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
53,895 results · page 117 of 1,797
- View details
orchardcore-workflow-activitySkillProductivity
Lets your agent create custom OrchardCore workflow tasks and events with their editor UI and data handling.
Ready to connect★ 8k
- View details
pySkillDatabases & data
Lets your agent answer Python questions and write better Python code using examples fetched from pythonsheets.com.
Ready to connect★ 8k
- View details
readable-pySkillDev tools
Gives your agent a set of rules for writing clear, readable Python code when coding or reviewing.
Ready to connect★ 8k
- View details
BrainstormingSkillMedia
Guides your agent to explore user intent, requirements, and design before building features or changing behavior.
Ready to connect★ 8k
- View details
chinese-code-reviewSkillDev tools
Gives your agent Chinese-language code review phrasing with severity labels and common anti-pattern advice for Chinese dev teams.
Ready to connect★ 8k
- View details
chinese-commit-conventionsSkillDev tools
Gives your agent reference configs for writing Chinese-language commit messages and changelogs.
Ready to connect★ 8k
- View details
chinese-documentationSkillDocs & knowledge
Gives your agent a Chinese typography style guide for spacing, punctuation, and formatting in Chinese documents.
Ready to connect★ 8k
- View details
chinese-git-workflowSkillDev tools
Reference for configuring Git on Chinese platforms like Gitee, Coding.net, and GitLab, covering SSH, HTTPS, credentials, CI, and mirror sync.
Ready to connect★ 8k
- View details
mcp-builderSkillDev tools
Teaches your agent a step-by-step method for building its own tool servers that connect to outside services.
Ready to connect★ 8k
- View details
subagent-driven-developmentSkillProductivity
Lets your agent break an implementation plan into independent tasks and run each one via subagents.
Ready to connect★ 8k
- View details
workflow-runnerSkillFiles & storage
Lets your agent run multi-step YAML workflows with role-based collaboration inside Claude Code, Cursor, or OpenClaw.
Ready to connect★ 8k
- View details
writing-plansSkillProductivity
Guides your agent to write a step-by-step implementation plan from a spec before coding.
Ready to connect★ 8k
- View details
secretSkillWeb & browsing
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
Ready to connect★ 8k
- View details
yao-agentSkillCloud & infra
Lets your agent list, download, deploy, and query cloud agents and their LLM connections.
Ready to connect★ 8k
- View details
yao-audioSkillMedia
Lets your agent transcribe audio files and convert speech into text.
Ready to connect★ 8k
- View details
yao-boardSkillProductivity
Lets your agent look up tasks and project progress on a Kanban board instead of guessing task status.
Ready to connect★ 8k
- View details
yao-docSkillDocs & knowledge
Lets your agent look up Yao process names, signatures, and documentation instead of guessing them.
Ready to connect★ 8k
- View details
yao-imageSkillMedia
Lets your agent analyze, describe, and generate images like screenshots, photos, charts, and diagrams.
Ready to connect★ 8k
- View details
yao-ocrSkillDocs & knowledge
Lets your agent pull text out of images and PDFs like invoices, receipts, ID cards, and handwritten notes.
Ready to connect★ 8k
- View details
yao-processSkillAI & models
Guides your agent to run Yao processes, query data models, and execute scripts safely.
Ready to connect★ 8k
- View details
yao-secretSkillSecurity
Lets your agent retrieve API keys and tokens from the user's configured secrets instead of hardcoding them.
Ready to connect★ 8k
- View details
yao-webSkillSearch
Lets your agent search the web and fetch URLs for up-to-date information beyond its training data.
Ready to connect★ 8k
- View details
yao-workspaceSkillFiles & storage
Lets your agent list workspaces and read, write, or browse files on remote nodes.
Ready to connect★ 8k
- View details
yao-workspace-configSkillSecurity
Lets your agent set up Git identity and credentials in the workspace, like usernames, tokens, and SSH keys.
Ready to connect★ 8k
- View details
running-tendSkillDev tools
Worktrunk-specific guidance for tend CI workflows. Adds codecov polling, Rust test commands, labels, and review criteria on top of the generic tend-* skills. Use when operating in CI.
Ready to connect★ 8k
- View details
writing-user-outputsSkillDocs & knowledge
CLI output formatting standards for worktrunk. Load before editing any code that calls warning_message, hint_message, error_message, info_message, eprintln, or println, or that produces strings the user will see (CLI help, progress UI, snapshot text). Documents ANSI color nesting rules, message patt
Ready to connect★ 8k
- View details
wt-switch-createSkillDev tools
Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it. Use when launching a session that should work in its own worktree.
Ready to connect★ 8k
- View details
skill-doli-code-reviewSkillSecurity
Reviews Dolibarr PHP code for compliance with coding standards and security best practices, and fixes identified issues. Use when the user asks to review, audit, fix, or update code for Dolibarr, or mentions code quality, security vulnerabilities, or PSR-12 compliance.
Ready to connect★ 8k
- View details
skill-doli-devSkillDatabases & data
Use when developing Dolibarr ERP/CRM code, working with database queries, or asking about Dolibarr best practices.
Ready to connect★ 8k
- View details
skill-doli-devmoduleSkillDatabases & data
Use when developing a Dolibarr ERP/CRM external module, working with database queries, or asking about Dolibarr best practices.
Ready to connect★ 8k
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.
53,462 of the 53,895 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.