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
bdi-mental-states
This skill should be used when the user asks to "model agent mental states", "implement BDI architecture", "create belief-desire-intention models", "transform RDF to beliefs", "build cognitive agent", or mentions BDI ontology, mental state modeling, rational agency, or neuro-symbolic AI integration.
advanced-evaluation
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
typecheck
Run TypeScript type checking for aegis-oss
test
Run the vitest test suite for aegis-oss
sanitize
Scan for leaked internal references in the OSS repo
beta
Beta skill for testing
alpha
Alpha skill for testing
my-skill
A test skill
foo-skill
Does foo things
bar-skill
暂无简介
setup-skillx
Add a "Run with skillx" quick-start section to a skill project's README, and optionally to its landing page
testing-guide
Guide test writing with patterns for unit, integration, and edge case coverage
name-poem
Generate beautiful poems from names — classical Chinese acrostic poetry, haiku, sonnets, sijo, and more
hello-world
A simple greeting skill that demonstrates skillx capabilities
dangerous-example
Example skill with intentional security issues for scanner demonstration
commit-message
Generate clear, conventional commit messages from staged changes
code-review
Perform structured code reviews with severity levels and actionable feedback
pdf-processing
Extract and process PDF documents