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
59,136 results · page 458 of 1,972
- View details
async-task-patternSkillProductivity
Helps your agent run long tasks (over 10 seconds) in the background so they don't get cut off by timeouts.
Ready to connect★ 1k
- View details
bash-styleSkillFiles & storage
Lets your agent follow Bash coding conventions when writing shell scripts, Dockerfiles, Makefiles, or YAML files.
Ready to connect★ 1k
- View details
cc-api-contract-safetySkillDev tools
Gives your agent guidelines for keeping frontend-backend API responses consistent when adding or changing interfaces.
Ready to connect★ 1k
- View details
cc-api-design-safetySkillFiles & storage
Lets your agent design REST API responses safely and avoid flaws when it does design claude skill work for API outputs.
Ready to connect★ 1k
- View details
cc-api-proxy-safetySkillCloud & infra
Lets your agent apply safety rules when writing or reviewing gateway, proxy, WAF, or CDN middleware code.
Ready to connect★ 1k
- View details
cc-async-task-patternSkillProductivity
Lets your agent run long tasks asynchronously so slow jobs avoid timeouts and repeated clicks.
Ready to connect★ 1k
- View details
cc-bash-styleSkillDocs & knowledge
Gives your agent style rules and standard command snippets for writing Bash, shell, Dockerfile, and Makefile code.
Ready to connect★ 1k
- View details
cc-code-quality-principlesSkillDev tools
Lets your agent check code changes against six modularization principles when writing or reviewing code.
Ready to connect★ 1k
- View details
cc-commit-msgSkillDocs & knowledge
Guides your agent to write clear, structured git commit messages for you to use manually.
Ready to connect★ 1k
- View details
cc-core-defensiveSkillDev tools
Guides your agent to make small, safe code edits with targeted checks and no unnecessary abstraction.
Ready to connect★ 1k
- View details
cc-external-system-debuggingSkillSearch
Makes your agent grab real data from external systems like browsers or CDNs before debugging instead of guessing from code alone.
Ready to connect★ 1k
- View details
cc-field-mapping-safetySkillDev tools
Stops your agent from guessing field names wrong when refactoring data mappings like dataIndex, enums, and type conversions.
Ready to connect★ 1k
- View details
cc-fixSkillDev tools
Gives your agent a structured workflow for fixing bugs and debugging code.
Ready to connect★ 1k
- View details
cc-frontend-devSkillDev tools
Gives your agent frontend claude skill guidance: Vue 3 coding standards, TypeScript rules, and UI style constraints.
Ready to connect★ 1k
- View details
cc-go-devSkillProductivity
Gives your agent Go coding conventions for writing source code, package structure, error handling, concurrency, and tests.
Ready to connect★ 1k
- View details
cc-java-devSkillDev tools
Gives your agent Java coding standards for naming, exception handling, and Spring Boot best practices.
Ready to connect★ 1k
- View details
cc-multi-tenant-safetySkillSecurity
Lets your agent run security checks that catch risks of data leaking between tenants.
Ready to connect★ 1k
- View details
cc-new-featureSkillProductivity
Lets your agent run a structured new claude skill workflow for features, from requirements to implementation.
Ready to connect★ 1k
- View details
cc-ops-safetySkillDatabases & data
Gives your agent safety guidelines for shell, services, containers, databases, and deployment operations with rollback and blast-radius thinking.
Ready to connect★ 1k
- View details
cc-payment-callback-safetySkillSecurity
Checks payment webhooks for forgery, replay attacks, and tampered amounts.
Ready to connect★ 1k
- View details
cc-project-initSkillDev tools
Lets your agent set up a new project using the standard project-init flow when invoked with the cc-use-exp prefix.
Ready to connect★ 1k
- View details
cc-python-devSkillAI & models
Lets your agent write Python with type annotations, pytest tests and uv tooling, via a python claude skill.
Ready to connect★ 1k
- View details
cc-query-performance-safetySkillDocs & knowledge
Warns your agent when code risks slow queries like N+1 loops or oversized IN clauses and suggests fixes.
Ready to connect★ 1k
- View details
cc-redis-safetySkillDatabases & data
A redis claude skill guiding your agent to write safe, fast Redis code: SCAN over KEYS, pipeline batching, TTL rules.
Ready to connect★ 1k
- View details
cc-refactor-safetySkillDev tools
Lets your agent refactor Claude skill code with a safety checklist that prevents losing the original context.
Ready to connect★ 1k
- View details
cc-reviewSkillSecurity
Runs a structured code review with your agent using the review claude skill for quick, full, or security passes.
Ready to connect★ 1k
- View details
cc-rust-devSkillProductivity
Rust Claude skill that applies Axum and Tokio coding standards for writing, organizing, and testing Rust code.
Ready to connect★ 1k
- View details
cc-size-checkSkillFiles & storage
Lets your agent review changed code for quality and reuse issues, fix them, and check files against size limits.
Ready to connect★ 1k
- View details
cc-statusSkillProductivity
Lets your agent check Codex configuration and task status in your project.
Ready to connect★ 1k
- View details
cc-streaming-export-safetySkillFiles & storage
Guides your agent to safely export large files like Excel or CSV without running out of memory.
Ready to connect★ 1k
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for how to install
- Best Claude skills for humanizer
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.
59,136 of the 59,136 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 workspace 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.