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

55,384 results · page 1128 of 1,847

  • policy-authorSkillMedia

    Lets your agent draft and check operational policy files against a required contract.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • post-merge-final-outcome-publisherSkillDev tools

    Lets your agent publish a final state update after a code merge.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • postmortem-makerSkillMonitoring & ops

    Lets your agent draft an incident postmortem from notes, flagging facts versus guesses and holding it for review.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • prior-artSkillMedia

    Lets your agent check existing tools, docs, and project patterns before a decision and give a cited go or stop recommendation.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • purchase-approvalSkillDev tools

    Lets your agent check a proposed purchase against a procurement policy and reject it if it breaks budget or vendor rules.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • redact-piiSkillMonitoring & ops

    Lets your agent detect and remove personal data from text before sharing it, with a pass, review, or block verdict.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • reflect-digestSkillDev tools

    Lets your agent group run signals by skill and hand validated evidence to skill-lab improve.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • refundSkillCommerce & finance

    Lets your agent issue a refund for one payment with built-in approval and confirmation steps.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • research-analyzeSkillDev tools

    Lets your agent verify and analyze evidence gathered during a research claude skill workflow.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • reviewer-boundarySkillProductivity

    Lets your agent act as a test fixture that marks a clear boundary for agent tasks.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • sbom-makerSkillDev tools

    Lets your agent generate a CycloneDX software bill of materials from a lockfile, with license risks flagged.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • scafld-native-smokeSkillDev tools

    Lets your agent run a smoke test of the scafld binary through its native v2 lifecycle.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • schema-guardSkillDev tools

    Lets your agent check API changes against the current contract and sample payloads before publishing.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • send-asSkillCommunication

    Lets your agent send a message or campaign through a connected provider after an approval step and delivery check.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • settle-invoiceSkillCommerce & finance

    Lets your agent validate and settle a single invoice with an approval step and confirmation readback.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • sign-receiptSkillDev tools

    Lets your agent create a signed receipt recording an action taken outside it, with references to its evidence.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • skill-labSkillFiles & storage

    Lets your agent design, create, update, and test skill packages using file writes and validation.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • skill-level-retrySkillDev tools

    Lets your agent echo text back while showing retry metadata declared on the skill.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • slack-notifySkillCommunication

    Lets your agent plan and post an approved Slack notification using this Slack Claude skill.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • sourceySkillDocs & knowledge

    Lets your agent generate documentation for a code project.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • spendSkillCommerce & finance

    Lets your agent send a single outbound payment with approval steps and confirmation of the result.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • sql-analystSkillDatabases & data

    Lets your agent answer data questions with a SQL Claude skill that reads from one governed database.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • stripe-paySkillCommerce & finance

    Lets your agent run a Stripe payment using the Stripe Claude skill through a hosted spend contract.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • taste-profileSkillAI & models

    Lets your agent turn examples, likes, and dislikes into a taste claude skill packet other agents use for style choices.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • thread-outbox-provider-fetchSkillDev tools

    Lets your agent fetch fixture thread readback data through the thread-outbox-provider front.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • thread-outbox-provider-graphSkillDev tools

    Lets your agent push a thread outbox entry to a fixture graph and read it back through the Rust front.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • thread-outbox-provider-pushSkillDev tools

    Lets your agent publish a fixture thread outbox entry through the Rust thread-outbox-provider.

    Ready to connect★ 92

    github.com/runxhq/runx93 stars

    View details
  • triage-test-runSkillMonitoring & ops

    Lets your agent diagnose a failing GitHub Actions run by fetching logs and grouping failures by root cause.

    Ready to connect★ 93

    github.com/filenclouddienste/filen-rs91 stars

    View details
  • types-serde-conventionsSkillDev tools

    Lets your agent add or change data types in this Rust codebase while following its rules.

    Ready to connect★ 93

    github.com/filenclouddienste/filen-rs91 stars

    View details
  • uncoveredSkillDev tools

    Lets your agent run a doctor fixture with an execution profile and no harness proof.

    Ready to connect★ 92

    github.com/runxhq/runx93 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.

55,384 of the 55,384 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