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
65,240 results · page 1382 of 2,175
- View details
flaky-test-triageSkillDev tools
Analyzes your repo's GitHub Actions runs to find which tests fail intermittently versus those that are truly broken.
Ready to connect★ 106
- View details
generate-cve-jsonSkillDocs & knowledge
Generate claude skill output: turns a CVE tracking issue into a ready-to-paste CVE 5.x JSON document.
Ready to connect★ 106
- View details
gh-merge-prSkillAI & models
Review and merge a GitHub PR after independent authorization. Used for current-head SubAgent Review of a single PR, evidence-based specialized Review calls, landing, and parity readback; bare branches or missing PRs are handed off to git-push-pr.
Ready to connect★ 108
- View details
git-push-prSkillDev tools
Push a verified branch and create or update exactly one GitHub pull request. Use when the user asks to 推送远程/建 PR/更新 PR and grants push authority. Read-only without explicit authority; never approves, merges, or closes issues.
Ready to connect★ 108
- View details
git-rebase-mainSkillProductivity
Land a finished branch on local main with linear history — commit pending work, commit main's own dirt first, rebase onto main, fast-forward main. Use when the user asks to rebase/merge/合回主分支 into local main after work is committed. Local only, never touches remotes.
Ready to connect★ 108
- View details
good-first-issue-authorSkillFiles & storage
Lets your agent draft a well-scoped 'good first issue' on an upstream GitHub repo from a suggested task idea.
Ready to connect★ 106
- View details
identity-mapSkillFiles & storage
Map a contributor's GitHub handle to their Slack, Discord, Matrix, mailing-list, and social-media identities. Infers each mapping from the sources the session can reach, grades the evidence, and records only what the maintainer confirms, in a project-wide identity file shared by the contributor-grow
Ready to connect★ 106
- View details
ipaship-auditSkillFiles & storage
Lets your agent scan iOS or Android app packages for App Store and Play policy violations and get fix steps.
Ready to connect★ 108
- View details
isolated-setup-doctorSkillAI & models
Checks your agent's isolated setup for blocks like missing SSH access, ports, or directories, then points to fixes.
Ready to connect★ 106
- View details
isolated-setup-installSkillAI & models
Guides your agent step by step through installing a sandboxed, approval-gated setup for coding CLIs.
Ready to connect★ 106
- View details
isolated-setup-updateSkillDev tools
Lets your agent compare your installed secure setup against the framework's current one and report the differences.
Ready to connect★ 106
- View details
isolated-setup-verifySkillAI & models
Checks your agent's security setup against a checklist and reports which items pass, fail, or partially match.
Ready to connect★ 106
- View details
issue-deduplicateSkillSecurity
Lets your agent merge two duplicate security-tracker issues into one while keeping everyone credited.
Ready to connect★ 106
- View details
issue-fixSkillSecurity
Drafts fixes for tracked security issues and opens pull requests on GitHub.
Ready to connect★ 106
- View details
issue-importSkillSecurity
Turns new security mailing-list reports into tracking issues on your board and drafts a thank-you reply to reporters.
Ready to connect★ 106
- View details
issue-import-from-mdSkillFiles & storage
Turns a markdown file of security findings into separate tracker issues ready for triage.
Ready to connect★ 106
- View details
issue-import-from-prSkillSecurity
Turn an existing GitHub pull request into a tracked security issue without needing a prior emailed vulnerability report.
Ready to connect★ 106
- View details
issue-import-from-scanSkillSecurity
Turns a security scanner's raw findings into a reviewed triage report before creating any tickets.
Ready to connect★ 106
- View details
issue-import-via-forwarderSkillSecurity
Lets your agent recognise security reports relayed by a broker and extract the reporter credit before importing them.
Ready to connect★ 106
- View details
issue-invalidateSkillSecurity
Lets your agent close an invalid tracker with a label, comment, board archive, and a reply draft to the reporter.
Ready to connect★ 106
- View details
issue-syncSkillCommunication
Keeps a security issue in sync with its GitHub discussion, mailing-list thread and related pull requests.
Ready to connect★ 106
- View details
keys-syncSkillFiles & storage
Helps your agent draft changes adding a release manager's public GPG key to a project KEYS file.
Ready to connect★ 106
- View details
license-compliance-auditSkillFiles & storage
Checks whether a code repo has proper LICENSE and NOTICE files and correct SPDX license headers.
Ready to connect★ 106
- View details
mentorSkillDev tools
Lets your agent draft helpful mentoring comments on GitHub issues and pull requests.
Ready to connect★ 106
- View details
mobile-qaSkillProductivity
Lets your agent run a QA checklist on a physical Android device over adb and triage failures into fixes.
Ready to connect★ 107
- View details
model-prepareSkillSecurity
Lets your agent draft a first security model for a project and open it as a pull request for maintainers to review.
Ready to connect★ 106
- View details
multi-agent-reviewSkillSecurity
Lets your agent review a code diff through three separate checks for bugs, security issues, and style, combined into one report.
Ready to connect★ 106
- View details
newcomer-issue-explainerSkillFiles & storage
Explains a GitHub good-first-issue in simple terms and outlines which files to read and what done looks like.
Ready to connect★ 106
- View details
nominationSkillDev tools
Lets your agent build a nomination brief showing whether a GitHub contributor is ready to become a committer.
Ready to connect★ 106
- View details
onboarding-conciergeSkillFiles & storage
Helps newcomers get started via an onboarding Claude skill that answers contribution questions from CONTRIBUTING.md.
Ready to connect★ 106
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for how to install
- Best Claude skills for humanizer
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.
65,240 of the 65,240 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.