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
55,055 results · page 662 of 1,836
- View details
aws-sdk-java-v2-s3SkillFiles & storage
Gives your agent working code patterns for storing and retrieving files in Amazon S3 with Java.
Ready to connect★ 345
- View details
aws-sdk-java-v2-secrets-managerSkillCloud & infra
Gives your agent Java code patterns for fetching and caching AWS Secrets Manager secrets instead of hardcoding credentials.
Ready to connect★ 345
- View details
better-authSkillDatabases & data
Guides your agent in setting up Better Auth authentication for a NestJS and Next.js app with Drizzle ORM and PostgreSQL.
Ready to connect★ 345
- View details
bolderSkillDev tools
Makes your agent restyle a working UI with bolder layouts, motion, and typography for more personality.
Ready to connect★ 344
- View details
bug-fix-briefSkillDocs & knowledge
Lets your agent create a structured bug fix brief with root cause, repro steps, fix options, and a checklist.
Ready to connect★ 345
- View details
chunking-strategySkillMonitoring & ops
Recommends chunk sizes, overlap, and semantic boundaries for RAG systems and evaluates retrieval quality.
Ready to connect★ 345
- View details
colorizeSkillDev tools
Lets your agent add a single accent color to a UI or tone down too many competing colors.
Ready to connect★ 344
- View details
copilot-cliSkillProductivity
Lets your agent hand coding tasks to GitHub Copilot from the terminal, choose models, and resume sessions.
Ready to connect★ 345
- View details
craftSkillDev tools
Lets your agent build a complete UI surface like a dashboard in one shot from a simple request.
Ready to connect★ 344
- View details
delightSkillDev tools
Lets your agent add a couple of tasteful micro-interactions to a working UI so it feels less generic.
Ready to connect★ 344
- View details
docs-updaterSkillDocs & knowledge
Lets your agent update README and CHANGELOG files automatically based on git changes since the last release.
Ready to connect★ 345
- View details
drawio-logical-diagramsSkillFiles & storage
Lets your agent create logical flow and system architecture diagrams as draw.io XML files.
Ready to connect★ 345
- View details
drizzle-orm-patternsSkillDatabases & data
Guides your agent in writing Drizzle ORM code for schemas, queries, relations, transactions, and migrations.
Ready to connect★ 345
- View details
dynamodb-toolbox-patternsSkillMedia
Gives your agent TypeScript patterns for building DynamoDB access layers with DynamoDB-Toolbox, from schemas to queries.
Ready to connect★ 345
- View details
extractSkillMedia
Lets your agent clean up UI code by turning repeated Tailwind classes into components and moving hardcoded values into design tokens.
Ready to connect★ 344
- View details
friction-logSkillFiles & storage
Lets your agent log repo annoyances as labeled GitHub issues or work through open ones.
Ready to connect★ 344
- View details
github-issue-workflowSkillAI & models
Lets your agent resolve GitHub issues end to end, from analysis to commit and pull request.
Ready to connect★ 345
- View details
graalvm-native-imageSkillDocs & knowledge
Gives your agent expert guidance for converting Java apps into fast-starting native executables with GraalVM.
Ready to connect★ 345
- View details
hardenSkillCommunication
Lets your agent audit and fix UI edge cases like empty states, errors, loading, offline, and permissions before launch.
Ready to connect★ 344
- View details
heuristicSkillMedia
Lets your agent score a UI design against Nielsen's usability rules and return a 0-100 usability scorecard.
Ready to connect★ 344
- View details
langchain4j-ai-services-patternsSkillDocs & knowledge
Shows Java developers how to build type-safe AI services and chatbots with LangChain4j patterns.
Ready to connect★ 345
- View details
langchain4j-mcp-server-patternsSkillAI & models
Helps your agent write Java code that exposes AI tools for programs to call.
Ready to connect★ 345
- View details
langchain4j-rag-implementation-patternsSkillSearch
Lets your agent build document Q&A pipelines in Java using LangChain4j RAG patterns.
Ready to connect★ 345
- View details
langchain4j-spring-boot-integrationSkillDocs & knowledge
Shows how to wire LangChain4j AI features into a Spring Boot app with config and dependency injection.
Ready to connect★ 345
- View details
langchain4j-testing-strategiesSkillAI & models
Lets your agent write unit and integration tests, including mock LLM responses, for Java LangChain4j apps.
Ready to connect★ 345
- View details
langchain4j-tool-function-calling-patternsSkillAI & models
Shows your agent how to build Java tools that AI models can call, using LangChain4j annotations and setup patterns.
Ready to connect★ 345
- View details
langchain4j-vector-stores-configurationSkillSearch
Helps your agent configure LangChain4J vector stores for semantic search across databases like Pinecone and pgvector.
Ready to connect★ 345
- View details
memory-md-managementSkillFiles & storage
Lets your agent audit, fix, and improve project memory files like CLAUDE.md.
Ready to connect★ 345
- View details
nestjsSkillDatabases & data
Lets your agent build NestJS server apps with REST or GraphQL APIs, auth guards, Drizzle database schemas, and microservices.
Ready to connect★ 345
- View details
nestjs-code-reviewSkillDatabases & data
Lets your agent review NestJS code for issues in controllers, services, modules, and dependency injection.
Ready to connect★ 345
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.
54,624 of the 55,055 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.