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
chatgpt5-web
Direct browser-automation ChatGPT 5 web lane - one skill, three modes via a `mode:` arg. Use when the user explicitly wants the ChatGPT web side (not Codex orchestration): mode:query for a single direct question; mode:discuss to debate/ideate/spar; mode:curate to compare candidates and pick the best. NOT for Codex-side lanes (use codex-consult).
chatgpt-apps
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata/CSP/domain settings, or produce a docs-aligned scaffold. Prefer a docs-first workflow via openai-docs or the OpenAI docs MCP.
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
caption-burn
Use when BURNING captions / subtitles / karaoke INTO a video as hardcoded pixels (hardsub) via libass through ffmpeg, OR soft-muxing them as a selectable, removable subtitle track. Covers ASS document generation sized to the export canvas, libass styling (font / size / colour / outline / box), the OpusClip word-by-word KARAOKE preset (per-word alternating yellow/green + scale-pop), hook-title / hook-card overlays, the CaptionOverride tuning patch, safe-area placement for 9:16, and the Netflix CPS/CPL/min-gap polish pass. Burn = lossy re-encode, permanent, styling survives anywhere; soft-mux = lossless stream-copy, toggleable, but loses ASS styling in MP4 (mov_text). NOT for moving/animated watermark removal (use video-watermark-removal), NOT for transcription/cue generation (this consumes an existing cue list), NOT for repositioning an already-burned track (burned pixels are permanent — re-burn from source). Source of truth: media_studio/features/caption.py, caption_karaoke.py, caption_override.py, caption_polish.py, tracks.py.
c4-architecture
Use when asked to create architecture diagrams, document system architecture, visualize software structure, or generate context/container/component/deployment diagrams — produces C4 model Mermaid diagrams written to docs/architecture/.
browser-rail
Use as the DEFAULT for any multi-step browser work on a site the owner is signed into - reading, filling, clicking, uploading, or posting across several turns on grok.com, chatgpt.com, a dashboard, a webmail, an admin panel, or any logged-in app. Drives a dedicated CDP Chrome/Edge profile with Playwright over role locators (the a11y tree), not pixels. Covers the Chrome-136 break where --remote-debugging-port is silently IGNORED on the default user-data-dir, the dedicated-profile fix, how the owner signs in ONCE so no credential ever passes through an agent, passing content as an evaluate ARG instead of inlining it into JS, and when to fall back to claude-in-chrome instead. Triggers include drive the browser, log into a site and do X, automate this web app, upload a file to a web page, attach to my Chrome, CDP, remote debugging port, connect_over_cdp, browser automation, or scrape a page I am logged into. NOT for a one-off look at a tab the owner already has open (use claude-in-chrome) and NOT for fetching a public page (use WebFetch or firecrawl).
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
blueprint
Use when blueprint is needed. Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step.
biomedical-paper-triage
Use when turning a raw list of biomedical papers into a ranked, access-tagged shortlist graded T1-T4 by human/animal/in-vitro evidence strength via Scholarly Access MCP ; do NOT use for generic literature metadata or citation graphs (use scholarly-literature-review) ; returns defensible ranked shortlist with evidence grades.
binja-sigmaker
Use when generating byte signatures or AOB patterns from Binary Ninja for runtime hooks, trainer work, or version-resilient function identification.
binexport
Use when exporting IDA Pro, Binary Ninja, or Ghidra analysis into BinExport artifacts for BinDiff or portable cross-tool comparison workflows.
bindiff
Use when comparing two related binaries or database exports to identify changed functions, patch deltas, or version-to-version differences in native reverse-engineering workflows.
binary-ninja
Use when Binary Ninja UI workflows, intermediate-language reasoning, or Binary Ninja Python API automation are needed for reverse engineering tasks.
binary-ninja-mcp
Use when installing or configuring Binary Ninja MCP, especially when a Binary Ninja plugin or npm-based MCP bridge must be wired into Codex, Claude Code, or Gemini CLI.
binary-ninja-diff-signatures
Use when working in Binary Ninja to compare versions, analyze changed functions, or generate stable signatures for runtime hooks, trainer features, or address portability across builds.
benchmark-optimization-loop
Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
bcsfe-save-roundtrip
Use when pulling, editing, or pushing a Battle Cats (EN, rooted BlueStacks) SAVE_DATA file - the byte-exact PowerShell + HOME-key flush pull, the headless BCSFE-Python library edit, and the in-place cat-redirect push that preserves uid 10065 and the SELinux app_data_file context. Includes the MSYS path-conversion 0-byte-truncation gotcha, the force-stop-before-push rule, and Ototo cannon fields.
bc-update-survival
Use when a Battle Cats (EN, jp.co.ponos.battlecatsen) update relinks lib/x86_64/libnative-lib.so and your pinned RVAs go stale — the toolpack that RETIRES hardcoded offsets. AOB wildcard-signature resolver (author a byte pattern that wildcards only the reloc-sensitive bytes, then re-locate the function by pattern via offline .so scan or live `frida search_memory`/Memory.scan — survives relink where a fixed RVA does not); ghidriff one-command cross-version .so diff that AUTO-PORTS the whole offset table old→new; and a per-version-bump update-triage (extract + sha-compare + diff APK/DAT/.so). Ships a SHADOW-mode drift gate (observe + log only, never blocks). Use before trusting any bc-drive / battlecats-event-unlock offset after a version bump. NOT for save-file edits (bcsfe-save-roundtrip) or live UI driving (bc-drive).