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
aac-spec
Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".
aac-source-driven-development
Grounds every framework-specific implementation decision in official documentation. Use when writing code that depends on a specific library, framework, or API version, when boilerplate or patterns will be copied across a project, or when the user asks for code that follows current best practices. Every pattern traces back to an authoritative source the user can check.
aac-shipping-and-launch
Prepares production launches. Use when deploying a feature to production for the first time, when releasing a significant change, when migrating data or infrastructure, or when planning a staged rollout with rollback. Pairs with aac-check-implementation-readiness (the pre-launch gate) by handling the actual ship discipline.
aac-shard-doc
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document
aac-review-verification-loop
Review workflow: Verification Loop Workflow
aac-review-security-audit
Perform STRIDE and OWASP Top 10 security assessment
aac-review-pr-analyzer
Multi-phase PR analysis specialist. Gathers context, analyzes diffs for patterns and risks, and outputs structured findings. Autonomous — runs during kanban In-Progress → Review transitions.
aac-review-eval-harness
Review workflow: Eval Harness Workflow
aac-review-eng-execution-review
Lock down execution architecture, data flows, and edge cases
aac-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
aac-review-e2e-testing
Review workflow: E2E Testing Workflow
aac-review-desk-check
Quick pre-implementation desk-check verification. Validates that artifacts are implementation-ready before work begins. Autonomous — runs during kanban transitions without user interaction.
aac-review-design-dimension-audit
Audit UX design against strict dimensions on a 0-10 scale
aac-review-coding-standards
Review workflow: Coding Standards Workflow
aac-review-ceo-scope-review
Challenge scope ambition and recommend expansion, holding, or reduction
aac-review-api-design
Review workflow: API Design Review Workflow
aac-review-adversarial-general
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
aac-retrospective
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"