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
54,514 results · page 507 of 1,818
- View details
sglang-upgradeSkillCloud & infra
Upgrade the sglang version used by Relax's training Docker image. Use when bumping/upgrading sglang (changing the base image tag), rebasing docker/patch/latest/sglang.patch onto a new sglang release, or porting Relax's sglang customizations forward to a new version. Covers the version-determination
Ready to connect★ 615
- View details
ssh-ray-clusterSkillProductivity
Lets your agent debug a remote Ray cluster by submitting tasks over SSH and checking the results.
Ready to connect★ 615
- View details
sync-githubSkillProductivity
Lets your agent sync code between internal GitLab and GitHub, including branch updates and CI checks.
Ready to connect★ 615
- View details
verl-to-relaxSkillDev tools
Lets your agent convert reinforcement learning training recipes from the verl framework to Relax.
Ready to connect★ 615
- View details
bench-maintainSkillCloud & infra
Lets your agent run routine maintenance on a markup validator benchmark, keeping coverage checks green and following upstream updates.
Ready to connect★ 614
- View details
bench-rule-enableSkillDev tools
Lets your agent turn on a markuplint rule in the bench config by editing tests/external/bench/config.ts.
Ready to connect★ 614
- View details
bench-setupSkillCloud & infra
Lets your agent set up and troubleshoot the nu-validator benchmark environment, including Docker and snapshot issues.
Ready to connect★ 614
- View details
bench-triageSkillDev tools
Lets your agent triage markuplint test fixtures by reading specs and recording verdicts like match-error or nu-over.
Ready to connect★ 614
- View details
bench-virtual-ruleSkillDev tools
Lets your agent copy a preset virtual rule into bench/config.ts so benchmarks test the new rule.
Ready to connect★ 614
- View details
bench-xrefSkillDev tools
Lets your agent sync benchmark cross-reference blocks onto GitHub issues and manage the mapping config.
Ready to connect★ 614
- View details
cyberedge-assess-scopeSkillWeb & browsing
Lets your agent run a security assessment of a website, checking assets, services, and vulnerabilities within an approved scope.
Ready to connect★ 613
- View details
cyberedge-correlate-cvesSkillSecurity
Lets your agent match observed software assets against published vulnerability records to find which flaws apply.
Ready to connect★ 613
- View details
cyberedge-discover-assetsSkillSearch
Lets your agent inventory domains and IP ranges with authorization-backed, passive asset discovery.
Ready to connect★ 613
- View details
cyberedge-discover-servicesSkillSecurity
Lets your agent scan approved domains or IPs to identify which network services are exposed.
Ready to connect★ 613
- View details
cyberedge-inspect-resultsSkillMonitoring & ops
Lets your agent inspect CyberEdge task results, findings, and evidence without making changes.
Ready to connect★ 613
- View details
cyberedge-monitor-public-codeSkillSearch
Lets your agent search public GitHub code for mentions of specific domain names during authorized security checks.
Ready to connect★ 613
- View details
cyberedge-observe-certificatesSkillDev tools
Lets your agent collect and inspect TLS certificates for an authorized CyberEdge scope.
Ready to connect★ 613
- View details
cyberedge-observe-websitesSkillWeb & browsing
Lets your agent collect HTTP metadata and technology fingerprints from websites within an authorized scope.
Ready to connect★ 613
- View details
cyberedge-query-registrationsSkillDev tools
Lets your agent look up domain registration and organization relationship data for approved target domains.
Ready to connect★ 613
- View details
cyberedge-report-findingsSkillSecurity
Lets your agent report and query evidence-backed security findings from authorized CyberEdge tasks.
Ready to connect★ 613
- View details
cyberedge-scan-vulnerabilitiesSkillSecurity
Lets your agent run authorized vulnerability scans and interpret the findings for a defined target scope.
Ready to connect★ 613
- View details
framework-parsersSkillDev tools
Lets your agent create and update markuplint parser and spec packages following the rules that keep builds passing.
Ready to connect★ 614
- View details
list-rule-testSkillDev tools
Lets your agent list rule test IDs, spot missing prefixes, and pick the next free ID number.
Ready to connect★ 614
- View details
markuplintSkillDocs & knowledge
Gives your agent reference knowledge for checking HTML files for errors with Markuplint, including rules and config.
Ready to connect★ 614
- View details
markuplint-configureSkillFiles & storage
Lets your agent add, remove, or adjust Markuplint rules for specific HTML files or elements.
Ready to connect★ 614
- View details
markuplint-setupSkillDev tools
Lets your agent set up Markuplint in a project, detecting the framework and creating a lint config.
Ready to connect★ 614
- View details
migrate4-5SkillFiles & storage
Lets your agent update markuplint config files and tests from v4 to v5, confirming breaking changes with you first.
Ready to connect★ 614
- View details
migrate4-5-legacy-pathSkillDev tools
Points your agent to the current location of the markuplint v4-to-v5 migration skill.
Ready to connect★ 614
- View details
qa-engineerSkillDev tools
A skill for performing code reviews and test quality checks as a QA engineer. Improves code coverage, detects test-faking code, catches swallowed exceptions, flags conditional logic in tests, promotes hardcoded assertions, and checks cross-platform/cross-runtime compatibility (Windows, Deno, Bun). L
Ready to connect★ 614
- View details
sponsorsSkillWeb & browsing
Lets your agent check active GitHub Sponsors and update README or website sponsor lists to match.
Ready to connect★ 614
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.
54,082 of the 54,514 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.