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
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 192262
gh-cli
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
fixing-accessibility
Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.
explain-your-thinking
Explain the basis for a prior decision or action.
execplan-implement
ExecPlan implementation workflow. Use when implementing ExecPlans and you are the parent agent. Do not use if you are a subagent being delegated to.
dotnet
Mandatory for all C#/.NET work. DO NOT use when delegating C#/.NET work to a subagent, but you MUST explicitly instruct the subagent to activate the dotnet skill in it's prompt. Always use for any work that touches, creates, modifies, reviews, or is likely to touch `.cs`, `.fs`, `.vb`, `.csproj`, `.fsproj`, `.vbproj`, `.sln`, `Directory.Build.props`, `Directory.Build.targets`, NuGet/package config, ASP.NET Core controllers/APIs, xUnit/NUnit/MSTest tests, EF Core, dependency injection, async/performance code, or any `dotnet` CLI command such as `dotnet build`, `dotnet test`, `dotnet run`, `dotnet restore`, or `dotnet format`. This skill takes precedence over workflow skills such as `prd-*`, and `code-review`; load `dotnet` first, then run the workflow skill inside the .NET context.
dotnet-upgrade
Use only when the user explicitly invokes dotnet-upgrade to research, plan, execute, or verify a .NET version upgrade.
dotnet-ui-app
Mandatory for all WinUI 3, Windows App SDK, and Avalonia UI work. Always use whenever a task creates, modifies, reviews, plans, designs, or troubleshoots a WinUI or Avalonia app; touches XAML UI, `.xaml`, `.axaml`, UI code-behind, controls, layout, navigation, windowing, styling, theming, accessibility, input, localization, responsiveness, or UI performance in those frameworks; sets up or checks a development environment; or asks to choose, build, run, package, or deploy a Windows desktop or cross-platform .NET UI app. Load `dotnet` first for C#/.NET project or CLI work, then use this skill for UI-specific guidance. Do not invoke for WPF, .NET MAUI, Uno Platform, or generic C# work unless the task also involves WinUI 3, Windows App SDK, Avalonia UI, or choosing among supported frameworks.
delegate-to-subagents
Pursue a long-running goal in a single session by co-ordinating subagents. Use when the user explicitly asks to delegate, spawn, dispatch, or fan out subagents.
task-wave
Handles tasks.
review-handoff
Helps with review handoffs for code changes and handoffs and reviews and teammate review context.
create-skill
Create or revise portable agent skills with clear triggers, focused instructions, and self-contained resources. Use when creating, modifying, refactoring, or deduplicating a skill or its SKILL.md, or authoring skill evaluations and benchmarks.
commit
Create a well-formed git commit from current changes using session history for rationale and summary. Use when asked to commit, save, or push current changes.
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
code-simplify
Simplify code for clarity and maintainability — reduce complexity without changing behavior
code-review
Strict review of a PR, diff, commit range, branch, staged/unstaged changes, or AI patch. Finds only high-confidence issues introduced or exposed by the reviewed change.
code-review-biaxis
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes - Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
code-modernization
Modernize legacy codebases with a guided, stepwise process that produces an executive brief
caveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".