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 388 of 1,808
- View details
cc-reviewSkillSecurity
Lets your agent run a structured code review with quick, full, or security-focused passes.
Ready to connect★ 1k
- View details
cc-rust-devSkillProductivity
Lets your agent follow Rust development standards for Axum and Tokio code, covering modules, errors, async, and testing.
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
- View details
cc-task-stateSkillProductivity
Lets your agent save and recover task progress, including blocked and unfinished steps, in project files.
Ready to connect★ 1k
- View details
cc-time-zone-safetySkillDev tools
Lets your agent check code for time zone mistakes that could corrupt production statistics.
Ready to connect★ 1k
- View details
code-quality-principlesSkillDev tools
Gives your agent a checklist of six code modularity principles when writing, refactoring, or reviewing code.
Ready to connect★ 1k
- View details
external-system-debuggingSkillDev tools
Guides your agent to capture real environment data when debugging code that talks to external systems like browsers or CDNs.
Ready to connect★ 1k
- View details
field-mapping-safetySkillDev tools
Helps your agent avoid mistakes when renaming or converting data fields during code refactoring.
Ready to connect★ 1k
- View details
frontend-devSkillDev tools
Gives your agent coding standards for frontend work, covering Vue 3 conventions, UI style, and TypeScript rules.
Ready to connect★ 1k
- View details
frontend-safetySkillDev tools
Adds safety rules for editing frontend code, covering Vue/React components, page layouts, and overlays.
Ready to connect★ 1k
- View details
go-devSkillDev tools
Gives your agent Go coding guidance on naming, error handling, concurrency, and testing standards.
Ready to connect★ 1k
- View details
java-devSkillDev tools
Gives your agent Java coding guidelines like naming conventions, exception handling, and Spring Boot best practices.
Ready to connect★ 1k
- View details
multi-tenant-safetySkillSecurity
Checks code touching tenant isolation to catch unauthorized cross-tenant access and data leaks.
Ready to connect★ 1k
- View details
ops-safetySkillDatabases & data
Gives your agent safety guidelines when running system-level commands like firewall, service, or database changes.
Ready to connect★ 1k
- View details
payment-callback-safetySkillCommunication
Checks payment callback and webhook code for security risks like forged notifications and tampered amounts.
Ready to connect★ 1k
- View details
pic-businessSkillDev tools
Lets your agent generate business-style infographics with control over style, colors, icons, and layout.
Ready to connect★ 1k
- View details
pic-cartoonSkillAI & models
Lets your agent create hand-drawn cartoon-style infographics from a description and save them as images.
Ready to connect★ 1k
- View details
project-initSkillFiles & storage
Lets your agent set up a new project by generating scaffold files, an AGENTS.md, and repo structure.
Ready to connect★ 1k
- View details
project-scanSkillFiles & storage
Lets your agent scan a repository and generate or update project docs like AGENTS.md, README, Dockerfile and setup scripts.
Ready to connect★ 1k
- View details
python-devSkillDev tools
Gives your agent Python coding standards for style, type annotations, error handling, and testing.
Ready to connect★ 1k
- View details
query-performance-safetySkillDocs & knowledge
Checks your code for slow query patterns like N+1 queries and overly long IN clauses before they cause problems.
Ready to connect★ 1k
- View details
refactor-safetySkillDev tools
Gives your agent a safety checklist to follow when refactoring code so original context isn't lost.
Ready to connect★ 1k
- View details
requirementSkillMedia
Guides your agent through a structured workflow to analyze software requirements and write explicit requirement documents.
Ready to connect★ 1k
- View details
ruanzhuSkillFiles & storage
Lets your agent generate software copyright source code documentation as a DOCX file.
Ready to connect★ 1k
- View details
rust-devSkillDev tools
Gives your agent Rust coding guidelines for Axum and Tokio backends, covering errors, async, modules, and testing.
Ready to connect★ 1k
- View details
size-checkSkillFiles & storage
Lets your agent review changed code for reuse, quality, and efficiency, fix issues, and check file size limits.
Ready to connect★ 1k
- View details
storage-url-safetySkillFiles & storage
Guides your agent in choosing safe file storage URLs so links don't expire or break when using services like S3.
Ready to connect★ 1k
- View details
streaming-export-safetySkillFiles & storage
Helps your agent write code that exports large files without running out of memory or leaving temp files behind.
Ready to connect★ 1k
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.