Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Filter by category

65,055 results · page 1447 of 2,169

  • outcome-runSkillMonitoring & ops

    Runs one improvement step toward a chosen goal by picking an action, doing it, and recording results.

    Ready to connect★ 92

    github.com/nimrobo/superdense92 stars

    View details
  • outcome-setupSkillDatabases & data

    Sets up a structured folder that defines goals, metrics, and improvement steps so your agent can track progress.

    Ready to connect★ 92

    github.com/nimrobo/superdense92 stars

    View details
  • outcome-updateSkillDev tools

    Improves your agent's outcome-loop playbooks by learning from past runs and reward evidence.

    Ready to connect★ 92

    github.com/nimrobo/superdense92 stars

    View details
  • png-compressSkillMedia

    Lets your agent batch-compress PNG images in a project to reduce file size without visible quality loss.

    Ready to connect★ 92

    github.com/job-yang/jobyang-ai-skills79 stars

    View details
  • private-house-codeSkillMedia

    Guides your agent to write code that is complete, readable, and sized to the task.

    Ready to connect★ 91

    github.com/see-sol-lab/private-house-code-v2.592 stars

    View details
  • project-context-primerSkillProductivity

    Lets your agent load project decisions, conventions, gotchas, and task status at the start of a session.

    Ready to connect★ 92

    github.com/omergocmen/vibe-coder-kit92 stars

    View details
  • react-router-data-modeSkillDev tools

    Lets your agent build React apps with createBrowserRouter and RouterProvider as a react claude skill.

    Ready to connect★ 92

    github.com/yyong008/react-router-antd-admin91 stars

    View details
  • react-router-declarative-modeSkillSearch

    A react claude skill for building React apps with React Router declarative mode: JSX routes, Link navigation, URL params.

    Ready to connect★ 92

    github.com/yyong008/react-router-antd-admin91 stars

    View details
  • sansi-erhouxingSkillDocs & knowledge

    Makes your agent read a whole document's structure before editing it, instead of patching one section at a time.

    Ready to connect★ 92

    github.com/job-yang/jobyang-ai-skills79 stars

    View details
  • strategy-backtestSkillFiles & storage

    Runs SMA crossover backtests on historical OHLCV/candlestick data, calculating total return, Sharpe ratio, max drawdown, win rate, and trade log. Supports CSV files and JSON input with automatic AKShare/hhxg column normalization. Use when the user asks to backtest a trading strategy, evaluate strate

    Ready to connect★ 92

    github.com/leionion/clawforge91 stars

    View details
  • superdenseSkillAI & models

    Lets your agent find and read records of its past sessions to recover context.

    Ready to connect★ 92

    github.com/nimrobo/superdense92 stars

    View details
  • tangshan-styleSkillDev tools

    Lets your agent turn tech predictions and future trends into engaging speculative essays with historical depth.

    Ready to connect★ 92

    github.com/job-yang/jobyang-ai-skills79 stars

    View details
  • test-driven-executionSkillAI & models

    Makes your agent write tests first, then code that passes them, so results match what you asked for.

    Ready to connect★ 92

    github.com/omergocmen/vibe-coder-kit92 stars

    View details
  • travel-guidebookSkillWeb & browsing

    Lets your agent turn a trip itinerary into a designed travel guidebook PDF.

    Ready to connect★ 91

    github.com/geekjourneyx/travel-guidebook92 stars

    View details
  • vddSkillAI & models

    Gives your agent a verification-driven development method so it reports honest test results instead of false success.

    Ready to connect★ 92

    github.com/job-yang/jobyang-ai-skills79 stars

    View details
  • video-readerSkillFiles & storage

    Lets your agent understand video files (.mp4, .mov, .gif) using the video claude skill, e.g. to debug app issues from screen recordings.

    Ready to connect★ 92

    github.com/job-yang/jobyang-ai-skills79 stars

    View details
  • abcd-skillSkillDatabases & data

    Lets your agent run the full ABCD Study brain-imaging workflow: download approved data, organize it into BIDS, and process MRI scans.

    Ready to connect★ 91

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • abide-skillSkillDatabases & data

    Lets your agent download the ABIDE autism brain imaging dataset, organize it into BIDS format, and run structural and fMRI processing pipelines.

    Ready to connect★ 91

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • add-backlogSkillDev tools

    Lets your agent add claude skill ideas to a backlog parking lot using 999.x numbering.

    Ready to connect★ 91

    github.com/buildomator/buildomator86 stars

    View details
  • adhd200-skillSkillDatabases & data

    Lets your agent download the ADHD-200 brain imaging dataset, organize it, and run structural and fMRI processing.

    Ready to connect★ 91

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • adni-skillSkillDev tools

    Lets your agent organize ADNI brain imaging data into BIDS format and run fMRIPrep preprocessing and ROI extraction workflows.

    Ready to connect★ 91

    github.com/cuhk-aim-group/neuroclaw83 stars

    View details
  • agent-platform-deploySkillCloud & infra

    Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check deployment status, verify serving endpoints, or clean up resources by undeploying models and deleting endpoints. Use when asked to deploy models on Agent Platform, list available Model Garden models, check if a

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-endpoint-managementSkillCloud & infra

    Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for run

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-eval-flywheelSkillDatabases & data

    Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidanc

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-inferenceSkillSecurity

    Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when you need to generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or l

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-migrate-from-ai-studioSkillAI & models

    Guides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-model-registrySkillCloud & infra

    Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-prompt-managementSkillCloud & infra

    Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-rag-engine-managementSkillDatabases & data

    Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner ski

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details
  • agent-platform-skill-registrySkillSearch

    'Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to register functionality or discover new capabilities.

    Ready to connect★ 91

    github.com/hermesonehq/hermes-registry91 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

62,835 of the 65,055 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your workspace and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI