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
54,017 results · page 175 of 1,801
- View details
api-endpointsSkillAI & models
Lets your agent define or update API operations that generate endpoints, SDK methods, and tools from one schema.
Ready to connect★ 5k
- View details
architecture-boundariesSkillMonitoring & ops
Lets your agent review code for architecture issues like layering, boundaries, multi-tenancy, and common anti-patterns.
Ready to connect★ 5k
- View details
artifact-designerSkillFiles & storage
Lets your agent create, check, and publish self-contained HTML pages like dashboards, reports, and prototypes.
Ready to connect★ 5k
- View details
async-jobs-and-eventsSkillCommunication
Lets your agent set up background job queues and event notifications instead of doing slow work inside HTTP handlers.
Ready to connect★ 5k
- View details
backofficeSkillAI & models
Lets your agent add, change, or protect admin-only backoffice features behind role checks.
Ready to connect★ 5k
- View details
ci-watchdogSkillMonitoring & ops
Lets your agent watch CI checks on GitHub pull requests and automatically fix failures until they pass.
Ready to connect★ 5k
- View details
database-clickhouse-weaviateSkillDatabases & data
Lets your agent query ClickHouse databases, run Goose migrations, and set up chdb test schemas.
Ready to connect★ 5k
- View details
database-postgresSkillDatabases & data
Lets your agent set up and manage Postgres databases, including schemas, migrations, queries, and row mapping code.
Ready to connect★ 5k
- View details
effect-and-errorsSkillAI & models
Helps your agent write Effect-style code with domain errors, HttpError, and error handling at HTTP boundaries.
Ready to connect★ 5k
- View details
env-configurationSkillAI & models
Lets your agent read and add environment variables, update .env.example, and validate config at startup.
Ready to connect★ 5k
- View details
explain-diff-htmlSkillAI & models
Lets your agent turn a code diff, branch, or PR into an HTML page explaining the change.
Ready to connect★ 5k
- View details
fix-datadog-issuesSkillMonitoring & ops
Lets your agent find production errors in Datadog, investigate them, fix the code, and open a pull request.
Ready to connect★ 5k
- View details
gh-issueSkillAI & models
Lets your agent create well-structured GitHub issues for bugs, features, and improvements.
Ready to connect★ 5k
- View details
managing-maintenance-windowsSkillAI & models
Lets your agent turn your site's maintenance mode on or off, sending visitors to a status page.
Ready to connect★ 5k
- View details
mintlify-previewSkillAI & models
Lets your agent run the Mintlify docs site locally so you can preview doc pages and navigation as you edit them.
Ready to connect★ 5k
- View details
notificationsSkillCommunication
Lets your agent send notifications to users across in-app and email channels with per-user preferences.
Ready to connect★ 5k
- View details
production-releaseSkillCloud & infra
Lets your agent prepare a production release by pushing version tags, running the release script, and updating the changelog.
Ready to connect★ 5k
- View details
review-pr-commentsSkillAI & models
Lets your agent go through pull request review comments and reply to each one in the right thread.
Ready to connect★ 5k
- View details
temporal-developerSkillAI & models
Helps your agent write, debug, and fix Temporal workflow code in Python, TypeScript, or Go.
Ready to connect★ 5k
- View details
toolchain-commandsSkillCloud & infra
Lets your agent install dependencies, run builds, tests, and lint, manage git hooks, and start local dev services.
Ready to connect★ 5k
- View details
web-frontendSkillMedia
Guides your agent in building and editing web app UI with routes, forms, and Tailwind styling.
Ready to connect★ 5k
- View details
excalidraw-diagramSkillDocs & knowledge
Lets your agent turn text into Excalidraw diagrams saved as Obsidian, standard, or animated files.
Ready to connect★ 5k
- View details
mermaid-visualizerSkillDocs & knowledge
Lets your agent turn text into Mermaid flowcharts, mindmaps, and other diagrams that render correctly.
Ready to connect★ 5k
- View details
academic-paper-reviewerSkillAI & models
Lets your agent simulate a peer review of an academic paper with ratings and revision feedback.
Ready to connect★ 5k
- View details
audit-flowSkillDatabases & data
Lets your agent trace system flows across code, APIs, auth, data, and network layers and export them as diagrams.
Ready to connect★ 5k
- View details
authentication-patternsSkillDatabases & data
Guides your agent through implementing and reviewing app authentication, comparing sessions, JWT, and OAuth.
Ready to connect★ 5k
- View details
broken-authenticationSkillSecurity
Lets your agent test web app login systems for weaknesses like weak passwords and session flaws.
Ready to connect★ 5k
- View details
burp-suite-testingSkillSecurity
Lets your agent intercept and modify web traffic and scan web apps for vulnerabilities using Burp Suite guidance.
Ready to connect★ 5k
- View details
cachingSkillAI & models
Guides your agent in designing and reviewing caching strategies like TTLs, cache keys, invalidation, and when not to cache.
Ready to connect★ 5k
- View details
chart-imageSkillWeb & browsing
Lets your agent turn data into PNG chart images like line, bar, pie, and heatmap graphs.
Ready to connect★ 5k
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.
53,585 of the 54,017 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.