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 196852
imhex
Use when hex editing, binary analysis, pattern language parsing, file identification, hash computation, or hex dump generation is needed. ImHex provides a powerful CLI and pattern language for structured binary data inspection.
imagegen
Use when asked to generate or edit images via the OpenAI Image API (generate, edit/inpaint/mask, background removal/replacement, transparent background, product shots, concept art, covers, batch variants); run `scripts/image_gen.py`, needs `OPENAI_API_KEY`. NOT for video (use sora) or Grok Imagine (use accurate-grok-imagine).
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 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. NOT for a single binary on the already-installed server (use ida-pro-mcp); the Reversecore mega-bundle stays PARKED.
ida-decompiler-cleanup
Use when Hex-Rays decompiler output in IDA Pro is noisy, poorly typed, or hard to reason about, especially for indirect-call typing, prototype cleanup, structure naming, variable cleanup, and preparing functions for durable analysis or signature work.
humanizer
Use when editing or reviewing text to remove AI-writing patterns (em dashes, filler phrases, passive voice, inflated symbolism) and make it sound more natural and human-written ; do NOT use for full 5-pass rewrite workflows or voice-matching (use agentic-humanizer) ; returns edited text with AI patterns removed.
hosted-model-agents
Deploy hosted or local models as agent runtimes (Hugging Face router + Hub MCP + Spaces + Endpoints, Modal/RunPod/Lightning, Azure Foundry, Ollama/LM Studio/llama.cpp, Cursor Max/auth2api), register them in .agents/models.json, reach them via the inference-hub MCP (models_list/chat/chat_many) or rendered provider blocks, then attach tools in the local harness. Use when picking where a model runs, wiring OpenAI /v1 or Gradio MCP, or adding tool loops for agents. Any model that emits tool_calls.
hexstrike-ai-setup
Use when installing, wiring, validating, or troubleshooting the local HexStrike AI binary and runtime environment for Codex, Claude, or Gemini ; do NOT use for MCP server registration wiring (use hexstrike-ai-mcp) or running an active authorized engagement (use hexstrike-ai-authorized-engagement) ; returns a validated running HexStrike runtime.
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.
hexstrike-ai-authorized-engagement
Use when routing an authorized security assessment, bug bounty, red-team exercise, or CTF task through the local HexStrike AI runtime ; do NOT use for installation or MCP wiring (use hexstrike-ai-setup or hexstrike-ai-mcp) ; returns HexStrike AI engagement results for authorized targets only.
harness-module-authoring
Author, register, test, or review lifecycle harness modules and hook checks in agent-skills-toolchain. Use when changing ci/harness HookEvent or HookResult modules, hooks/_dispatch/manifest.json checks, fail-open behavior, redaction, persistent side effects, deduplication, calibrated-silence confidence gates, contraindication registry rows, or block-versus-inject policy.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
hacktricks
Retrieve and synthesize HackTricks and HackTricks Cloud guidance for authorized security research, pentests, CTFs, hardening, incident response, reverse engineering, and web, network, Active Directory, mobile, cloud, OS, and protocol techniques. Use when the user names HackTricks or needs a concrete security technique, checklist, command, payload, prerequisite, or defensive reference. Route between the connected hacktricks MCP, the offline corpus, and the quota-limited official HackTricks AI API. Do not use it as current CVE or vendor truth, as authorization to act, or as a substitute for generic library documentation.
hacktricks-api
Query the HackTricks AI for a synthesized, curated answer when the local hacktricks corpus search is not enough. Cached (repeat queries cost nothing) and rate-limit-aware (weekly RAG quota). Covers the same broad domains as HackTricks — security, cloud, web, network, forensics, AI, and general dev. Prefer the local hacktricks skill first; use this to escalate.
grok-lane
Local Grok OpenAI-compatible lane (chenyme/grok2api bridge) - launch, keepalive, model catalog, client wiring and budget caps for grok-4.x models on this estate.
grill-with-docs
Use when stress-testing a plan against the workspace's domain knowledge and prior decisions - challenge terminology, sharpen fuzzy language, and write resolved decisions back. Use when the user says grill against our docs or decisions, or wants a glossary-aware design grill. NOT for a plain plan interview (use grill-me) or a program-scale scope (use grill-me-extensive).
grill-me
Interview the user about a plan or design, resolving each branch of the decision tree. Use when the user wants to stress-test a plan or says grill me. NOT for program-scale or under-specified scopes (use grill-me-extensive).
grill-me-extensive
Program-scale extensive grilling 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, then walk one question at a time with a recommendation, capturing every decision. Modes: expansion, modification, scope-change, modernization, better-ideas, red-team, simplification, prioritization.