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
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196926
gem-hunt
Use when the user wants to DISCOVER high-value improvements to their OWN agentic workspace/toolkit — new hooks, behaviors, gems, skills, MCPs, cross-domain techniques, or frontier-harness patterns — via a wide multi-lens agent fan-out, then a consolidated adopt/prune decision. This is the named "agentic-perfection sweep" / "extensive gem search" process. Triggers: "find more gems", "search extensive(ly) for improvements", "agentic perfection", "fan out to explore improvements/hooks", "what are we missing vs other tools", "self-improve the harness". NOT for interrogating ONE existing plan (use grill-me-extensive), NOT for ordinary topic research (use deep-research).
game-re-binary
Use when asked to analyze, reverse engineer, or understand an unknown binary, game executable, or DLL. Applies when the goal is mapping the binary structure, finding notable functions, or understanding what a binary does without running it.
wds-4-ux-design
Transform ideas into detailed visual specifications through scenario-driven design
frida
Use when runtime hooking, device instrumentation, API tracing, or patch-on-the-fly behavior matters more than static disassembly alone.
wds-3-scenarios
Create UX scenario outlines from Trigger Map through structured micro-steps
fresh-context-verify
Use when a value, address, offset, or assumption has become load-bearing and you have relied on it for many steps without an independent check — especially in long reverse-engineering or autonomous-loop work that keeps hitting inconsistencies. Re-derive the value in a FRESH context that cannot inherit your current reasoning, and halt if it disagrees. The structural fix for sunk-cost grinding on a wrong-but-consistent anchor.
wds-2-trigger-mapping
Map business goals to user psychology through structured workshops
firecrawl
Web scraping, crawling, structured extraction, site mapping, and change monitoring via the Firecrawl MCP. Use to turn known or discovered URLs into clean markdown or schema-structured JSON, screenshot pages or extract brand identity (colors, fonts, spacing, components), crawl or map entire sites, harvest docs and cookbooks, run competitive or design research, pull structured data with a schema, parse local PDFs and Office files, search the web with operators and domain filters, monitor pages for meaningful changes, search arXiv and GitHub, or drive an autonomous browse agent. Pairs with the Exa MCP (`web_search_exa`) — Exa finds by meaning, Firecrawl fetches, extracts, crawls, and monitors.
figma
Thin PROJECT overlay on the official Figma MCP skill pack. Use when fetching Figma design context, screenshots, variables, or assets, when writing/generating designs INTO Figma, when mapping components with Code Connect, or when setting up and troubleshooting the Figma MCP connection. The canonical HOW lives in the pack skills (figma-use, figma-design-to-code, figma-generate-design, figma-code-connect); this overlay only carries the mandatory pack-skill gate plus this workspace's implementation conventions and seat caveats.
execution-grounded-bon
暂无简介
wds-1-project-brief
Establish project context - foundation for all design work
diff-blind-test-synth
暂无简介
wds-0-project-setup
Project onboarding - determine project type, complexity, tech stack, and route to correct phase
design-system
Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Emits/consumes the single `.design/` artifact contract and scores on the canonical DESIGN-EVAL v1 rubric (9 dims, 0-4) — the legacy 10-dim 0-10 visual-audit scale is RETIRED.
wds-0-alignment-signoff
Create alignment around your idea before starting the project
design-studio
ONE entry to the whole design pipeline over a running app (Reframe, momentstudio, WebCoder, bilbo) — the mode-routed successor to design-review-loop. Runs the full TCR design-review loop (8 gates, G0 PRIME to G7 VERIFY, revert-gate) plus a thin mode router to jump to one stage — direct (scope, define good, pick a direction, palette/font), audit (a11y/contrast/dead-button UI audit, visual review), mirror (code-to-canvas transpose to Figma), critique (design-critique persona panel), iterate (Figma branch, design tokens), implement (Figma-to-code), verify (re-audit delta), loop (the whole pass), drive (drive/point/interact the live app, to ui-drive), session (interactive restyle of a live element, to design-studio-session). Absorbs the folded design skills' triggers — design review, design system audit, frontend design direction, visual review, mirror to Figma, implement design, drive the app, interactive tweak. NOT for a design DOCUMENT (metaswarm review-design) nor rubric math (ui-audit, critique-panel).
bmad-workflow-builder
Builds workflows and skills through conversational discovery and validates existing ones. Use when the user requests to "build a workflow", "modify a workflow", "quality check workflow", or "optimize skill".
design-studio-session
The interactive-modify capability behind `design-studio session` mode. Use when the owner wants to point at a LIVE element in a running app (Reframe, momentstudio, WebCoder, bilbo) and iteratively restyle it with Claude and Codex — preview candidates as injected style overlays FIRST, resolve the clicked element back to its source file:line, apply ONE scoped micro-commit, incrementally re-audit only the changed screen, and auto-decide KEEP or REVERT through the SAME revert-gate as the batch design-review loop. Do NOT use for a whole-app batch audit (use design-review-loop / ui-audit) or for driving the app without modifying it (use ui-drive).