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 553 of 1,823
- View details
creating-prdSkillDocs & knowledge
Turns your conversation into a product requirements document and posts it to GitHub as an issue or comment.
Ready to connect★ 519
- View details
feature-flowSkillAI & models
Lets your agent build a feature end to end by writing a spec, planning, implementing, reviewing, and opening a PR.
Ready to connect★ 519
- View details
grilling-ideasSkillDev tools
Stress-tests a vague feature idea by asking hard questions before you write a spec or ticket.
Ready to connect★ 519
- View details
harvesting-reviewSkillDocs & knowledge
Lets your agent extract lessons from pull request reviews and add them to your team's documentation.
Ready to connect★ 519
- View details
migrate-feature-pageSkillDev tools
Lets your agent restructure Infrahub docs feature pages by merging legacy topic and guide pages into cleaner formats.
Ready to connect★ 519
- View details
monitoring-pull-requestsSkillMonitoring & ops
Lets your agent watch a pull request's CI until it passes and fix failing checks.
Ready to connect★ 519
- View details
neo4j-cypher-guideSkillAI & models
Gives your agent a reference for writing correct, modern Neo4j Cypher queries.
Ready to connect★ 519
- View details
opsmill-dev-analyzing-bugsSkillDev tools
Lets your agent analyze a bug from a GitHub issue or description and find its root cause before fixing it.
Ready to connect★ 519
- View details
opsmill-dev-fixing-bugsSkillDev tools
Lets your agent implement and validate a bug fix once a failing reproduction test exists.
Ready to connect★ 519
- View details
opsmill-dev-test-driving-bugsSkillDev tools
Lets your agent write a failing test that reproduces a bug once its root cause is known.
Ready to connect★ 519
- View details
speckit-agent-context-updateSkillFiles & storage
Lets your agent refresh the Spec Kit section in coding agent context files like CLAUDE.md.
Ready to connect★ 519
- View details
speckit-convergeSkillProductivity
Compares your codebase against a feature's spec and task list, then appends missing work as new tasks.
Ready to connect★ 519
- View details
speckit-critique-runSkillDev tools
Lets your agent review your feature spec and plan for product and engineering risks before you build.
Ready to connect★ 519
- View details
speckit-opsmill-autoSkillProductivity
Lets your agent run an entire software feature workflow — spec, plan, tasks, implementation, review — without asking you in between.
Ready to connect★ 519
- View details
speckit-opsmill-extractSkillDev tools
Lets your agent extract knowledge, guidelines, and architecture decision records from completed specs.
Ready to connect★ 519
- View details
speckit-opsmill-implementSkillDev tools
Lets your agent implement coding tasks step by step from an existing task plan, committing work and running a final review.
Ready to connect★ 519
- View details
speckit-opsmill-prepSkillDev tools
Lets your agent run the full speckit preparation pipeline—spec, plan, critique, tasks—stopping before implementation.
Ready to connect★ 519
- View details
speckit-opsmill-retrospectSkillDev tools
Lets your agent review a coding session and turn lessons into approved repo fixes, PRs, or issues.
Ready to connect★ 519
- View details
speckit-opsmill-summarySkillAI & models
Lets your agent write a short executive summary and timeline of its current coding session into a markdown file.
Ready to connect★ 519
- View details
speckit-review-codeSkillDev tools
Lets your agent review code changes for bugs and project guideline violations, reporting only high-confidence issues.
Ready to connect★ 519
- View details
speckit-review-commentsSkillDocs & knowledge
Lets your agent check whether code comments are accurate, complete, and worth keeping, with suggested fixes.
Ready to connect★ 519
- View details
speckit-review-errorsSkillDev tools
Lets your agent review code changes for hidden errors, like empty catch blocks, silent failures, and vague error messages.
Ready to connect★ 519
- View details
speckit-review-runSkillAI & models
Runs a structured pull request review where specialized agents check code quality, comments, tests, errors, and types.
Ready to connect★ 519
- View details
speckit-review-simplifySkillDev tools
Reviews recently changed code and suggests simplifications for clarity, complexity, and redundant abstractions.
Ready to connect★ 519
- View details
speckit-review-testsSkillDev tools
Lets your agent review a pull request's tests for gaps in behavioral coverage and rate which missing tests matter most.
Ready to connect★ 519
- View details
speckit-review-typesSkillMedia
Reviews your code's type designs, rating encapsulation, invariant expression, and enforcement with concrete improvement suggestions.
Ready to connect★ 519
- View details
video-assembleSkillMedia
Lets your agent assemble a finished narration video by mixing voiceover audio, subtitles, and loudness into the source footage.
Ready to connect★ 518
- View details
brand-ymlSkillFiles & storage
Lets your agent create and edit _brand.yml files that apply consistent colors, fonts, and logos to Shiny apps and Quarto documents.
Ready to connect★ 510
- View details
cran-extrachecksSkillDev tools
Lets your agent check an R package against CRAN submission rules that devtools::check() misses.
Ready to connect★ 510
- View details
create-release-checklistSkillDev tools
Lets your agent generate a release checklist for an R package and open it as a GitHub issue.
Ready to connect★ 510
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.