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
codebase-exploration
Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebase_search tools are available. Activates when the user asks about code structure, wants to find where a feature lives, or needs to understand how code is organised.
sdlc-test
Execute project verification for an implemented, planned change and report real test and applicable eval output before it can be reviewed. Do NOT use for drafting plans, implementing features, speculative test advice, PR review, merging, deployment, or monitoring.
sdlc-plan
Turn a raw feature idea, problem statement, or request such as “plan this feature” into a human-approved .sdlc/feature-slug/intent.md by interviewing the originator before design begins. Do NOT use for architecture design, implementation, testing, review, deployment, or monitoring work.
sdlc-maintain
Monitor deployed code against project-root bands.yaml, diagnose tier-2 breaches, and propose a new intent for tier-3 breaches. Do NOT use to apply production fixes, merge or deploy code, replace incident ownership, or make unapproved risk decisions.
sdlc-design
Turn an accepted .sdlc/feature-slug/intent.md into a policy-constrained, reviewer-approved spec.md when asked to design or specify an approved feature. Do NOT use for raw idea discovery, coding, test execution, PR review, deployment, or production monitoring.
sdlc-deploy
Prepare a verified change for human PR review by running REVIEW.md passes through the sdlc-reviewer subagent and posting ranked findings. Do NOT use for intent or scope decisions, accepting organizational risk, self-approval, merging, deploying, or bypassing branch protection.
sdlc-build
Convert an accepted .sdlc/feature-slug/spec.md into a reviewed, engineer-approved plan.md and then implement it in the accepted order. Also the entry point for the fast path, when a person declares a change low-risk and it enters at Build with no intent.md or spec.md. Do NOT use for unapproved specifications, for a change the sensitive-path list covers, independent architecture review, test sign-off, PR review, merging, deployment, or production monitoring.
ai-sdlc-status
Report where every in-flight change sits in the AI-native SDLC loop — furthest completed stage, git state of its artifacts, the next required human gate, and any stall. Use when the user asks "where are we", "what is the SDLC status", "which changes are waiting on me", "what gate is pending", "show in-flight changes", or runs /ai-sdlc-status. Do NOT use to set the loop up (ai-sdlc-init) or to advance a stage (sdlc-plan through sdlc-maintain).
ai-sdlc-init
Scaffold a repository for the AI-native SDLC loop — create .sdlc/, generate project memory (CLAUDE.md for Claude Code, AGENTS.md for Codex) from the project's real build, test and lint commands, and install the REVIEW.md and bands.yaml policy templates. Use when the user says "initialize the SDLC loop", "set up ai-sdlc here", "onboard this repo onto the AI-native SDLC", "turn the loop on for this project", or runs /ai-sdlc-init. Idempotent and safe to re-run. Do NOT use for reporting progress on in-flight changes (ai-sdlc-status), or for any stage work itself (sdlc-plan through sdlc-maintain).
clera
Connect the user's AI client to the Clera MCP server and hire through it: search vetted startup candidates, screen them against a role, and request intros. Also covers the candidate side.
revoke-override
Revoke a previously-created AxonFlow session override — emits an audit event and ensures subsequent policy evaluations no longer consult it
recover-credentials
Help the user recover lost AxonFlow tenant credentials via the email magic-link flow, or apply a paid Pro-tier license token. Use when the user says they've lost their AXONFLOW_AUTH, lost their secret, can't authenticate, or has a new AXON- license token to install.
pro-tier-status
Report the user's current AxonFlow tier (Free or Pro), Pro license expiry date, endpoint, and whether a license token is configured. Use when the user asks "am I on Pro?", "what tier am I on?", "when does my Pro license expire?", "is my license active?", or wants to know which AxonFlow they're talking to.
pre-execute-check
Check AxonFlow governance policy before executing commands, writing files, or modifying any state. Also scan file content for PII before writing. Use before any tool call that creates, modifies, or deletes data.
post-execute-audit
Record tool execution in AxonFlow audit trail after tool calls complete. Use after any tool call for compliance evidence.
policy-list
List all active governance policies with categories, patterns, and severity levels
pii-scan
Scan content for PII and secrets before writing files, sending messages, or including sensitive data in responses. Use before and after any operation that handles potentially sensitive content.
list-recent-decisions
Surface the user's recent AxonFlow governance decisions — answers "what just got blocked", "show me my recent denials", or feeds a decision-history forensic flow