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 751 of 1,842
- View details
readability-guidanceSkillDev tools
Lets your agent load a shared writing-voice and readability standard so drafted text stays consistent.
Ready to connect★ 267
- View details
spike-consumer-adversarialSkillDev tools
Runs a worst-case early-exit test harness that verifies an agent's skill call keeps going despite final-sounding guidance.
Ready to connect★ 267
- View details
spike-consumer-baselineSkillFiles & storage
Lets your agent build an incident post-mortem and read a readability standard file mid-workflow in a test harness.
Ready to connect★ 267
- View details
spike-consumer-forkedSkillMonitoring & ops
Lets your agent build an incident post-mortem report from supplied data during spike harness trial runs.
Ready to connect★ 267
- View details
spike-consumer-inlineSkillMonitoring & ops
Builds an incident post-mortem from provided trial data while pulling in a readability guidance skill mid-workflow.
Ready to connect★ 267
- View details
spike-guidance-adversarialSkillDev tools
Provides an adversarial test variant of spike guidance for checking how agent skills handle misleading completion prompts.
Ready to connect★ 267
- View details
spike-guidance-forkedSkillDev tools
Lets your agent run a readability-guidance spike payload in a forked context when another spike skill calls it.
Ready to connect★ 267
- View details
spike-guidance-inlineSkillDev tools
Lets your agent inject a shared readability standard into its own context when running a spike.
Ready to connect★ 267
- View details
spike-probeSkillAI & models
Checks whether a newly created project skill is properly loaded into a subagent's context.
Ready to connect★ 267
- View details
stakeholder-summarySkillDev tools
Turns a feature spec into a plain-language summary for non-technical stakeholders.
Ready to connect★ 267
- View details
structurizrSkillDev tools
Lets your agent turn C4 architecture text files into SVG diagrams.
Ready to connect★ 268
- View details
update-depsSkillDev tools
Lets your agent check for dependency updates, upgrade versions in TOML catalogs, and update the Gradle wrapper.
Ready to connect★ 268
- View details
update-pr-descriptionSkillDev tools
Lets your agent write or update a GitHub pull request description based on the changes in the current branch.
Ready to connect★ 267
- View details
work-items-to-issuesSkillFiles & storage
Lets your agent turn a work-items.md file into GitHub issues, one per work slice, in the right repos.
Ready to connect★ 267
- View details
work-items-to-jiraSkillFiles & storage
Lets your agent turn a work-items.md plan file into separate Jira tickets in a project.
Ready to connect★ 267
- View details
work-items-to-linearSkillFiles & storage
Lets your agent turn a work-items.md plan into Linear issues, one per task slice.
Ready to connect★ 267
- View details
qstash-jsSkillCommunication
Lets your agent send scheduled and queued messages to HTTP endpoints using QStash in serverless apps.
Ready to connect★ 267
- View details
Code Review & QualitySkillAI & models
Lets your agent review code quality across five dimensions and give structured feedback.
Ready to connect★ 265
- View details
edge-pythonSkillFiles & storage
Lets your agent write, run, test and package programs in the Edge Python language using the edge command-line tool.
Ready to connect★ 265
- View details
Incremental ImplementationSkillAI & models
Guides your agent to build features in small working slices, checking each one before moving on.
Ready to connect★ 265
- View details
rustdocSkillFiles & storage
Lets your agent write and revise Rustdoc documentation comments in Rust source files.
Ready to connect★ 265
- View details
shift-docsSkillDocs & knowledge
Helps your agent file Shift docs, architecture notes, and tickets in the right place.
Ready to connect★ 265
- View details
Test-Driven DevelopmentSkillAI & models
Guides your agent to write tests first, then code, using the RED-GREEN-REFACTOR cycle.
Ready to connect★ 265
- View details
wechat-article-searchSkillSearch
Lets your agent search WeChat Official Account articles by keyword and get titles, summaries, publish times, sources, and links.
Ready to connect★ 265
- View details
argocd-externalsecret-namespace-permissionSkillCloud & infra
Fixes ArgoCD ExternalSecret sync failures caused by a namespace not being permitted in the project.
Ready to connect★ 264
- View details
art-directSkillDocs & knowledge
Lets your agent read a document and propose art directions with AI image prompts for its visuals.
Ready to connect★ 264
- View details
async-await-null-race-conditionSkillMedia
Helps fix Dart null check errors caused by objects being set to null during async awaits.
Ready to connect★ 264
- View details
aws-v4-signing-custom-headers-gcsSkillFiles & storage
Lets your agent add custom metadata headers to S3-compatible uploads to Google Cloud Storage without signature errors.
Ready to connect★ 264
- View details
bash-herestring-newline-secretsSkillSecurity
Helps your agent fix password failures caused by stray newlines when secrets are created with bash here-strings.
Ready to connect★ 264
- View details
blossom-content-addressed-url-filteringSkillFiles & storage
Helps fix media processing that silently skips video files stored on content-addressed servers due to extension-based URL filtering.
Ready to connect★ 264
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.