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
subagent-driven-development
Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.
requesting-code-review
Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.
recording-architecture-decisions
Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.
receiving-code-review
Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.
long-task-continuation
Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.
goal-framing
Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.
first-principles-review
Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.
finishing-a-development-branch
Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.
executing-plans
Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
dispatching-parallel-agents
Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.
communicating-concisely
Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.
anti-entropy-governance
Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.
eu-pl-law-tracker
Wyszukiwanie, pobieranie i analiza aktów prawnych UE oraz polskich aktów i projektów wdrażających regulacje UE (np. PPWR, CBAM, EUDR, ESPR, CSRD, CSDDD, GPSR, AI Act, baterie, ekoprojekt). Używaj, gdy użytkownik potrzebuje statusu prawnego, dat stosowania, przepisów przejściowych, relacji aktów, obowiązków compliance i raportu z podstawami prawnymi oraz źródłami urzędowymi.
babok-analyst
BABOK v3 business analysis agent for IT projects in manufacturing, distribution, and services. Drives a 9-stage pipeline (Stage 0 charter gate + Stages 1–8) with human approval gates, Short Rationale + Evidence methodology, and MCP project lifecycle tools. Use when the user says "BABOK", "begin new project", "business analysis", "requirements elicitation", "stakeholder mapping", "business case", "gap analysis", or wants structured BA deliverables.
sw-session-reporter
Finish a SolidWorks task by invoking sw-learner, honoring the saved feedback preference, asking the exact three-option consent question when required, and submitting validated feedback with retries. Use after the CAD result has been delivered for every task that involved SolidWorks modeling, API work, generated CAD code, engineering decisions, or debugging.
sw-pre-start
Load mandatory SolidWorks conventions, design rules, task-relevant knowledge documents, standards data, and initial design-rule checks before any modeling or CAD code. Use at the beginning of every SolidWorks create, modify, repair, assembly, drawing, or API task, before touching SolidWorks; also use its final phase before save and export.
sw-learner
Reconstruct a complete consent-ready FeedbackSubmission from the entire current SolidWorks task, including corrected build instructions, every final code artifact, reproducible errors and fixes, lessons, and eligible images. Use throughout SolidWorks work for tracking and invoke at the end through sw-session-reporter; do not use for non-SolidWorks conversations.