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 196921
gem-hunt
Use when the user wants to DISCOVER high-value improvements to their OWN agentic workspace/toolkit - new hooks, behaviors, gems, skills, MCPs, or frontier-harness patterns - via a wide multi-lens agent fan-out, then a consolidated adopt/prune decision. The named "agentic-perfection sweep" / "extensive gem search". Triggers: "find more gems", "what are we missing vs other tools".
gcp-compute-foothold
Use when operating the bolt-finance-rides GCP compute primitive - minting cloud-platform SA tokens via VM metadata + serial-port read (IAM/iamcredentials SERVICE_DISABLED), standing up compute/GPU rigs on idle quota (A2 192 vCPU / A100-40GB / L4 x32 / T4 x16, europe-west1), running in-VPC workloads, or re-checking quota/API pre-run. Triggers - gcp-compute-foothold, bolt-finance-rides, SA token mint, metadata token, serial-port token, a2-highgpu, GPU rig on bolt quota, fenti OAuth redundancy.
gateguard
Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.
game-unpack-pe
Use when asked to unpack, unprotect, or extract real code from a protected or obfuscated Windows executable. Applies when a binary shows a stub entry point, packed sections, few imports, or signs of VMProtect, Themida, UPX, or custom packers.
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.
game-frida-trace
Use when asked to trace, intercept, hook, or monitor function calls in a live process using Frida dynamic instrumentation. Applies to game processes, anti-cheat DLLs, or any running Windows/Android process.
game-find-anticheat
Use when asked to identify, map, locate, or analyze anti-cheat components in a game process or binary. Applies both to static pre-launch analysis and runtime behavioral identification.
frontend-design-direction
Set an ECC-specific frontend design direction for production UI work. Use when building or improving websites, dashboards, applications, components, landing pages, visual tools, or any web UI that needs stronger product-specific design judgment.
frontend-a11y
Accessibility patterns for React and Next.js — semantic HTML, ARIA attributes, form labeling, keyboard navigation, focus management, and screen reader support. Use when building any interactive UI component or form.
frida
Use when runtime hooking, device instrumentation, API tracing matters more than static disassembly. NOT for MCP setup (use frida-mcp).
frida-mcp
Use when installing or configuring frida-mcp as an MCP server for live Frida instrumentation in Codex, Claude Code, or Gemini CLI.
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.
format-codex-sessions
Use when Codex rollout JSONL files need to be turned into readable Markdown conversations, transcripts, or chat logs without dumping raw event noise, prompt bulk, or secrets.
forge-discipline
Use when turning a named behavioral pattern (gem, fresh arXiv finding, matured instinct) into an INSTALLED, self-tested Claude Code hook in one pass. A BEHAVIOR forge, not a tool forge - it forges hooks/tripwires the harness runs deterministically, not MCP tools. Scaffolds the hook, runs a chaos self-test proving it fires and fails open on garbage, then stages it with the one-line install.
firecrawl
Web scraping, crawling, structured extraction, site mapping, and change monitoring via the Firecrawl MCP. Use to turn URLs into clean markdown or schema-structured JSON, extract brand identity (colors, fonts, spacing), crawl or map sites, parse local PDFs/Office files, search the web with operators, or monitor pages for changes. Pairs with the Exa MCP (Exa finds by meaning, Firecrawl fetches).
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
figma
Use when fetching Figma design context, screenshots, variables, or assets via the Figma MCP server, or when setting up and troubleshooting the Figma MCP connection ; do NOT use for pixel-perfect full-component implementation from Figma nodes (use figma-implement-design) ; returns Figma design data and MCP setup guidance.
figma-implement-design
Use when the user provides Figma URLs or node IDs and needs production-ready code with pixel-perfect 1:1 fidelity to the design, translating Figma components into project-convention code via the Figma MCP ; do NOT use for generic Figma data fetching or MCP setup (use figma) ; returns implemented component code matching Figma specs.