GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
dev
Development workflows for the playwright-cli repository. Use when the user asks about rolling dependencies, releasing, or other repo maintenance tasks.
smart-tree
Intelligent filesystem exploration using the `tree` command. Use this skill when you need to understand a project structure, find relevant files for a task, or map out a codebase before making changes. Replaces naive full-tree dumps with a multi-pass, heuristic-driven approach that minimizes token cost while maximizing structural insight.
smart-tree
Intelligent filesystem exploration using the `tree` command. Use this skill when you need to understand a project structure, find relevant files for a task, or map out a codebase before making changes. Replaces naive full-tree dumps with a multi-pass, heuristic-driven approach that minimizes token cost while maximizing structural insight.
writing-assistant
Help improve and flesh out written text in markdown or plain text files. Use when the user wants writing feedback, style fixes, grammar corrections, or help expanding bullet points into prose. Does not write text from scratch.
workspace
暂无简介
skill-writer
Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.
review
Review code changes for quality, security, and best practices
review-mr
Find the GitLab merge request for the current jj branch and run a code review on it. Use when the user wants to review the MR, review the merge request, review "my MR", or review the current branch's changes on GitLab.
researcher
Research a topic by gathering information from web sources and local files. Use when the user asks to research, investigate, or deep-dive into a subject. Supports incremental research via a research.md file.
repo-init
Initialize a repository with devenv, direnv, and jj (Jujutsu). Use when setting up a new project, initializing a repo, or when the user mentions devenv, direnv, or jj setup together.
planner
Create or refine an implementation plan for a feature or task. Use when the user asks to plan, design an approach, outline steps, or break down a task into an implementation plan. Reads research.md for context and produces a plan.md file.
linear-ticket
Create and maintain Linear issues through the Linear MCP, keeping descriptions short and factual and expressing connections as Linear relations instead of prose. Use when the user asks to create, file, open, or update a Linear ticket/issue, or to link, block, assign, or re-scope one. Supports a fast-path for small tickets and an interactive path that confirms team and project.
copilot
Guide through problems without direct solutions - show imports, API patterns, and documentation
add-mcp
Add an MCP server to the current project. Use when the user wants to add, configure, or enable an MCP server like context7, kubernetes, playwright, storybook, or codegraphcontext.
ponytail
Lazy senior dev mode. Forces the simplest, shortest solution that works: YAGNI, stdlib first, no unrequested abstractions.
ponytail-review
Review a diff for over-engineering. Finds what to delete: reinvented stdlib, needless deps, speculative abstractions. One line per finding.
ponytail-help
Quick reference for ponytail's modes, skills, and commands. One-shot display.
ponytail-gain
Show ponytail measured impact as a scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display.