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.

Category: AI & models

9,019 results · page 32 of 301

  • wiringSkillAI & models

    Lets your agent verify that wiring and connections are set up correctly.

    Ready to connect★ 4k

    github.com/parcadei/continuous-claude-v34k stars

    View details
  • pr-writing-reviewSkillAI & models

    Lets your agent pull writing and style feedback out of GitHub pull request review comments.

    Ready to connect★ 4k

    github.com/evalstate/fast-agent4k stars

    View details
  • agentSkillAI & models

    Lets your AI agent act as a hands-on electronics engineer that plans and edits atopile circuit projects directly.

    Ready to connect★ 4k

    github.com/atopile/atopile4k stars

    View details
  • agent-summarySkillAI & models

    Lets your agent show a short live status line of what it's currently doing.

    Ready to connect★ 4k

    github.com/atopile/atopile4k stars

    View details
  • ato-languageSkillAI & models

    Lets your agent write and review .ato files, a language for describing electronic circuits declaratively.

    Ready to connect★ 4k

    github.com/atopile/atopile4k stars

    View details
  • code-reviewSkillAI & models

    Guides your agent through reviewing code changes in this repo, scoring impact and test coverage and flagging real bugs.

    Ready to connect★ 4k

    github.com/atopile/atopile4k stars

    View details
  • devSkillAI & models

    LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.

    Ready to connect★ 4k

    github.com/atopile/atopile4k stars

    View details
  • apm-usageSkillAI & models

    Guides your agent through installing, configuring, authoring, and troubleshooting AI-agent packages with the apm CLI.

    Ready to connect★ 4k

    github.com/microsoft/apm4k stars

    View details
  • batch-bug-shepherdSkillAI & models

    Lets your agent triage a batch of suspected bugs and turn them into ready-to-review PRs.

    Ready to connect★ 4k

    github.com/microsoft/apm4k stars

    View details
  • contract-skillSkillAI & models

    Lets your agent follow a standard lifecycle contract for managing plugin-based tasks.

    Ready to connect★ 4k

    github.com/microsoft/apm4k stars

    View details
  • helloSkillAI & models

    Lets your agent install and manage packaged skills from a shared registry.

    Ready to connect★ 4k

    github.com/microsoft/apm4k stars

    View details
  • placeholderSkillAI & models

    Lets your agent install and manage packaged skills from a shared registry.

    Ready to connect★ 4k

    github.com/microsoft/apm4k stars

    View details
  • academic-paperSkillAI & models

    Helps your agent plan, draft, cite, and revise academic papers in standard structures and formats.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • academic-plottingSkillAI & models

    Lets your agent create publication-ready figures for ML papers, from architecture diagrams to data charts.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • bayesian-estimationSkillAI & models

    Guides your agent through Bayesian statistics: setting priors, running MCMC, checking convergence, and reporting results.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • bayesian-workflowSkillAI & models

    Guides your agent through rigorous Bayesian modeling in PyMC with built-in checks for priors, convergence, and calibration.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • causal-inferenceSkillAI & models

    Lets your agent run causal effect analyses (like "did X cause Y?") using Bayesian statistics with built-in checks on assumptions.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • deep-researchSkillAI & models

    Lets your agent run thorough academic research: finding sources, checking facts, and writing a cited report.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • dowhySkillAI & models

    Lets your agent run causal analysis to answer whether X actually causes Y, not just whether they're correlated.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • game-theory-paper-writerSkillAI & models

    Lets your agent draft, revise, and stress-test game theory research papers from a topic, draft, or reviewer comments.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • literature-review-toolsSkillAI & models

    Lets your agent pick and run open-source tools for literature reviews, from searching papers to writing summaries.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • marginaleffectsSkillAI & models

    Gives your agent expert help interpreting statistical models, computing marginal effects, treatment effects, and hypothesis tests in R or Python.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • python-econ-computingSkillAI & models

    Guides your agent to write Python code for economic models like DSGE and HANK, plus causal inference and data analysis.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • Subagent-Driven Literature ReviewSkillAI & models

    Lets your agent screen and analyze large batches of research papers in parallel using subagents.

    Ready to connect★ 4k

    github.com/brycewang-stanford/auto-empirical-research-skills4k stars

    View details
  • geminiSkillAI & models

    Lets your agent get a second opinion from Google Gemini to review, stress-test, or consult on changes.

    Ready to connect★ 4k

    github.com/nowork-studio/notfair-plugin4k stars

    View details
  • paid-ads-chatgptSkillAI & models

    Lets your agent plan and review ChatGPT ad campaigns and performance from exported data.

    Ready to connect★ 4k

    github.com/nowork-studio/notfair-plugin4k stars

    View details
  • paid-ads-setupSkillAI & models

    Connects your Google, Meta, X, or LinkedIn ad accounts and sets up reusable campaign context for your agent.

    Ready to connect★ 4k

    github.com/nowork-studio/notfair-plugin4k stars

    View details
  • upgradeSkillAI & models

    Lets your agent update the NotFair plugin to its latest version, refreshing the marketplace repo and plugin cache.

    Ready to connect★ 4k

    github.com/nowork-studio/notfair-plugin4k stars

    View details
  • alliumSkillAI & models

    Lets your agent write and maintain Allium spec files that describe software behaviour precisely and generate tests from them.

    Ready to connect★ 4k

    github.com/datadog/datadog-agent4k stars

    View details
  • create-componentSkillAI & models

    Lets your agent scaffold a new Fx component with def, fx, and impl packages for the Datadog Agent codebase.

    Ready to connect★ 4k

    github.com/datadog/datadog-agent4k 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.

54,764 of the 55,196 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 gateway 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