Capability
Runs commands agent skills
Skills whose files run package managers, CLIs or other commands. Counted among the 742 skills with full pages, whose files the directory reads in full.
Highest-scoring with this capability: codeql from trailofbits/skills (92/100), agent-ready from mblode/agent-skills (91/100) and tao-analyze-detection-kpi from NVIDIA/skills (90/100).
- 102 listed skills
- 43 repositories
By category
Developer Tools and Frameworks (25) · AI Agents and LLM Engineering (21) · DevOps and Cloud (12) · Business, Sales and Finance (9) · Video, Image, Audio and Creative (7) · Testing and QA (7) · Science and Research (6) · Productivity and Knowledge Work (5) · Security (3) · Data, Analytics and Databases (2) · Frontend and Design (2) · Writing and Editing (1) · Code Review and Code Quality (1) · Documents and Office Files (1)
All 102 skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| agent-ready 91/100 · A | mblode/agent-skills | Implements agent-readiness on sites and docs from scorecards like Mintlify Agent Score or AFDocs, including llms.txt coverage and agents hitting 404s on guessed URLs. |
| apollo-server 84/100 · B | apollographql/skills | Guides building GraphQL servers with Apollo Server 5.x, including project setup, resolvers and schemas, authentication and authorization, plugins, custom data sources, and troubleshooting. |
| article-extractor 74/100 · C | michalparkola/tapestry-skills-for-claude-code | Extracts clean article content from URLs such as blog posts and tutorials and saves it as readable text without ads, navigation, or clutter. |
| atlassian 83/100 · B | sanjay3290/ai-skills | Manages Jira issues and Confluence wiki pages in Atlassian Cloud, including JQL and CQL searches, workflows, transitions, comments, and browsing spaces. |
| aws-cdk-development 85/100 · B | zxkane/aws-skills | Guides building AWS cloud infrastructure with CDK in TypeScript or Python, covering app structure, construct patterns, stack composition, and deployment workflows. |
| aws-mcp-setup 80/100 · B | zxkane/aws-skills | Configures AWS MCP servers for documentation search and API access, covering both the full AWS MCP Server and the lightweight Documentation MCP. |
| browser-trace 80/100 · B | browserbase/skills | Captures a DevTools-protocol trace of browser automation, including CDP events, screenshots, and DOM dumps, and splits it into per-page searchable buckets for debugging. |
| cf-cli 78/100 · C | cloudflare/skills | Guides using Cloudflare's beta cf CLI for the public Cloudflare API and Workers projects, including sign-in, command search, deploy, dev, build, and resource commands. |
| chaos-engineer 84/100 · B | jeffallan/claude-skills | Designs chaos experiments and failure injection frameworks and runs game day exercises for distributed systems, producing runbooks, experiment manifests, rollback procedures, and post-mortem templates. |
| citation-management 89/100 · B | K-Dense-AI/claude-scientific-skills | Manages academic citations by searching OpenAlex, PubMed, and Google Scholar, extracting metadata, validating references, and generating formatted BibTeX entries. |
| claude-real-video-for-agents 80/100 · B | HUANGCHIHHUNGLeo/claude-real-video | Installs and uses the crv tool so an AI agent can watch videos by extracting deduplicated scene-aware keyframes and transcribing audio. |
| codeql 92/100 · A | trailofbits/skills | Scans a codebase for security vulnerabilities using CodeQL's interprocedural data flow and taint tracking analysis, with run-all and important-only scan modes. |
| coding-agent 75/100 · C | swarmclawai/swarmclaw | Delegates coding tasks to external coding agents such as Claude Code, Codex, Pi, and OpenCode via shell, including new features, PR reviews, and refactoring. |
| cookie-sync 80/100 · B | browserbase/skills | Syncs cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites as the user. |
| create-voltagent 68/100 · D | VoltAgent/skills | Guides creating AI agent projects with the VoltAgent framework, using either CLI setup or manual bootstrapping. |
| cypress-cloud-cli 81/100 · B | cypress-io/ai-toolkit | Runs the cy-cloud CLI to inspect Cypress Cloud organizations, projects, runs, specs, tests, failure screenshots, and Test Replay data. |
| cypress-skill 86/100 · B | LambdaTest/agent-skills | Generates Cypress end-to-end and component tests in JavaScript or TypeScript, supporting local execution and the TestMu AI cloud. |
| detox-skill 84/100 · B | LambdaTest/agent-skills | Generates Detox end-to-end tests in JavaScript for React Native apps, running on local simulators and emulators or the TestMu AI cloud. |
| dev-browser 77/100 · C | SawyerHood/dev-browser | Automates browser tasks through the dev-browser CLI with persistent named pages, such as navigating sites, filling forms, taking screenshots, and extracting web data. |
| devops-engineer 84/100 · B | jeffallan/claude-skills | Creates Dockerfiles, CI/CD pipelines, Kubernetes manifests, and Terraform or Pulumi templates, and handles deployment automation, GitOps configuration, and incident response runbooks. |
| dexpaprika-api 80/100 · B | coinpaprika/skills | Queries the DexPaprika API, CLI, and streaming service for DEX data, including networks, pools, tokens, and trading activity. |
| document-hunter 82/100 · B | bitwize-music-studio/claude-ai-music-skills | Searches and retrieves primary source documents, such as court filings, government reports, and public records, from free public sources using automated browser navigation. |
| eas-app-stores 83/100 · B | expo/skills | Builds and submits iOS and Android apps with EAS to TestFlight, the App Store, or Google Play, including eas.json setup, signing, and release pipelines. |
| eas-observe 76/100 · C | expo/skills | Adds expo-observe to Expo projects, records per-route metrics, events, and errors, and queries or interprets the metrics with the EAS CLI. |
| eas-simulator 85/100 · B | expo/skills | Runs and controls an app on a remote iOS or Android simulator hosted on EAS cloud, for machines that cannot run a simulator locally. |
| eas-update-insights 85/100 · B | expo/skills | Checks the health of published EAS Updates, including crash rates, launch counts, unique users, payload size, and embedded versus OTA users per channel. |
| emblem-ai 81/100 · B | EmblemCompany/Agent-skills | Adds user management with multi-chain wallet authentication, AI assistant chat surfaces, and observability to apps, using React components, TypeScript SDKs, and session-based authentication. |
| emblem-ai-agent-wallet 83/100 · B | EmblemCompany/Agent-skills | Connects to EmblemVault to run review-first, operator-controlled wallet workflows across Solana, Ethereum, Base, BSC, Polygon, Hedera, and Bitcoin, and explains Emblem's authentication model. |
| emblem-ai-prompt-examples 81/100 · B | EmblemCompany/Agent-skills | Provides example prompts for EmblemAI tasks such as research, portfolio review, quote requests, NFT discovery, and prediction-market analysis, with explicit confirmation before value-moving actions. |
| emblem-ai-react 78/100 · C | EmblemCompany/Agent-skills | Adds website authentication and wallet-enabled users to a React app using EmblemAuthProvider, ConnectButton, social, email, and wallet login, chat components, and React auth hooks. |
| emblem-defi-yield 78/100 · C | EmblemCompany/Agent-skills | Researches DeFi yield opportunities, compares protocols, checks DeFi positions with Nansen, and enters liquid staking via token swaps through EmblemAI. |
| emblem-market-research 78/100 · C | EmblemCompany/Agent-skills | Provides crypto market intelligence through EmblemAI, including trending tokens, on-chain analytics, derivatives data, and smart money tracking from CoinGecko, CoinGlass, Birdeye, and Nansen. |
| emblem-memecoin-scout 78/100 · C | EmblemCompany/Agent-skills | Finds trending memecoins on Solana, Base, and Hedera, tracks new token launches, and assesses risk with rug-pull detection, holder analysis, and smart money tracking. |
| emblem-portfolio-tracker 78/100 · C | EmblemCompany/Agent-skills | Tracks a crypto portfolio across seven blockchains with aggregated balances in USD, conditional trade profit and loss, and DeFi position tracking through Nansen. |
| emblem-token-swap 78/100 · C | EmblemCompany/Agent-skills | Executes token swaps across six blockchains with automatic route optimization and cross-chain bridging via ChangeNow, using EmblemAI. |
| expo-app-clip 83/100 · B | expo/skills | Adds an iOS App Clip target to an Expo app, so a lightweight Clip can be invoked from a URL alongside the parent app. |
| expo-brownfield 83/100 · B | expo/skills | Integrates Expo and React Native into an existing native iOS or Android app, including embedding screens in SwiftUI, UIKit, or Kotlin. |
| expo-data-fetching 83/100 · B | expo/skills | Guides implementing and debugging network requests and data fetching using fetch, React Query, SWR, caching, offline support, and Expo Router data loaders. |
| expo-design-system 79/100 · C | expo/skills | Builds and maintains a design system in an Expo app, covering design tokens, components with variant, size, and state props, and shared component extraction. |
| expo-examples 85/100 · B | expo/skills | Points to Expo's official example projects, about 70 with-* integrations, for adding third-party libraries or services to an Expo app or scaffolding projects. |
| expo-migrate-module 87/100 · B | expo/skills | Migrates a Swift Expo native module from the Expo Modules API 1.0 DSL to the 2.0 macro API, preserving its JavaScript and TypeScript contract. |
| expo-module 87/100 · B | expo/skills | Guides creating Expo native modules and views in Swift, Kotlin, and TypeScript, covering the module definition DSL, shared objects, config plugins, and autolinking. |
| expo-web-to-native 83/100 · B | expo/skills | Migrates a web React app to native iOS and Android with Expo, including how web idioms like the DOM and CSS map to native. |
| faiss 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides fast k-NN search and clustering of dense vectors with Facebook's FAISS, including GPU acceleration and Flat, IVF, and HNSW index types. |
| find-skills 81/100 · B | vercel-labs/skills | Helps users discover and install agent skills when they ask how to do something or look for a skill that extends capabilities. |
| firebase-ai-logic-basics 80/100 · B | firebase/skills | Integrates Firebase AI Logic into mobile and web apps to call Gemini models from client code for text generation, multimodal input, chat, and streaming. |
| firebase-auth-basics 82/100 · B | firebase/skills | Guides setting up and using Firebase Authentication for apps that need user sign-in, user management, or secure data access through auth rules. |
| firebase-firestore 81/100 · B | firebase/skills | Sets up, queries, and configures Cloud Firestore databases, including data modeling, security rules, indexes, and SDK integrations for Web, Python, iOS, Android, and Flutter. |
| firebase-hosting-basics 81/100 · B | firebase/skills | Deploys and configures classic Firebase Hosting for static sites, single-page apps, and microservices, including custom domains, redirects, rewrites, headers, multi-site setups, and preview channels. |
| firebase-remote-config-basics 86/100 · B | firebase/skills | Manages Firebase Remote Config templates, feature flags, loading strategies, version history, in-app defaults, real-time listeners, and SDK setup for Android and iOS. |
| hf-cloud-python-env-setup 85/100 · B | huggingface/skills | Sets up an isolated Python environment with the right Python version and current boto3 for SageMaker and other AWS automation work. |
| huggingface-local-models 80/100 · B | huggingface/skills | Selects models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm, covering quant selection, conversion, and OpenAI-compatible serving. |
| image-utils 84/100 · B | Bria-AI/bria-skill | Manipulates images with Python Pillow, including resizing, cropping, compositing, format conversion, watermarks, brightness and contrast adjustments, and web optimization. |
| knowledge-distillation 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Compresses large language models into smaller student models using knowledge distillation, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training. |
| lab-hardware-cad 86/100 · B | K-Dense-AI/claude-scientific-skills | Designs custom laboratory hardware as parametric build123d models and exports STEP, STL, and DXF files for fabrication. |
| langchain 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides building LLM-powered applications with LangChain, including agents, chains, RAG, tool calling, memory management, and vector store retrieval across multiple providers. |
| learn-this 77/100 · C | michalparkola/tapestry-skills-for-claude-code | Extracts content from a YouTube video, article, or PDF URL, detecting the content type automatically, and turns it into an action plan. |
| linting-neostandard-eslint9 77/100 · C | mcollina/skills | Configures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy .eslintrc files or the standard package. |
| literature-review 89/100 · B | K-Dense-AI/claude-scientific-skills | Conducts systematic, scoping, and narrative literature reviews using sources such as PubMed, arXiv, and bioRxiv, tracking search coverage and evidence limitations. |
| llava 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides visual instruction tuning and image-based conversations with LLaVA, which combines a CLIP vision encoder with Vicuna or LLaMA models for visual question answering. |
| minimax-music-gen 77/100 · C | MiniMax-AI/skills | Generates music, songs, and audio tracks, including lyrics generation, covers, turning supplied lyrics into a song, and background music for a described mood. |
| model-merging 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Merges multiple fine-tuned models with mergekit to combine capabilities without retraining, using methods such as SLERP, TIES-Merging, DARE, and Task Arithmetic. |
| model-pruning 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Reduces LLM size and speeds inference with pruning techniques like Wanda and SparseGPT, without retraining, including structured, unstructured, N:M, and magnitude pruning. |
| neuropixels-analysis 87/100 · B | K-Dense-AI/claude-scientific-skills | Analyzes Neuropixels extracellular recordings with SpikeInterface, covering data loading, preprocessing, drift correction, Kilosort4 spike sorting, quality metrics, and unit curation. |
| nextjs-on-cloudflare 72/100 · C | cloudflare/skills | Builds, migrates, and deploys Next.js apps on Cloudflare Workers with vinext, including choosing between vinext and OpenNext and moving existing apps to Workers. |
| nodejs-core 80/100 · B | mcollina/skills | Supports contributing to and debugging Node.js core, including commit and PR tone, native crashes, V8 performance, node-gyp builds, N-API bindings, and libuv issues. |
| notion-apps 70/100 · C | makenotion/skills | Sets up and scaffolds Notion Apps using the Notion Apps SDK and the ntn CLI when starting a new Notion App project. |
| notion-cli 78/100 · C | makenotion/skills | Uses the Notion CLI (ntn) to call the Notion API, manage workers, upload files, create pages, and query databases. |
| oauth 80/100 · B | mcollina/skills | Implements OAuth 2.0 and 2.1 authorization flows in Fastify applications, including PKCE, client credentials, device flow, refresh token rotation, and JWT validation. |
| orca-replay 86/100 · B | Continuum-AI-Corp/OrcaReplay | Answers questions about a past agent run from its recording rather than memory, and replays or forks that run. |
| pdf 86/100 · B | anthropics/skills | Handles PDF tasks including extracting text and tables, merging, splitting, watermarking, creating PDFs, filling forms, extracting images, and running OCR on scanned files. |
| playwright-cli 80/100 · B | testdino-hq/playwright-skill | Automates browser interactions with playwright-cli to test web applications you own, including navigation, form filling, screenshots, tracing, debugging, and generating Playwright test code. |
| playwright-skill 86/100 · B | LambdaTest/agent-skills | Generates Playwright automation scripts and end-to-end tests in TypeScript, JavaScript, Python, Java, or C#, run locally or on TestMu AI cloud. |
| primer-design 87/100 · B | K-Dense-AI/claude-scientific-skills | Designs and audits PCR and RT-qPCR primers with Primer3, including off-target amplification searches, existing primer checks, and in-silico PCR and BLAST screening. |
| publish-models 71/100 · C | replicate/skills | Pushes and publishes custom AI models to Replicate and sets up CI/CD for releasing new model versions safely, including cog-safe-push validation. |
| react-email 83/100 · B | resend/resend-skills | Guides building HTML email templates with React components, rendering them to HTML, adding the visual email editor, and sending with Resend. |
| react-native-dev 73/100 · C | MiniMax-AI/skills | Guides React Native and Expo development, covering components, styling, animations, navigation, state management, networking, performance, testing, native capabilities, and deployment. |
| relsa-severity-assessment 88/100 · B | K-Dense-AI/claude-scientific-skills | Combines welfare readouts from laboratory animal studies into a daily severity score per animal and forecasts which animals may reach a humane endpoint. |
| render-chatgpt-chat 81/100 · B | gooseworks-ai/goose-skills | Assembles a ChatGPT chat-reveal video ad from thread and timeline JSON, using a recorded mobile chat and a designed end card. |
| resend-cli 83/100 · B | resend/resend-skills | Operates the Resend platform from the terminal with the resend CLI, covering sending emails, domains, contacts, broadcasts, templates, webhooks, API keys, automations, and events. |
| rover 84/100 · B | apollographql/skills | Guides using the Apollo Rover CLI to publish and fetch schemas, compose supergraphs, run local development, validate with check and lint, and configure authentication. |
| rtvi-cv-scaffold-vss-service 85/100 · B | NVIDIA/skills | Scaffolds a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka, based on a YOLO26 reference implementation. |
| safe-browser 75/100 · C | browserbase/skills | Builds constrained-browser agents whose safe_browser tool enforces a domain allowlist, so an agent can browse without raw browser, shell, or CDP access. |
| sentence-transformers 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Generates sentence, text, and image embeddings with 5000+ pre-trained models for semantic similarity, clustering, retrieval, RAG, and semantic search. |
| sentencepiece 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides training language-independent SentencePiece tokenizers with BPE or Unigram directly on raw text, for multilingual, CJK, and reproducible tokenization needs. |
| setup 84/100 · B | Necmttn/ax | Installs and verifies ax, the agent experience layer, walking through install.sh, skills.sh, and the first ingest, validating with ax doctor. |
| slack-gif-creator 87/100 · B | anthropics/skills | Provides constraints, validation tools, and animation concepts for creating animated GIFs sized and optimized for Slack. |
| smartui-skill 81/100 · B | LambdaTest/agent-skills | Generates SmartUI visual regression test configurations for screenshot comparison on TestMu AI cloud, working with Playwright, Selenium, Cypress, and Puppeteer. |
| snipgrapher 77/100 · C | mcollina/skills | Configures snipgrapher to generate syntax-highlighted code snippet images as PNG, SVG, or WebP, with custom themes, reusable profiles, and batch jobs. |
| speculative-decoding 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Accelerates LLM inference with speculative decoding, Medusa multiple heads, and lookahead decoding, covering draft models, tree-based attention, and parallel token generation. |
| strategy-board 84/100 · B | tronghieu/agent-skills | Runs a C-level strategy advisory board of specialist agents that takes an executive from a strategic question to a defended recommendation. |
| superdesign 83/100 · B | superdesigndev/superdesign-skill | Designs or redesigns frontend UI, presentations, and graphics on the Superdesign canvas using a choice of AI models, comparing results and exploring visual variants. |
| swarmclaw 74/100 · C | swarmclawai/swarmclaw | Teaches agents running on SwarmClaw how to use its 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. |
| tao-analyze-detection-kpi 90/100 · A | NVIDIA/skills | Runs TAO Data Services KPI analysis for object detection, comparing inference annotations with ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP. |
| technical-doc-creator 78/100 · C | mhattingpete/claude-skills-marketplace | Creates HTML technical documentation with code blocks, API workflows, system architecture diagrams, and syntax highlighting for API references and developer documentation. |
| train-sentence-transformers 83/100 · B | huggingface/skills | Trains and fine-tunes sentence-transformers models, including bi-encoders, cross-encoders, sparse encoders, and multi-vector encoders, with guidance on loss selection, hard-negative mining, evaluators, and Hub publishing. |
| unbrowse 83/100 · B | unbrowse-ai/unbrowse | Searches and calls websites through Unbrowse's API or remote MCP, reusing indexed site tools, reading pages, and learning missing routes in its cloud browser. |
| using-git-worktrees 84/100 · B | obra/superpowers | Ensures feature work or plan execution happens in an isolated workspace, using native tools or a git worktree fallback. |
| varlock 75/100 · C | wrsmith108/varlock-claude-skill | Manages environment variables and secrets with Varlock so secrets are never exposed in terminals, logs, traces, or Claude's context. |
| vision-analysis 69/100 · D | MiniMax-AI/skills | Analyzes, describes, and extracts information from images, including text extraction, using the MiniMax vision MCP tool. |
| windows-vm 76/100 · C | obra/superpowers-lab | Creates, manages, and connects to a headless Windows 11 VM running in Docker with SSH access, including stopping and restarting it. |
| youtube-transcript 74/100 · C | michalparkola/tapestry-skills-for-claude-code | Downloads YouTube video transcripts, captions, and subtitles when given a YouTube URL or a request to fetch or transcribe a video. |