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
agent-cleaner-skills
Identify unused Codex skills and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up / slim / 瘦身 their Codex skills or MCP servers, audit which are unused, or recover context budget.
agent-cleaner-skills
Identify unused Claude Code skills, subagents, and MCP servers and disable them to reduce system-prompt context bloat. Use when the user asks to clean up / slim / 瘦身 their installed skills, subagents, or MCP servers, audit which are unused, or recover context budget.
virtual-piano
Show a virtual piano to play music
text-spinner
Spin the given text on my head.
send-email
Send an email.
self-mirror
个人言行修炼批判镜。基于模型在持续观察中自动建立的人格画像(现实自我/理想自我),逐字分析其本人语音转写,反讨好但不对抗地指出言行与理想方向的差距、给出可直接使用的替代说法,并在用户自我否定或处于危机时优先给予支持。
restaurant-roulette
Show a roulette wheel to allow user to randomly select a restaurant based on location and cuisine.
query-wikipedia
Query summary from Wikipedia for a given topic.
qr-code
Generates a QR code for the given url.
mood-tracker-lite
A lightweight mood tracking skill that stores and visualizes your daily emotional state. Log moods, view history, and see trend analysis with an interactive dashboard.
mood-music
A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
kitchen-adventure
Act as a dungeon master for a text-based adventure set in a world where everyone is a sentient kitchen appliance. Trigger when user says "start kitchen adventure".
interactive-map
Show an interactive map view for the given location.
calculate-hash
Calculate the hash (SHA-256, MD5) of a given text string. Useful for verifying data integrity, generating unique identifiers, or cryptographic demonstrations.
workflow-review
Skeptical auditor review. Answer ready-for-public-release for the scope. Summary is a findings table plus a hunt-results table. Ignore prior reviews unless named. Load skills from the Section 3 table. Locked finding How. Default runs tests; static on explicit reduced scope. Use on /review.
workflow-review-loop
Review and remediate in a loop until findings are resolved. Use on /review-loop or when user wants review+fix cycles without a plan.
workflow-requirements
Record an atomic, contradiction-free requirement list as REQ-<AREA>-<TOPIC> (shall / shall not / shall exhibit). The ID names the subject. Context prose gets no ID. Implementation-far. Use on /requirements, or before /plan when none exist. Use existing artifacts when the user already supplied them.
workflow-port-dotnet-rust
Port a .NET/C# solution to Rust as a complete, content-equivalent port. Phase 0 intake and machine inventory, Phase 1 human alignment into port/MANIFEST.md, Phase 2 autonomous loop, Phase 3 closing audit. Full books: every public member, behavior item, and .NET test booked with a closed status set. Use on /port-dotnet-rust, when porting .NET or C# to Rust, or when port/** is in scope.