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
devspark-evolve-constitution
Analyze PR review findings and codebase patterns to propose constitution amendments with change tracking
api-proxy-endpoint
Create serverless API proxy endpoints that hide API keys and provide a unified backend for the dashboard frontend. Designed for Vercel deployment.
devspark-discover-knowledge
Evidence-based `.knowledge` maintenance discovery — proposes gaps, weak mappings, relationship/alias candidates, contradictions, and historical leakage for human review
skill-discovery
Search for reusable skills across OpenSpace's local registry and cloud community. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.
devspark-discover-constitution
Analyze existing codebase to discover implicit patterns and conventions, then guide user through crafting a constitution via interactive questioning.
delegate-task
Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.
devspark-critic
On demand for one specific material concern — challenge whether the work is wrong about the real system it will run in, such as unimplementable conditions, absent operational controls, and unexamined assumptions about code, dependencies, and failure. Never a default gate.
devspark-create-pr
Draft or update a pull request from the verified code, knowledge, tests, and Git delta.
zip-export-deliverable
Ensures codebase deliverables are properly exported as ZIP archives through a dedicated finalization step
zip-deliverable-finalization
Ensure codebase deliverables are properly packaged as ZIP exports in a dedicated final step
devspark-context-projection
Deterministic Context Projection — traverses ONLY authoritative `.knowledge` relationships (entity relations, constrains/constrained_by, links.references) a small bounded distance from one or more seed ids, for direct inspection/debugging independent of `/devspark-plan`
zero-iteration-failure-analysis
Identify and handle agent failures with 0 iterations as pre-execution system issues
devspark-constitution
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
devspark-commit-audit
Analyze git commit history patterns for contributor velocity, commit hygiene, DORA metrics, AI adoption level, and architecture maturity
write-file-fallback-report
Generate professional documents using write_file when primary data sources fail, leveraging embedded domain knowledge instead of external retrieval
devspark-closeout
Re-decide whether the active route is finished by classifying every open finding against the convergence rule, without re-running verification.
fallback-doc-with-delegation
Generate professional documents after tool failures using shell_agent for complex formats or write_file for simple text/markdown
devspark-clarify
For an existing specification, ask up to 5 targeted clarification questions and encode the answers into the spec. On a work branch, asks in conversation and writes no spec.