLM-as-Judge scorers, evaluation datasets, quality gates, tracing, and continuous evaluation. Triggers on "evaluate agent", "MLflow scorer", "LLM judge", "safety evaluation", "quality gate", "agent testing", "hallucination detection", or when implementing spec/010-agent-evaluation.md requirements.

全方位的文件建立、編輯和分析功能，支援追蹤修訂、註解、格式保留和文字擷取。當 Claude 需要處理專業文件（.docx 檔案）時使用，包括：(1) 建立新文件、(2) 修改或編輯內容、(3) 處理追蹤修訂、(4) 新增註解，或任何其他文件相關任務

建立有效技能的指南。當使用者想要建立新技能（或更新現有技能）以透過專業知識、工作流程或工具整合來擴展 Claude 的能力時，應使用此技能。

Analyse rhétorique et épistémologique d'articles, discours et textes argumentatifs. Utiliser ce skill quand l'utilisateur demande d'analyser la qualité argumentative d'un texte, d'identifier des sophismes ou biais, d'évaluer la fiabilité des sources citées, de déconstruire la logique d'un raisonnement, ou de produire une réécriture critique structurée d'un document.

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 you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

This skill should be used when the user wants to open or preview a file that already exists on disk using the operating system's default application. Triggers on requests like "open this file", "show me the PDF", "preview the image", "view the document", or "display the spreadsheet". Works with all file types including PDFs, images, documents, emails, and spreadsheets.

Analyzes ICU clinical data using the Common Longitudinal ICU data Format (CLIF) and clifpy Python library. Loads and filters CLIF tables (vitals, labs, medications, respiratory support, microbiology) by hospitalization_id and category columns. Computes clinical scores including SOFA, Charlson Comorbidity Index (CCI), and Elixhauser. Creates wide datasets and performs data transformations. Use when working with ICU data, CLIF format, clifpy, clinical scoring, ventilator data, sepsis research, or intensive care analytics.

Search Mouser Electronics for component availability, pricing, datasheets, and lead times. Use when designing hardware, sourcing components, checking inventory, comparing prices, or finding datasheets for electronic parts.

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

提示词工程专家技能，帮助用户学习和应用 Claude 提示词最佳实践。当用户需要优化提示词、学习提示词技巧、或提高与 Claude 交互质量时使用此技能。适用场景包括：提示词优化、提示词分析、学习提示词技术、应用最佳实践。

文件归档与组织技能，基于 Johnny.Decimal 方法论。当用户需要组织文件、创建归档系统、整理数字资产时使用此技能。 适用场景包括：(1) 规划和创建文件组织结构，(2) 设计区域(Areas)和类别(Categories)，(3) 建立索引系统(JDex)， (4) 迁移现有文件到结构化系统，(5) 解答文件组织相关概念和最佳实践。

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Resize images using ImageMagick when they are too large to view or process. Use this skill when you encounter an image file that exceeds token limits, is too large to read, or when you need to create a smaller version of an image for viewing.

Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.

Search documents in Paperless-ngx via REST API. Full-text search, tag/correspondent filtering, and direct links to documents.

Analyze and optimize Xcode asset catalogs - find unused assets, missing resolutions, compress images

Parse and analyze macOS crash logs to identify crash causes and debugging information

Debug Kubernetes issues using kubectl, logs, events, and resource inspection. Use on 'pod not starting', 'crash loop', 'OOMKilled', 'debug k8s', 'why is pod failing'.

Git operations including commits, branches, worktrees, and safety protocols. Use on 'git', 'commit', 'branch', 'worktree', 'rebase', 'merge'.

Manage Google Docs with full document operations including reading content, inserting/appending text, find and replace, text formatting (bold, italic, underline), page breaks, document structure, and document creation. Use for document content operations, text insertion/replacement, formatting, structured document generation, and content extraction. This skill should be used for ALL Google Docs-related requests.

Manage Google Contacts with full CRUD operations via Ruby scripts. This skill should be used when searching, viewing, creating, updating, or deleting contacts in Google Contacts. Supports contact lookup, batch operations, and comprehensive contact field management including names, emails, phones, addresses, birthdays, organizations, and notes.

Browser automation and E2E testing via local Playwright Docker container

Manage Google Sheets with comprehensive spreadsheet operations including reading/writing cell values, formulas, formatting, sheet management, and batch operations. Use for spreadsheet data operations, cell ranges, formulas, formatting, batch updates, and data analysis workflows. Shares OAuth token with email, calendar, contacts, drive, and docs skills.

Create production-ready prompts using systematic methodology. Use when: (1) Building new prompts for Claude, (2) Improving existing prompts, (3) Creating prompt templates, (4) Designing system prompts for agents.

Generate production-quality SVG icons with COLOR support using VTracer vectorization. Converts raster images to clean, colorful SVG paths.

Review branch changes for correctness, regressions, architecture quality, and project-rule compliance. Use when asked to review a PR/branch/diff, assess merge readiness, or return an APPROVE/REJECT verdict with prioritized findings.

Проверка лимитов затрат для Telegram пользователей

Use the director-developer CLI to introspect the Director engine for Spec-Driven Development. Run this tool to get accurate, ground-truth information about available types, APIs, and capabilities.

Create, validate, and package Claude skills - modular packages that extend Claude's capabilities through specialized knowledge, workflows, and tool integrations.

Create and edit workout routines in Hevy fitness app via API. User-invocable with /hevy. Use when: User wants to create/edit Hevy routines, convert training programs (text/PDF/image) to Hevy format, or work with the Hevy API. Triggers: "/hevy", "hevy routine", "add to hevy", "gym routine", "gym program", "lifting program", "training plan", "PPL", "push pull legs", "5x5", "531", "GZCLP", "nSuns", "import workout", "sync to hevy", "weightlifting"

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Factory 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 | Sử dụng khi: tạo Word, chỉnh sửa docx, tài liệu văn bản, track changes

Build PRISMA 2020-compliant systematic literature review systems with RAG-powered analysis in VS Code. Use when researcher needs automated paper retrieval (Semantic Scholar, OpenAlex, arXiv), AI-assisted PRISMA screening (50% or 90% threshold), vector database creation (ChromaDB), or research conversation interface. Supports knowledge_repository (comprehensive, 15K+ papers, teaching/exploration) and systematic_review (publication-quality, 50-300 papers, meta-analysis) modes. Conversation-first workflow with 7 stages.

Semantic code search with call graph analysis. Use when asking "where is X?", "what calls this function?", exploring unfamiliar code, or analyzing dependencies. Finds code by natural language with callers/callees/imports relationships.

Code search and intelligence using CIDX. Use when searching codebases, finding implementations, tracing call graphs, analyzing dependencies, or searching git history. Preferred over grep/find for all code exploration.

This skill should be used when creating new RFC 2119-conformant specification documents, iterating on specification drafts, choosing keywords (MUST/SHOULD/MAY/MUST NOT) while writing, structuring sections, or progressively refining specifications.

Generate single-file TypeScript MCPs for any MCP client. Use when users request creating an MCP, building an MCP server, or implementing Model Context Protocol tools. Generates AI-friendly, production-ready code with security best practices, auto-installing dependencies, and fork-first design. Triggers on phrases like "create a GitHub MCP", "build an MCP for file operations", or "make an MCP that does X".

Quick capture for thoughts, observations, or ideas during research sessions. Use when the user types /note or wants to capture a quick thought without context-switching. Logs timestamped notes to activity.md. Supports both explicit /note command and natural language like "make a note" or "jot down".

Guide for debugging ShareGo session issues. Use when troubleshooting connection failures, handshake problems, state machine issues, or data transfer errors.

Scribe app development guide for Wails v3 + Vue 3 desktop app. Use when building, debugging, or modifying the Scribe plugin manager.

Implementation orchestrator for stages 2-6 (Foundation through Validation)

Auto-detection and interaction with Flipper Zero hardware. Use when the user needs to find a connected Flipper, retrieve device information, or perform serial CLI operations.

本地生成 Telegram 语音消息，支持自动清洗、分段与临时文件管理。

Creates well-structured git commits by analyzing changes, drafting messages, and executing commits. Use when the user asks to commit changes, save work, create a commit, or mentions committing their code.

Multi-engine text-to-speech skill. Supports Qwen3-TTS local voice cloning, VoiceCraft online TTS, and OpenAI TTS.

Propagates skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running skill-propagator/assets/propagate.sh (including --dry-run/--scope).

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Use when explicitly optimizing Cairo arithmetic with bounded integers to eliminate overflow checks and reduce steps

No description available

Real-time serial log monitoring for ESP32 and microcontrollers. Capture device output to a file and monitor logs in real-time. Use when debugging embedded devices, investigating crashes, or monitoring device behavior.

Discover and install third-party agent skills from the open skills ecosystem (skills.sh). This skill should be used when users want to find, install, update, or manage external skills for Claude Code or other AI agents, or when they mention skills.sh, npx skills, or want to extend their agent with community skills.

Browser automation toolkit using Playwright. Supports interacting with web applications, form filling, capturing screenshots, viewing browser logs, and running automated tests. Use when automating browser tasks, testing web UI, or scraping web pages.

Write testable acceptance criteria in Given/When/Then (Gherkin) format for stories, epics, and features. Use when defining acceptance criteria, writing test scenarios, or when user mentions "acceptance criteria", "Given/When/Then", "Gherkin", "test scenarios", or "AC".

Creates new AI agent skills following the Agent Skills spec. Trigger: When user asks to create a new skill, add agent instructions, or document patterns for AI.

Propagates skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running .agent/skills/skill-propagator/assets/propagate.sh (including --dry-run/--scope).

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Parse and execute incoming handoffs from Cursor following the normalized handoff schema with mixed-capability phases (analysis and write-capable)

Solana Tokenized Vault Standard (ERC-4626 port) development playbook. Covers Anchor program development, vault mechanics, share/asset accounting, inflation attack protection, and testing with LiteSVM/Mollusk/Trident.

This skill should be used after running tests when failures occur. It ensures test failures are properly diagnosed through instrumentation and logging until the root cause is found and fixed. The skill treats all test failures as real bugs that must be resolved, never skipped.

Laravel Sail Docker development environment patterns.

Pragmatic coding standards - concise, direct, no over-engineering, no unnecessary comments

Automatically scans GOAL.md for unchecked items, provides completion status summary, and enables coordinator to mark items as complete

Use when working on the documentation website, Docusaurus config, docs content, theme customization, or versioning. Covers the website/ directory.

You MUST use this before writing or debugging E2E tests. Covers test independence, test-only API endpoints, Playwright configuration, and common pitfalls like shared database race conditions and toast assertions.

主工作流编排技能，协调各子 Agent 完成从素材研究到文章输出的完整流程。

카카오톡 연동 전제조건 체크. "카톡 설정", "권한 확인", "kakao setup", "KakaoTalk setup" 시 사용.

카카오톡 메시지 전송. "카톡 보내줘", "메시지 전송", "kakao send", "KakaoTalk send message" 시 사용.

카카오톡 연결 상태 확인. "카톡 상태", "연결 확인", "kakao status", "KakaoTalk connection" 시 사용.

Ultimate RabbitMQ expertise skill for production-grade message broker architecture, implementation, and operations. Top 0.01% knowledge covering: (1) Advanced messaging patterns - Dead Letter Exchanges, Delayed Messages, Priority Queues, Consistent Hash Exchange, Sharding, (2) High Availability - Clustering, Quorum Queues, Stream Queues, Federation, Shovel, (3) Performance Engineering - prefetch tuning, connection pooling, batch publishing, memory optimization, flow control, (4) Security - TLS/mTLS, OAuth2, LDAP, certificate rotation, (5) Monitoring - Prometheus metrics, custom health checks, anomaly detection, (6) Troubleshooting - memory alarms, network partitions, queue backlogs, consumer starvation, (7) Multi-tenancy - vhost design, resource limits, isolation patterns, (8) Event-driven architectures - CQRS, Event Sourcing, Saga patterns with RabbitMQ. Use when: building messaging systems, debugging RabbitMQ issues, optimizing performance, designing HA architectures, implementing advanced patterns, production hardening, capacity planning, migration strategies.

Senior/Lead Developer Bun.js + Docker dengan pengalaman 20 tahun. Skill ini digunakan ketika: (1) Membuat project Bun.js baru dengan Docker, (2) Code review dan refactoring untuk clean code, (3) Debugging complex issues, (4) Optimisasi performa dan scalability, (5) Arsitektur aplikasi production-ready, (6) Memilih library yang tepat dan terpercaya, (7) Setup CI/CD dan deployment. Trigger keywords: "bun", "bunjs", "bun.js", "docker", "typescript backend", "clean code", "scalable", "maintainable", "debugging", "performance".

Persistent memory graph skill using the MCP Memory server

Creates high-quality pull requests with mandatory self-critique before submission. Activate this skill whenever you are asked to create, open, submit, or push a pull request. Also activate when the user says "make a PR", "open a PR", "submit this for review", "push and create a PR", "I'm done, create the PR", or any variation of requesting a pull request. Always activate before running `gh pr create`.

Automated UI audit system for discovering routes, creating exploration tasks, and generating Playwright tests. Supports multiple user types, auth detection, and ticket-driven workflow with Vibe-Kanban integration.

AutoChip project configuration structure and utilities for managing IC module metadata, including schema validation and extraction tools.

Reduce Claude Code token burn with proactive compacting, task-scoped sessions, checkpoint files, tiered docs, and relevance-based context pruning. Use when a user explicitly asks to reduce context usage/cost, run token benchmarks, or optimize CLAUDE.md. Do not use to expand product scope or skip correctness checks.

Creates timestamped configuration files for sports poetry multi-agent workflows. Invoked when users request to 'create config', 'set up configuration', 'configure sports poetry', provide sports lists for generation, or need help understanding configuration options. Validates sports count (3-5), checks API keys for LLM mode, and generates both JSON config and reproducible generator script (project)

Verify GCP Composer Airflow environments have no running DAGs before deployment to prevent conflicts

Run BitBot's iterative test workflow (implement → test → fix → commit → push). Use PROACTIVELY during development to ensure quality before committing.

Create professional presentations, documents, webpages, and social posts using Gamma's AI-powered design API. Use when the user asks to create, generate, or build any type of presentation, slide deck, document, webpage, or social media post. Supports AI-generated content from prompts, condensing existing text, or preserving exact content with beautiful design.

Complete asset management feature for Polkadot dApps using the Assets pallet. Use when user needs fungible token/asset functionality including creating custom tokens, minting tokens to accounts, transferring tokens between accounts, destroying tokens, viewing portfolios, or managing token metadata. Generates production-ready code (~2,200 lines across 15 files) with full lifecycle support (create→mint→transfer→destroy), real-time fee estimation, transaction tracking, and user-friendly error messages. Works with template infrastructure (WalletContext, ConnectionContext, TransactionContext, balance utilities, shared components). Load when user mentions assets, tokens, fungible tokens, token creation, minting, portfolio, or asset pallet.

Consolidate learnings from action logs into project docs and skills. Use when user asks to "consolidate", "compile learnings", "summarize sessions", or update project knowledge from .claude/action-log.jsonl.

Control Unity Editor via OpenClaw Unity Plugin. Use for Unity game development tasks including scene management, GameObject/Component manipulation, debugging, input simulation, and Play mode control. Triggers on Unity-related requests like inspecting scenes, creating objects, taking screenshots, testing gameplay, or controlling the Editor.

Google Cloud Platform CLI (gcloud, gcloud storage, bq). Use when: managing GCP resources, deploying to Cloud Run/Cloud Functions/GKE/App Engine, working with Cloud Storage, BigQuery, IAM, Compute Engine, Cloud SQL, Pub/Sub, Secret Manager, Artifact Registry, Cloud Build, Cloud Scheduler, Cloud Tasks, Vertex AI, VPC/networking, DNS, logging/monitoring, or any GCP service. Also covers: authentication, project/config management, CI/CD integration, serverless deployments, container registry, docker push to GCP, managing secrets, Workload Identity Federation, and infrastructure automation.

Extraer y reimportar codigo VBA de archivos Excel .xlsm en Windows usando Python (pywin32/oletools) o VBScript. Usar para exportar modulos .bas, refactorizar en VS Code y volver a importar al XLSM.

Analyze any Intelligems A/B test and get a plain-English verdict — should you roll it out, keep running, or kill it? Includes risk assessment, segment nuance, and profit impact.

Write clear user stories with testable acceptance criteria. Use for requirements definition and feature scoping.

Search the web using multiple search engines simultaneously (Bing, Yahoo, Startpage, Aol, Ask) via async-search-scraper, iterating through result pages.

Robyn backend scaffolding and architecture guidance for projects using robyn-config. Use when creating or evolving Robyn services, choosing DDD vs MVC, choosing SQLAlchemy vs Tortoise, adding new entities/routes/repositories with robyn-config add, auditing Robyn backend quality, or authoring and improving skill markdown for Robyn engineering workflows.

Use when querying the bknd source repository with btca CLI. Covers setup, configuration, and query patterns for learning bknd internals including data module, authentication, media handling, and adapter configuration.

Traffic Light Protocol (TLP) file access control. This skill should be used when the user asks about TLP levels (RED, AMBER, GREEN, CLEAR), file classification, reading protected files, safe-read, blind-metadata, redacted reading, inline redaction markers, secret detection, .tlp configuration, file access policies, or frontmatter TLP overrides.

Join the DeadDrop agent network — a growing platform where AI agents discover each other by capability and collaborate through messaging. Register to make your unique skills available to every other agent on the network, find agents that complement what you do, and exchange messages. Every agent that joins makes the network more valuable for all. Use this skill to register, search for agents, send and receive messages, or manage your profile at agentdeaddrop.com.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Generates MSTest tests in C#. Microsoft's built-in testing framework for .NET. Use when user mentions "MSTest", "[TestMethod]", "[TestClass]", "Assert.AreEqual". Triggers on: "MSTest", "[TestMethod]", "[TestClass]", "Microsoft test framework".

Generates Gauge test specifications in Markdown with step implementations in Java, Python, JS, or Ruby. ThoughtWorks' test automation framework. Use when user mentions "Gauge", "spec file", "## Scenario", "step implementation". Triggers on: "Gauge", "Gauge spec", "Gauge framework", "ThoughtWorks test".

Generates Robot Framework tests in keyword-driven syntax with Python. Supports SeleniumLibrary, RequestsLibrary, and custom keywords. Use when user mentions "Robot Framework", "*** Test Cases ***", "SeleniumLibrary", ".robot file". Triggers on: "Robot Framework", "*** Test Cases ***", ".robot", "SeleniumLibrary", "keyword-driven test".

Generates Geb browser automation tests in Groovy with Spock integration. jQuery-like content DSL and page object pattern. Use when user mentions "Geb", "Groovy test", "GebSpec", "Browser.drive". Triggers on: "Geb", "GebSpec", "Groovy browser test", "Browser.drive".

Generates TestNG tests in Java with groups, data providers, parallel execution, XML suite configuration, and listeners. Use when user mentions "TestNG", "@DataProvider", "testng.xml", "groups". Triggers on: "TestNG", "@DataProvider", "testng.xml", "TestNG suite", "parallel tests Java".

Interface para servidores MCP (Model Context Protocol) via CLI. Use quando precisar interagir com tools externas, APIs ou fontes de dados via servidores MCP, listar servidores/tools MCP disponiveis ou chamar tools MCP pela linha de comando.

Crie aplicacoes agenticas com GitHub Copilot SDK. Use ao embutir agentes de IA em apps, criar tools customizadas, implementar respostas em streaming, gerenciar sessoes, conectar a servidores MCP ou criar agentes customizados. Dispara em Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

Automacao de navegador, debugging e analise de performance em nivel especialista usando Chrome DevTools MCP. Use para interagir com paginas web, capturar screenshots, analisar trafego de rede e perfilar performance.