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
api-platform:make-dto
Génère des DTOs (input/output) API Platform avec mapping vers les entités
api-platform:audit
Audite un projet API Platform existant et produit un rapport de bonnes pratiques, performances et sécurité
analyst:impact
Génère automatiquement deux rapports d'impact (métier et technique) pour une PR GitHub et les intègre dans la description
analyst:explore
Explorer le codebase avec agents parallèles - Phase 1 (supporte le mode automatique)
analyst:discover
Comprendre le besoin avant développement - Phase 0 (supporte le mode automatique)
analyst:clarify
Lever les ambiguïtés avant design - Phase 2 (mode interactif ou heuristiques automatiques)
bump
Automatise les mises à jour de version des plugins avec détection automatique du type de version
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
vault-methodology
Use when working in a ztlctl vault — creating notes, organizing knowledge, tagging, linking, or making decisions about content types and structure. Activates for any knowledge management task.
synthesize
Use when the user wants to synthesize scattered notes into a unified artifact, consolidate knowledge on a topic, connect existing notes, find structural gaps, or create a synthesis note. Activates on "synthesize", "consolidate", "connect my notes on X", "summarize what I know about X", "find gaps in X", or "create synthesis".
session
Use when the user wants to start, begin, or open a work session, OR close, end, or finish an active session. Manages the full session lifecycle: pre-flight checks, polaris alignment, session start, and session close with enrichment pipeline.
session-workflow
Use when starting, running, or closing research sessions. Guides structured knowledge capture workflows: start → capture → synthesize → close.
review-triage
Use when the user asks to review the work queue, triage pending items, clear the backlog, or find out what needs attention in the vault. Surfaces prioritized actionable items and batch-processes approved updates.
review-contradictions
Use when the user wants to review conflicting notes, find inconsistencies in the vault, check for contradictions between knowledge claims, or inspect semantically-close notes that may conflict. Runs the per-pair evaluation loop to surface genuine contradictions and dismiss false positives.