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 292 of 1,808
- View details
video-downloaderSkillMedia
Lets your agent download videos from YouTube and other platforms in different formats and qualities.
Ready to connect★ 2k
- View details
beuiSkillAI & models
Lets your agent find and install animated React UI components like toasts, drawers, and chat interfaces.
Ready to connect★ 2k
- View details
continue-taskSkillFiles & storage
Lets your agent resume a coding task from a saved state file, restoring context and branch where you left off.
Ready to connect★ 2k
- View details
cross-device-diagnoseSkillDocs & knowledge
Guides your agent through diagnosing sync problems between two devices step by step.
Ready to connect★ 2k
- View details
design-auditSkillMedia
Lets your agent scan a codebase for design problems like dead code, complexity, and broken abstractions.
Ready to connect★ 2k
- View details
dual-side-debugSkillMonitoring & ops
Lets your agent read clipboard sync logs on both a Mac and its paired Windows machine to debug sync problems.
Ready to connect★ 2k
- View details
e2e-test-thinkerSkillDev tools
Analyzes your branch's changes and drafts a plan of end-to-end tests to cover them.
Ready to connect★ 2k
- View details
gen-changelogSkillDocs & knowledge
Lets your agent write bilingual release changelogs from your Git history.
Ready to connect★ 2k
- View details
ios-log-diagnoseSkillMonitoring & ops
Lets your agent run the iOS app in a simulator and read its logs itself to diagnose sync bugs.
Ready to connect★ 2k
- View details
local-log-debugSkillFiles & storage
Lets your agent inspect and filter uniclipboard's local JSONL logs to trace what happened during a sync or pairing issue.
Ready to connect★ 2k
- View details
plan-reviewerSkillDocs & knowledge
Lets your agent stress-test a Markdown implementation plan with an independent adversarial review before you build it.
Ready to connect★ 2k
- View details
pr-greenlightSkillMonitoring & ops
Lets your agent run local checks, fix failures, open and push a pull request, and watch CI until it passes.
Ready to connect★ 2k
- View details
refresh-agentsSkillFiles & storage
Lets your agent update the code-structure sections of AGENTS.md to match the current codebase.
Ready to connect★ 2k
- View details
research-then-implementSkillWeb & browsing
Lets your agent research a topic once, save a brief, and build from it instead of repeating work.
Ready to connect★ 2k
- View details
review-strictSkillFiles & storage
Lets your agent do a strict, evidence-based code review of branch or working-tree changes without editing files.
Ready to connect★ 2k
- View details
skill-evolveSkillDev tools
Lets your agent update its own skill instructions by turning solved issues into lessons saved back into the skill file.
Ready to connect★ 2k
- View details
tracing-best-practicesSkillMonitoring & ops
Gives your agent coding rules and best practices for adding tracing and logging to Rust code.
Ready to connect★ 2k
- View details
trigger-prepare-releaseSkillDev tools
Lets your agent kick off a GitHub Actions release workflow with optional version, bump type, channel, and base branch settings.
Ready to connect★ 2k
- View details
wrapSkillDev tools
Lets your agent wrap up a coding session by committing and pushing changes and saving state for the next session to resume.
Ready to connect★ 2k
- View details
zhengxi-viewsSkillDev tools
Lets your agent answer questions about fund manager Zheng Xi's investment views with traceable quotes from his public statements.
Ready to connect★ 2k
- View details
agent-deviceSkillAI & models
Lets your agent control iOS and Android devices and simulators by tapping, typing, scrolling, and taking screenshots.
Ready to connect★ 2k
- View details
e2e-current-prSkillDev tools
Lets your agent generate and run end-to-end test scenarios based on changes in the current pull request branch.
Ready to connect★ 2k
- View details
e2e-defaultSkillCloud & infra
Lets your agent run a built-in end-to-end OTA update test that deploys bundles and checks the app UI.
Ready to connect★ 2k
- View details
hot-updater-agentSkillMonitoring & ops
Lets your agent run and monitor HotUpdater end-to-end test jobs via a local dashboard CLI.
Ready to connect★ 2k
- View details
add-ingestr-sourceSkillProductivity
Guides your agent through adding support for a new data source in the Bruin CLI, from config code to docs and tests.
Ready to connect★ 2k
- View details
bruin-fivetran-migratorSkillDev tools
Lets your agent migrate a Fivetran data connection to a new Bruin ingestr project in guided, review-gated steps.
Ready to connect★ 2k
- View details
bruin-semantic-layerSkillMonitoring & ops
Lets your agent create and edit Bruin semantic layer models, defining metrics, dimensions, joins, and queries in YAML.
Ready to connect★ 2k
- View details
create-dashboardSkillDatabases & data
Lets your agent create and edit data dashboards by writing YAML or TSX definition files with widgets, filters, and SQL queries.
Ready to connect★ 2k
- View details
duplicate-investigateSkillDev tools
Guides your agent to trace and diagnose duplicate rows and failed uniqueness checks in Bruin data pipelines.
Ready to connect★ 2k
- View details
freshness-checkSkillProductivity
Lets your agent investigate why data pipelines are late or stale and trace the problem to the upstream asset.
Ready to connect★ 2k
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.