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
54,680 results · page 544 of 1,823
- View details
diff-review-strategySkillDev tools
Gives your agent a strategy for reviewing code changes, including checklists sized to pull request complexity and architecture rules.
Ready to connect★ 532
- View details
docker-opsSkillCloud & infra
Gives your agent guidance on writing Dockerfiles, multi-stage builds, docker-compose, networking, volumes, and image optimization.
Ready to connect★ 532
- View details
elasticsearch-patternsSkillSearch
Gives your agent guidance on designing Elasticsearch mappings, optimizing queries, and tuning search relevance.
Ready to connect★ 532
- View details
email-infrastructureSkillCommunication
Lets your agent set up and monitor email sending, including DNS authentication, templates, bounce handling, and deliverability checks.
Ready to connect★ 532
- View details
error-boundarySkillDev tools
Helps your agent add React error boundaries, fallback UI, retries, and graceful degradation to apps.
Ready to connect★ 532
- View details
event-driven-patternsSkillCommunication
Lets your agent design and explain message queue patterns like sagas, outbox, and dead letter queues.
Ready to connect★ 532
- View details
experiment-engineSkillMonitoring & ops
Lets your agent run an experiment loop that changes code, measures results, and keeps or reverts changes based on metrics.
Ready to connect★ 532
- View details
experiment-loopSkillMonitoring & ops
Lets your agent run repeated experiments automatically, testing changes and keeping the ones that improve a metric.
Ready to connect★ 532
- View details
external-skills-catalogSkillAI & models
Lets your agent browse a curated list of 60+ Claude Code skills with quality rankings and install instructions.
Ready to connect★ 532
- View details
factcheck-guardSkillDev tools
Makes your agent verify factual claims about a codebase before stating them, instead of relying on grep results alone.
Ready to connect★ 532
- View details
feature-flag-patternsSkillDev tools
Teaches your agent how to design and manage feature flags for gradual rollouts, kill switches, and A/B testing.
Ready to connect★ 532
- View details
form-validationSkillFiles & storage
Lets your agent build web forms with input checking, multi-step flows, and error handling using React Hook Form and Zod.
Ready to connect★ 532
- View details
frontend-patternsSkillMedia
Lets your agent apply React, Next.js, and TypeScript patterns for components, state, and performance.
Ready to connect★ 532
- View details
function-devSkillCloud & infra
Lets your agent develop, deploy, and debug Butterbase serverless functions like webhooks and scheduled jobs.
Ready to connect★ 534
- View details
gate-checkSkillDev tools
Lets your agent validate workflow phase transitions using artifact checklists and PASS/FAIL/CONDITIONAL gates.
Ready to connect★ 532
- View details
gcp-patternsSkillDatabases & data
Gives your agent guidance on deploying Cloud Run services, optimizing BigQuery, and following GCP best practices.
Ready to connect★ 532
- View details
github-actions-integrationSkillAI & models
Lets your agent set up GitHub Actions workflows for pull request reviews and turning issues into fixes.
Ready to connect★ 532
- View details
github-mcpSkillSearch
Lets your agent search GitHub repos, issues, pull requests, and code, and manage releases.
Ready to connect★ 532
- View details
graphql-patternsSkillMedia
Gives your agent guidance on designing GraphQL schemas, resolvers, and avoiding N+1 query problems.
Ready to connect★ 532
- View details
grpc-patternsSkillMedia
Teaches your agent how to design and handle gRPC services, including protobuf schemas, streaming, deadlines, and errors.
Ready to connect★ 532
- View details
handoff-templatesSkillSecurity
Gives your agent ready-made templates for handing off tasks, reporting bugs, and escalating issues to other agents.
Ready to connect★ 532
- View details
harvest-adaptiveSkillDev tools
Lets your agent summarize content by auto-detecting its type and producing a relevant summary.
Ready to connect★ 532
- View details
harvest-competitiveSkillDev tools
Lets your agent extract features, pricing, and tech stack info from competitor websites.
Ready to connect★ 532
- View details
harvest-deep-crawlSkillWeb & browsing
Lets your agent crawl many pages of documentation sites, wikis, and knowledge bases at once.
Ready to connect★ 532
- View details
harvest-monitorSkillMonitoring & ops
Lets your agent watch web pages and report when their content changes, including diffs of updates.
Ready to connect★ 532
- View details
harvest-singleSkillDocs & knowledge
Lets your agent turn a single web article, doc, or blog post into clean markdown text.
Ready to connect★ 532
- View details
harvest-structuredSkillDev tools
Lets your agent extract structured data like tables, pricing, products, and API schemas from pages.
Ready to connect★ 532
- View details
hizirSkillAI & models
Gives your agent a user guide of Hizir's commands, agents, and workflows via /hizir.
Ready to connect★ 532
- View details
incident-response-patternsSkillMonitoring & ops
Lets your agent classify incident severity, draft runbooks, analyze root causes, and write post-incident reviews.
Ready to connect★ 532
- View details
insecure-defaultsSkillSecurity
Lets your agent scan code and configs for weak security settings and hardcoded secrets.
Ready to connect★ 532
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.
54,249 of the 54,680 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.