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
54,221 results · page 129 of 1,808
- View details
web-proto-editorialSkillDev tools
Lets your agent build web pages with a warm solid-color canvas, serif headings, and simple body text.
Ready to connect★ 9k
- View details
web-proto-softSkillDev tools
Lets your agent build Apple-style web pages with soft gradient backgrounds, layered tilted cards, and springy buttons.
Ready to connect★ 9k
- View details
video-shotcraftSkillWeb & browsing
Lets your agent turn a webpage or frontend project into a cinematic product video with music-synced cuts.
Ready to connect★ 9k
- View details
add-ai-integrationSkillCloud & infra
Guides your agent through adding or editing AI provider integrations in the Sentry JavaScript SDK.
Ready to connect★ 9k
- View details
add-cdn-bundleSkillWeb & browsing
Lets your agent create a new CDN bundle for a browser package with chosen features.
Ready to connect★ 9k
- View details
bump-conventionsSkillMonitoring & ops
Lets your agent update the @sentry/conventions dependency to a new version across all packages in the monorepo.
Ready to connect★ 9k
- View details
bump-size-limitSkillMonitoring & ops
Lets your agent raise bundle size limits in .size-limit.js when CI size checks fail.
Ready to connect★ 9k
- View details
dotagentsSkillMonitoring & ops
Lets your agent install, update, remove, and list agent skills and manage their configuration.
Ready to connect★ 9k
- View details
e2eSkillMonitoring & ops
Lets your agent run end-to-end tests for Sentry JavaScript SDK test applications.
Ready to connect★ 9k
- View details
fix-issueSkillMonitoring & ops
Lets your agent attempt a small fix for a Sentry JavaScript GitHub issue and open a pull request.
Ready to connect★ 9k
- View details
linear-project-statusSkillMonitoring & ops
Lets your agent analyze a Linear project and produce a health and status summary for its lead or manager.
Ready to connect★ 9k
- View details
linear-project-updateSkillMonitoring & ops
Lets your agent draft and, with your approval, post status updates to your Linear project.
Ready to connect★ 9k
- View details
port-span-namesSkillMonitoring & ops
Rewrites tracing span names to remove raw URLs and IDs so they follow low-cardinality conventions.
Ready to connect★ 9k
- View details
skill-scannerSkillMonitoring & ops
Lets your agent scan other agent skills for security issues.
Ready to connect★ 9k
- View details
track-framework-updatesSkillMonitoring & ops
Lets your agent compile a weekly digest of releases, discussions, and RFCs for the Sentry JS SDK's frameworks.
Ready to connect★ 9k
- View details
upgrade-depSkillMonitoring & ops
Lets your agent upgrade dependency versions in the Sentry JavaScript SDK codebase.
Ready to connect★ 9k
- View details
vendor-otelSkillMonitoring & ops
Lets your agent copy an OpenTelemetry instrumentation package into the Sentry JavaScript SDK source.
Ready to connect★ 9k
- View details
write-testsSkillWeb & browsing
Lets your agent write unit and end-to-end tests, fix failing tests, and add coverage for your code.
Ready to connect★ 9k
- View details
appstoreSkillDev tools
Lets your agent prepare and validate a MiaoYan Mac App Store build.
Ready to connect★ 9k
- View details
lintSkillDev tools
Lets your agent run SwiftLint and swift-format checks on Swift code to report style and lint issues.
Ready to connect★ 9k
- View details
miaoyanSkillDocs & knowledge
Lets your agent create, edit, organize, and present notes in the MiaoYan Markdown note app.
Ready to connect★ 9k
- View details
agent-tuningSkillAI & models
Lets your agent adjust its model choice, effort level, adapter mappings, and eval candidate settings.
Ready to connect★ 8k
- View details
branch-sync-and-push-safetySkillDev tools
Lets your agent safely sync local git branches, rebase, recover custody, and push without force-push mistakes.
Ready to connect★ 8k
- View details
ci-monitorSkillMonitoring & ops
Lets your agent monitor CI checks, handle timeouts, and rerun failing checks on pull requests.
Ready to connect★ 8k
- View details
daemon-runtimeSkillMonitoring & ops
Lets your agent manage background daemon tasks like startup, shutdown, logging, and event subscriptions.
Ready to connect★ 8k
- View details
documentation-guidanceSkillDocs & knowledge
Lets your agent update documentation ownership and generated guidance settings when docs change.
Ready to connect★ 8k
- View details
eval-corpusSkillFiles & storage
Guides your agent when editing eval capture, gold labels, tune sets, matching, replay storage, or the eval CLI.
Ready to connect★ 8k
- View details
gate-worktree-git-safetySkillDev tools
Guides your agent to safely handle Git worktrees, gate containment, and GitHub PR targeting without mistakes.
Ready to connect★ 8k
- View details
no-mistakesSkillProductivity
Runs your code changes through automated review, tests, lint, and CI before pushing them and opening a pull request.
Ready to connect★ 8k
- View details
pipeline-review-and-agentsSkillAI & models
Helps your agent review session changes, find decisions, handle agent timeouts and test behavior.
Ready to connect★ 8k
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.
53,789 of the 54,221 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.