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
deep-review
The deep five-axis review — correctness, readability, architecture, security, performance — with the quality gate and the GitHub posting format. Slower and more thorough than /code-review.
clarity
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write, rewrite, review, and lint modes.
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.
cerebro-cli
Query the cerebro cortex knowledge base for project context, journal entries, intent/goals, TODOs, and statistics. Use when the user asks about their projects, wants to read journal entries, check goals/intentions, search for TODOs across repos, or get an overview of their activity data. Also use when browsing what the user has been working on across their side projects.
c4-diagrams
Create software architecture diagrams using the C4 model (Context, Containers, Components, Code). Applies Simon Brown's diagramming principles: titles, legends, directional arrows, explicit text, abstractions-first. Use when user asks for architecture diagrams, system diagrams, C4 diagrams, or wants to document software structure.
write-skill
Create or improve a Claude Code Agent Skill (SKILL.md). Use when the user asks to capture a workflow as a skill, create a reusable skill, or turn something we just did together into a skill.
ssh-controlmaster
Use a persistent SSH connection via ControlMaster when running multiple commands against the same remote host, to avoid repeated authentication overhead. Use when about to run several ssh commands in a row against one host.
reflect
Analyze recent session transcripts for the current project and suggest CLAUDE.md improvements. Invoke manually once a month or after a significant stretch of work.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
git-message-style
Vlad's personal conventions for writing commit messages and PR descriptions — subject shape, body rules, vocabulary, and PR body structure. Use when writing a commit message or a PR description in one of Vlad's personal repos (not a team repo with its own convention).
gem-security-update
Fix Dependabot security alerts for Ruby gems. Use when the user shares a GitHub Dependabot URL, asks to fix gem vulnerabilities, or mentions a gem CVE needing a version bump.
export-conversation
Export the current conversation to a markdown file. Use this whenever the user asks to "export", "save", or "write" the conversation to a file, or says something like "export this conversation to X.md".
codex-review
Run a code review using the local OpenAI `codex` CLI. Use ONLY when the user names codex explicitly — "codex review", "run codex on this branch", "what does codex say". Do NOT use for generic review requests like "review my changes" or "look for bugs"; those belong to /code-review, which stays local. This one uploads the diff to OpenAI.
check-screenshot
Find and read the most recent screenshot on the Desktop. Use when the user says "check ss".
grill-me
Stress-test a plan or design through a focused, one-question-at-a-time decision interview. Use only when invoked as $grill-me.
gem-security-update
Remediate Dependabot security alerts for Ruby gems with conservative dependency and toolchain changes. Use only when invoked as $gem-security-update.
fabric-synthetic-data
Generate and upload synthetic data to Microsoft Fabric lakehouse tables. Covers star-schema generation, realistic fake data (names, dates, IDs, transactions), configurable row counts, referential integrity between tables, Parquet export, and OneLake upload. Use when: synthetic data, test data, fake data, sample data, generate tables, populate lakehouse, seed data, mock data.
fabric-semantic-model
Infer and generate Power BI semantic models (TMDL format) from Microsoft Fabric lakehouse tables. Covers star-schema detection, table classification (fact/dimension), relationship inference, DAX measure generation, data type mapping, and deployment via REST API. Use when: create semantic model, build data model, star schema, Power BI model, TMDL, fact table, dimension table.