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
ida-pro-mcp
Use when installing or configuring mrexodia/ida-pro-mcp for IDA Pro, or when wiring its client config into Codex, Claude Code, or Gemini CLI after the IDA plugin is available.
ida-multi-mcp
Use when you need to analyze SEVERAL binaries in IDA at once through one MCP endpoint, or when you must re-find a function whose address SHIFTED after a rebuild/game-update. Wires MeroZemory/ida-multi-mcp (a distinct, more capable server than the already-installed mrexodia/ida-pro-mcp) and its local BCSD engine — similar_functions / compare_functions rank matches by instruction-shingle MinHash plus API/string/constant anchors plus CFG shape, name-independently (survives stripping), within a binary or across instances. The keystone Battle Cats recipe — open the pinned old IDB and the new .so as two instances, then similar_functions to auto-re-locate the moved offset table after a relink. Additive and opt-in — adds NO hook, gate, or blocking behavior. Reversecore mega-bundle stays PARKED (do not wire).
wds-6-asset-generation
Generate visual and text assets from specifications through AI-powered creative production
hexstrike-ai-mcp
Use when registering, repairing, or configuring HexStrike AI as an MCP server with a framed stdio bridge for Codex, Claude Code, or Gemini CLI ; do NOT use for runtime installation (use hexstrike-ai-setup) or running engagements (use hexstrike-ai-authorized-engagement) ; returns working MCP server registration for HexStrike.
wds-5-agentic-development
AI-assisted development, testing, and reverse engineering through structured agent collaboration
grill-me-extensive
Program-scale extensive grilling — an addon to the grill-me skill for wide or under-specified decision spaces. Scout context, fan out a brainstorm to surface directions beyond the stated ask, structure a categorized decision list, lead with foundational framing questions, then walk one question at a time with a recommendation each and capture every decision durably. Includes grill modes for expansion, modification, scope-change, modernization, better-ideas, red-team, simplification, and prioritization. Use when scoping a program, when the user says "grill me extensively" or "suggest more", or when grill-me alone is too small for the decision space.
ghidra-mcp
Use when installing or configuring GhidraMCP for a local Ghidra workflow, or when bridging its MCP client into Codex, Claude Code, or Gemini CLI after the Ghidra extension is installed.
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