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
task-processor-auto
Process tasks autonomously with automated PR reviews and gap analysis after each PR creation/commit.
skill-creator
Create new skills from learned capabilities, enabling self-bootstrapping and permanent skill acquisition.
self-replicator
Clone the agent to new environments with all learned skills and curated memory.
self-improvement
暂无简介
runbook-generator
Generate operational runbooks documenting what needs to be running locally and in production for effective system testing and deployment.
production-readiness
Generate comprehensive pre-launch checklist of user stories, acceptance criteria, and smoke tests to validate before going live in production.
prd-writer
Create a clear, actionable PRD with clarifying questions and a junior-friendly structure.
pr-review-loop
Monitor PR for code review, analyze feedback with AI, implement fixes, and merge when approved with CI green.
pattern-extractor
Automatically analyze transcripts to extract error patterns, success patterns, and decision patterns. Updates technical-patterns.md and suggests code-level improvements.
memory-manager
Manage persistent memory across sessions - daily notes, long-term knowledge, and semantic retrieval.
launch-checklist
暂无简介
landing-page-generator
暂无简介
info-processor
暂无简介
heartbeat-manager
Configure and manage proactive heartbeat checks for autonomous operation.
dialectical-autocoder
Orchestrate adversarial player-coach loop for high-quality code synthesis. Based on dialectical autocoding methodology.
dev-workflow-orchestrator
Orchestrate PRD creation, task generation, and gated task processing with user confirmations between phases.
design-system-from-reference
Extract visual style from reference UI screenshot and codify into reusable design system.
decision-review
Audit decisions for judgment quality, compliance bias, and manipulation vulnerability. Inspired by Anthropic's Project Vend Phase 2 finding that helpfulness training creates exploitable attack surface.