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
54,510 results · page 523 of 1,817
- View details
review-ticketSkillSecurity
Lets your agent review tickets and pull requests through scope, security, architecture, and testing lenses.
Ready to connect★ 567
- View details
sdlcSkillProductivity
Lets your agent pick the next software development step for a task based on your code and files.
Ready to connect★ 567
- View details
security-testSkillSecurity
Lets your agent scan code changes for vulnerabilities and leaked secrets before they merge.
Ready to connect★ 567
- View details
Skill CreatorSkillAI & models
Lets your agent follow a standard for writing new agent skills that use tokens efficiently.
Ready to connect★ 567
- View details
skill-benchmarkSkillAI & models
Lets your agent test a skill's quality by comparing its results against older requirements.
Ready to connect★ 567
- View details
system-design-sessionSkillMedia
Lets your agent run an interactive system design session that turns a product goal into a justified architecture with diagrams and ADRs.
Ready to connect★ 567
- View details
test-loopSkillAI & models
Lets your agent create and maintain end-to-end test suites from acceptance criteria for web and mobile apps.
Ready to connect★ 567
- View details
traceability-auditSkillAI & models
Lets your agent build a report linking requirements, criteria, code, tests, and release artifacts.
Ready to connect★ 567
- View details
uat-signoffSkillAI & models
Lets your agent walk a business approver through a feature demo and record their acceptance signoff.
Ready to connect★ 567
- View details
verify-bugSkillProductivity
Lets your agent verify a fixed bug by running JIRA reproduce steps, comparing before/after, and updating the ticket.
Ready to connect★ 567
- View details
verify-workSkillCloud & infra
Lets your agent check finished feature, bug, UI, API, security, or deployment work against acceptance criteria.
Ready to connect★ 567
- View details
zephyr-coverage-analysisSkillMonitoring & ops
Lets your agent analyze Zephyr test coverage for a Jira story and report metrics and recommendations.
Ready to connect★ 567
- View details
higgsfieldSkillMedia
Helps your agent write and refine video and image generation prompts and pick the right AI model.
Ready to connect★ 566
- View details
ln-64-community-announcerSkillAI & models
Lets your agent draft and post announcements in GitHub Discussions.
Ready to connect★ 565
- View details
svg-diagramSkillAI & models
Lets your agent create SVG flowcharts and architecture diagrams with typography suited to CJK text.
Ready to connect★ 563
- View details
agent-workflowSkillAI & models
Lets your agent plan and coordinate large OpenPost features, refactors, and multi-ticket work with recorded scope and dependencies.
Ready to connect★ 562
- View details
cuelumeSkillDev tools
Lets your agent add and audit OpenPost interaction sounds, catching missing or duplicate UI cues.
Ready to connect★ 562
- View details
deploy-appSkillCloud & infra
Lets your agent deploy an app to a Kubernetes cluster and check that it starts up successfully.
Ready to connect★ 562
- View details
deploy-app-from-localSkillCloud & infra
Lets your agent deploy local code from your machine to a live cloud app.
Ready to connect★ 562
- View details
get-jobSkillDev tools
Lets your agent research a job posting, rewrite your resume for it, and prepare for each interview round.
Ready to connect★ 555
- View details
humaSkillDev tools
Lets your agent write Go REST and RPC APIs with automatic OpenAPI 3.1 documentation using the Echo adapter.
Ready to connect★ 562
- View details
loop-workerSkillProductivity
Lets your agent work through a project's pending milestones one by one, implementing and shipping tasks until done.
Ready to connect★ 562
- View details
mermaidSkillDocs & knowledge
Lets your agent create Mermaid diagrams of systems, components, and dependency flows from descriptions.
Ready to connect★ 562
- View details
mock-clusterSkillCloud & infra
Lets your agent create, inspect, or resize a local mock Kubernetes cluster and deploy the bex operator into it.
Ready to connect★ 562
- View details
openapi-typescriptSkillDev tools
Lets your agent generate TypeScript types and typed API clients from OpenAPI specs.
Ready to connect★ 562
- View details
openpost-cliSkillSecurity
Lets your agent create, edit, and schedule posts on OpenPost, plus check account, billing, and job status.
Ready to connect★ 562
- View details
pm-brainstormSkillFiles & storage
Analyze and decompose a product topic into a text-only proposal for the repository's .pm board. Use when the user wants to pressure-test scope, size milestones, identify dependencies, or prepare exact PM board commands without writing board files.
Ready to connect★ 562
- View details
qa-find-bugsSkillFiles & storage
Drive the live product at https://dashboard.bex.co as a signed-in QA user (QA_EMAIL / QA_PASSWORD from .env), hunt real bugs across the hosting features, research each fix down to file:line, file the non-duplicate findings to the w6 board through /pm, and /ship the scheduled milestone. Use when the
Ready to connect★ 562
- View details
qa-find-bugs-cliSkillFiles & storage
Lets your agent hunt for bugs in a CLI tool and file researched fix reports.
Ready to connect★ 562
- View details
stripe-directorySkillCommerce & finance
Lets your agent search a directory of businesses and services and build a shortlist for your needs.
Ready to connect★ 562
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.
54,078 of the 54,510 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.