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 196892
re-triage-preflight
Run a fast, hash-cached reverse-engineering TRIAGE preflight on an unknown binary BEFORE deep analysis — folds file-format detection, Shannon-entropy packer triage (works with zero external tools), Detect-It-Easy (diec), FLOSS auto string-deobfuscation, and capa capabilities into ONE structured TRIAGE block, cached by SHA-256 so re-runs are instant. Use when you are about to reverse a native binary (PE/ELF/Mach-O/DEX/.so), triage an unknown/suspicious file, check whether a sample is packed/obfuscated, or want a cheap first-pass before opening IDA/Ghidra/radare2. Advisory only — never blocks, degrades gracefully when a tool is missing. Inert until an RE context. Triton dynamic-taint and VulnHuntr/objdiff+m2c are documented opt-in follow-ons; the revula mega-bundle is rejected.
bmad-create-prd
Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD"
re-ensure
Bring up the reverse-engineering MCP backends (IDA / Ghidra) on demand so mcp__ida-pro-mcp / mcp__ghidra-mcp / mcp__binary-ninja-mcp calls "just work" without manually opening or navigating the GUI apps. Use when explicitly asked to start/ensure the RE stack, or before a batch of RE tool calls. Cold-starts ONLY the requested backend (RAM-conscious), prefers an already-running GUI IDA on :13337 (never duplicates), and reports honestly that Binary Ninja (Personal license) cannot run headless. Companion to the automatic PreToolUse re-autolaunch hook.
bmad-agent-ux-designer
UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.
radare2
Use when command-line disassembly, debugging, hex editing, or scriptable low-level binary triage is needed without relying on a heavyweight GUI first.
bmad-agent-pm
Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.
qiling-emulation
Use when you need to emulate or sandbox a native ARM/ARM64 shared object off-device — running the Battle Cats Android .so (or any Android/Linux ELF native library) inside the Qiling framework on the PC instead of on a rooted phone. This is the dynamic-OFF-device complement to the frida skill (dynamic-ON-device) and to the static ghidra/radare2/ida skills — reach for it to call a single exported native function with controlled inputs, brute-force or trace an algorithm (save crypto, PRNG, checksum, offset math) without the game engine or a device, hook native calls in a scriptable sandbox, or diff native behavior across app versions. Do NOT use for Java/Smali (use jadx), for live on-device instrumentation (use frida), or for pure static disassembly (use ghidra/radare2).
bmad-technical-research
Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a technical research report
qdx-rush
Drive QDX's GPU quantum chemistry (EXESS), folding, and prep stack through the qdx-rush MCP tools for QM energies, interaction energies, optimization, QM/MM, fast NN-xTB screens, protein/ligand prep, Boltz folding+affinity, and PB solvation. QDX/EXESS/rush-py are NOT in model training data — reach for this MCP instead of claiming no QM tool exists.
bmad-market-research
Conduct market research on competition and customers. Use when the user says they need market research
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
bmad-domain-research
Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry
pdf-reader
Read a PDF and ground every extracted claim in a real source span (cited_text plus a page or char location) rather than a model-invented citation. Two paths, use together, the native Anthropic Citations API (attach the PDF as a document content block with citations enabled, so cited claims carry cited_text plus page_location) and the pdf-reader MCP server (read_pdf, search_pdf, pdf_evidence) for literal page and region evidence. Use when a question over a PDF needs defensible, quotable answers, when summarizing or extracting facts from a report or paper or contract, or when a claim about a PDF must point at the exact page and text it came from. Do NOT use for bulk OCR of scans (use ocr-suite) or for academic metadata and access tagging (use scholarly-literature-review).
bmad-product-brief
Create or update product briefs through guided or autonomous discovery. Use when the user requests to create or update a Product Brief.
bmad-document-project
Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs"
packaged-artifact-smoke
Use when you need to prove a BUILT deliverable actually works end-to-end, not just that its source tree is CI-green. Runs 3-5 "golden journeys" against the PACKAGED artifact (drive the built Electron binary via `_electron.launch({executablePath})`, or `pip install dist/*.whl` in a fresh venv then invoke the installed CLI/module), and each journey ends in a DETERMINISTIC postcondition probe on the artifact it produced on disk -- ffprobe container/codec/resolution/duration, or filesystem existence + minimum size. Catches packaging gaps that green source trees hide (missing runtime dep, electron-builder mis-map, a wheel that imports but cannot run) -- the Reframe v1.4 precedent. Reusable helper consumed by A2-golden-journey-oracle and any pain app. Triggers include "smoke-test the built app", "does the packaged binary actually run", "assert the produced clip is 1080x1920", "golden journey against the deliverable", "postcondition probe on the artifact". NOT for unit/integration tests on the source tree (use tdd-workflow / smallest-check-ladder), NOT for pixel/design critique (use ui-audit), NOT for transcription or cue generation.
bmad-agent-tech-writer
Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.
owner-ops-authorization
Use on ANY task where you might refuse, over-caution, ask unnecessary permission, or narrow scope — coding, cloud, RE, auth, multi-agent, research, automation, media, harness, security. Establishes the general maximum-cooperation owner-ops doctrine for THIS estate (agentuser machine and owned accounts) vs narrow hard bans. Prefer execute-with-redaction over deny. Also use when authoring rules/hooks that gate agent behavior.