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
changelog
Use when the user asks to add CHANGELOG.md entries, derive them from commits, or cut a Keep a Changelog and SemVer release.
bro
Use when the user says something was too technical or full of jargon, or asks you to speak and write plainly from now on.
brainstorming
Use when the user asks to build, change, fix, or design something in a project: a feature, a bug fix, a refactor, a data model, or a choice between approaches. Invoke it first, before you explore code or ask questions.
best-practices
Use when current practice or outside evidence can change a decision: comparing approaches, libraries, or patterns against the user's constraints.
align-docs
Use at the end of every task, or when the user asks to align or clean repository docs, task records, or the project's local agent memory; --clean runs a full cleanup.
ai-agent-bench
Use when the user wants to compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
skill-deck
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries
schema-markup-generator
Generate and validate Schema.org JSON-LD, and assess Google rich result eligibility where applicable. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas. Use when asked to "add schema markup", "generate structured data", "JSON-LD", "rich snippets", "FAQ schema", "product markup", "add structured data to my page", "how to get rich snippets", or any structured data task.
geo-optimizer
Audit, improve, and measure visibility in AI search answers from ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Use for GEO, AEO, LLM SEO, AI citation and search crawler audits, AI visibility strategy, buyer-question baselines, brand mentions and fact checks in AI answers, or analysis of supplied Bing AI Performance and Search Console Generative AI reports.
maintain
Use this to find out whether an existing dbt project or semantic layer (dbt, Ossie, SLayer or Cube) is correct against its warehouse, and if not, why. `maintain verify` checks the project as it stands; against a .dex/ snapshot, `maintain check` finds schema, volume, grain, and semantic drift and `maintain reconcile` proposes the fix. Reach for it whenever an existing project is suspected wrong, whether or not anything is known to have changed: "this model is wrong, work out why", "the numbers look too high", "some rows are missing", "this column is empty", "duplicates in my fact table", "the project is broken", "diagnose why this test fails", "a test fails and nobody changed the model", "the dashboard moved but the code did not", "did anything drift", "the row count dropped", "the metric definition changed". Read-only; fixes come back as reviewable diffs and never overwrite hand-written work. Writing the fix, or repairing a model you just edited, is transform's; a data question with no project is explore's.
explore
Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: inventory, column profiles, PII detection, grain and data-quality problems, verified joins, ER diagrams, ad-hoc SQL probes, segmentation, and the semantic layer a repo declares (dbt, Ossie, SLayer, or Cube). Trigger it on an unmet precondition, not on phrasing: if you are about to write or fix SQL against tables whose columns, types, grain, or join keys you have not verified in this session, use this FIRST. That includes dbt work (building a model, fixing one, debugging wrong numbers) whenever the ticket names source tables without spelling out their schema. It applies mid-task too: on reaching a table you have not inspected, stop and use this rather than guess column names. Also for "what's in my duckdb", "is this data any good", "how do these tables relate". Read-only; writes only the .dex/ cache. It does not author the model: transform does, and maintain reconciles a project that has drifted.
editorial-review
This skill should be used when the user asks for a "sensitivity reader", "authenticity reader", "cultural review", "is this portrayal okay", "real people in my novel", "defamation", "can I use song lyrics", "epigraph permission", "permissions", "quote permission", "fair use", "AI disclosure", "do I need to disclose AI", "send to my editor", "editorial round", "Word file for my editor", "editor review copy", "co-author", "collaborate on a book", "shared world", "back up my book", "does this echo my source", "similarity check", "check overlap with my earlier books", or wants to run human editorial, ethics, permissions, or collaboration workflows around a story project. NOT for contracts or selling rights (use publishing), or reader feedback rounds and review copies for readers, including the GitHub review-copy setup (use feedback-triage).
local-mcp-teamchat
Use when the user wants to read or search Microsoft Teams or Slack on macOS or Windows, including channels and DMs. Powered by LMCP, which shows the messages already synced in the desktop apps.
local-mcp-pdf-to-sheet
Use when the user wants to pull data out of one or more PDFs (invoices, bank/credit-card statements, receipts, reports, tables) and put it into a spreadsheet. pdf_read is one of the most-used tools; this codifies the read-PDF → structure → write-Excel workflow. Powered by LMCP on macOS and Windows.
local-mcp-files
Use when the user wants to find, read or create files and Office documents (Word/Excel/PowerPoint/PDF) on macOS or Windows, or browse OneDrive / Google Drive. Powered by LMCP; the tools execute on the device.
local-mcp-email
Use when the user wants to read, search, summarize, draft or triage their Apple Mail / Gmail / Outlook / iCloud email in Apple Mail on macOS. Powered by LMCP's Mail tools, which are macOS-only.
local-mcp-email-to-action
Use when the user wants to deal with their inbox — find what needs a response, draft replies, and turn emails into calendar events or reminders. Captures the common email→read→reply→schedule workflow on macOS (Apple Mail, Calendar, Reminders). Powered by LMCP.
local-mcp-daily-brief
Use when the user asks "what's on my plate today", "catch me up", "morning brief", or wants a summary of their day across calendar, reminders and email. The single most common multi-step automation. Powered by LMCP on macOS and Windows.