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 1440 of 2,169

  • codex-multi-profileSkillAI & models

    Lets your agent keep several ChatGPT logins side by side in the Codex app via this codex claude skill.

    Ready to connect★ 94

    github.com/hung2124/codex-multi-profile94 stars

    View details
  • connection-auth-rulesSkillAI & models

    Lets your agent build connection auth rules for Monte Carlo by fetching live connector schemas and transform steps.

    Ready to connect★ 92

    github.com/monte-carlo-data/mc-agent-toolkit94 stars

    View details
  • contract-drafterSkillDev tools

    Lets your agent draft contracts from a template with named parties and terms, checking each clause against it.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • crm-cleanupSkillProductivity

    A CRM Claude skill that compares call transcripts against your CRM records and proposes checked field updates.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • cve-auditSkillSecurity

    Lets your agent check npm dependency versions against known vulnerability records and report findings.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • data-storeSkillAI & models

    Lets your agent read data and make declared state changes through controlled data-source operations instead of raw queries.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • data-subject-requestSkillDev tools

    Lets your agent review a data erasure or export request against policy and log a decision.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • diagnose-skill-runSkillDev tools

    Lets your agent diagnose a failed Claude skill run from receipts and evidence and suggest a small fix without replaying it.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • dispute-respondSkillFiles & storage

    Lets your agent prepare and file a payment dispute response backed by receipts, approvals, and proof of service.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • ecosystem-briefSkillDev tools

    Lets your agent produce a decision-ready briefing on a software ecosystem from fresh, governed evidence.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • effect-v4-best-practicesSkillDev tools

    Effect v4 best practices for TypeScript. Use when writing or reviewing Effect programs (Effect.gen, Effect.fn, Layer, Schema, Context.Service, TaggedError, Data.taggedEnum, Effect.forEach, ManagedRuntime, SqlSchema, HttpClient, FetchHttpClient).

    Ready to connect★ 94

    github.com/peterpme/dotfiles93 stars

    View details
  • elsevier-figure-styleSkillDev tools

    Lets your agent create, revise, and check manuscript figures in Elsevier style using matplotlib or ggplot2.

    Ready to connect★ 94

    github.com/guhou-hvi/elsevier-figure-style94 stars

    View details
  • email-lifecycleSkillCommunication

    This email Claude skill lets your agent plan and run lifecycle sequences like welcome, nurture, and win-back.

    Ready to connect★ 92

    github.com/hyperfx-ai/marketing-skills94 stars

    View details
  • external-adapter-echoSkillDev tools

    Lets your agent run a governed subprocess that echoes its inputs back for testing.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • external-adapter-graphSkillDev tools

    Lets your agent run a graph step that executes an external subprocess adapter under governance rules.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • failingSkillDev tools

    Lets your agent deliberately trigger a failure to test how it or other tools handle errors.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • generate-validation-notebookSkillDatabases & data

    Lets your agent generate claude skill notebooks that validate dbt changes from a GitHub PR or local repo.

    Ready to connect★ 92

    github.com/monte-carlo-data/mc-agent-toolkit94 stars

    View details
  • ghostwriteSkillDev tools

    Lets your agent turn gathered evidence into publication-ready drafts and handoff packages.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • github-mcp-heroSkillDev tools

    Lets your agent use a GitHub claude skill that can read repos while blocking any changes outside its allowed scope.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • github-mcp-merge-prSkillDev tools

    A github claude skill that lets your agent merge a GitHub pull request on your behalf.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • github-mcp-pr-review-noteSkillDocs & knowledge

    Lets your agent add a review note to GitHub pull requests using a GitHub Claude skill.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • github-mcp-read-issueSkillDev tools

    Lets your agent read a GitHub issue using a github claude skill that returns fixed test data.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • github-mcp-write-commentSkillDev tools

    Lets your agent post a comment on a GitHub issue using a github claude skill that writes the same comment every time.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • github-pr-commentSkillDev tools

    Lets your agent post one exact comment on a GitHub pull request using this GitHub Claude skill.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • governed-outboundSkillDev tools

    Lets your agent send approved data to an outside service after checking it's on an allowlist and scrubbing personal info.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • helpdeskSkillDev tools

    Lets your agent sort support requests and draft customer replies for a human to approve before sending.

    Ready to connect★ 93

    github.com/runxhq/runx94 stars

    View details
  • hylo-compile-noteSkillDocs & knowledge

    Lets your agent turn a raw note into wiki-style knowledge pages in a knowledge base.

    Ready to connect★ 89

    github.com/skoowoo/hylo94 stars

    View details
  • hylo-index-knowledgeSkillFiles & storage

    Lets your agent build and update index files that organize your Hylo knowledge base by domain.

    Ready to connect★ 89

    github.com/skoowoo/hylo94 stars

    View details
  • hylo-memorySkillFiles & storage

    Lets your agent turn your notes into organized personal memory files covering identity, goals, people, and more.

    Ready to connect★ 89

    github.com/skoowoo/hylo94 stars

    View details
  • hylo-notesSkillSearch

    Lets your agent search, read, create, edit, and delete personal notes in Hylo.

    Ready to connect★ 89

    github.com/skoowoo/hylo94 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