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

55,257 results · page 166 of 1,842

  • test-anti-patternsSkillFiles & storage

    Audits your test files and produces a severity-ranked report of weak, flaky, or meaningless tests.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • test-gap-analysisSkillDev tools

    Lets your agent check whether existing tests would catch bugs if production code changed and find gaps.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • test-smell-detectionSkillDev tools

    Lets your agent audit your existing test code for formal, research-backed test smells like Mystery Guest and Sleepy Test.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • test-taggingSkillDev tools

    Lets your agent classify existing tests by type and report how they are distributed across categories.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • testability-obstacleSkillFiles & storage

    Helps your agent write deterministic C#/.NET tests by replacing DateTime, random numbers, files and similar inputs with controlled fakes.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • thread-abort-migrationSkillDev tools

    Guides your agent through replacing .NET Thread.Abort calls with cooperative cancellation when upgrading to modern .NET.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • use-igniteui-blazorSkillDev tools

    Lets your agent set up Ignite UI Lite components in Blazor apps, including packages, registration, and themes.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • use-js-interopSkillDev tools

    Guides your agent to write, review, or fix code that lets Blazor web components call JavaScript and vice versa.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • vectorizationSkillDocs & knowledge

    Guides your agent to write and review fast .NET SIMD code that stays correct and safe.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • writing-mstest-testsSkillDev tools

    Helps your agent fix, rewrite, and explain existing MSTest tests for .NET.

    Ready to connect★ 5k

    github.com/dotnet/skills5k stars

    View details
  • cc-workflow-ai-editorSkillAI & models

    Lets your agent build and edit visual AI agent workflows in CC Workflow Studio just by chatting with it.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • ccwf-cliSkillFiles & storage

    Lets your agent render, validate, preview, export, or run workflow JSON files from the terminal using the ccwf command.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • jira-driven-planningSkillSearch

    Lets your agent draft implementation plans split into frontend, backend, and infrastructure using your Jira ticket details.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • next-ideaSkillFiles & storage

    Lets your agent invent product improvement ideas, judge them against a quality bar, and file the winners as GitHub issues.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • next-qaSkillDev tools

    Lets your agent run one round of QA work: steward an open test PR, then build one queued test task and open a PR.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • next-qa-ideaSkillFiles & storage

    Lets your agent scan a codebase for untested behavior and file one QA issue proposing the test to write.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • next-taskSkillSecurity

    Lets your agent run one autonomous coding task: pick a queued issue, build it on a branch, and open a PR.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • pr-review-analysisSkillDev tools

    Lets your agent fetch GitHub PR review comments, check each one against the code, and report which are valid.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • pr-to-mainSkillDev tools

    Lets your agent open a pull request to main in a pnpm monorepo, including creating the required changeset and picking the right PR template.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • pr-to-main-cleanupSkillDev tools

    Lets your agent delete local and remote feature branches after their PR is merged into main.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • workflow-schema-tuningSkillAI & models

    Lets your agent adjust the workflow schema so AI-generated workflows pick the node types and behavior you want.

    Ready to connect★ 5k

    github.com/breaking-brake/cc-wf-studio5k stars

    View details
  • annotating-variantsSkillDev tools

    Lets your agent annotate genetic variants, predict their effects, and convert HGVS nomenclature using tools like Ensembl VEP.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • ask-openmedSkillDev tools

    Routes clinical-data requests to the right OpenMed workflow, checking privacy needs before processing.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • assembling-fhir-bundlesSkillDev tools

    Lets your agent package multiple FHIR R4 health records into one transaction bundle ready to send to an EHR.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • auditing-deid-leakageSkillDatabases & data

    Lets your agent re-check de-identified clinical text for leftover personal identifiers and get a leakage report.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • auditing-deidentification-runsSkillDev tools

    Lets your agent produce a signed, reproducible audit trail showing what patient data was redacted and why.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • auditing-part11-trailsSkillCloud & infra

    Lets your agent create and verify audit trails with signatures and tamper-evidence for regulated medical pipelines.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • auditing-safe-harbor-checklistSkillDocs & knowledge

    Lets your agent check de-identified medical text against the 18 HIPAA Safe Harbor identifier categories.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • auditing-subgroup-fairnessSkillAI & models

    Lets your agent check a medical text model for accuracy differences across demographic groups like sex, age, and race.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k stars

    View details
  • authoring-model-cardsSkillMonitoring & ops

    Lets your agent generate a model card documenting a clinical model's intended use, metrics, limitations, and disclaimers.

    Ready to connect★ 5k

    github.com/maziyarpanahi/openmed5k 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.

54,826 of the 55,257 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