Access pre-computed website action manuals containing page descriptions, functionality, DOM structure, and element selectors for browser automation. Use when you need CSS/XPath selectors for UI elements, building browser-based AI agents, or looking up how to interact with a website's UI.

CRITICAL: Use for json-ui component rendering and development. Triggers on: json-ui, json render, component catalog, report render, HTML report, I18nString, i18n, bilingual, language switch, dual language, PaperHeader, AuthorList, Abstract, MetricsGrid, Section, Highlight, Zod schema, catalog.ts, cli.ts, components/index.tsx, "how to add a component", "how to render JSON", JSON 渲染, 组件目录, 报告渲染, 多语言, 中英文切换

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Use when user asks to research, analyze, investigate, deep-dive, or generate a report on any subject. Supports academic papers (arXiv), technologies, trends, comparisons, and general topics.

View, search, and download academic papers from arXiv. Supports API queries, web scraping via Actionbook, and HTML paper reading via ar5iv. Use when user asks about arxiv papers, academic papers, research papers, paper summaries, latest papers, or wants to search/download/read papers.

Export any web article to a local Obsidian-ready Markdown directory. Fetches page content via actionbook CLI, downloads images locally, rewrites image references to relative paths, and optionally translates the article using AI. Produces a self-contained folder with README.md, images/, and an index.md navigation file.

Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and json-ui visual report generation.

Automates browser interactions for form filling and web page interaction. Used by the request-website command to submit website indexing requests.

Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.

Activate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors.

Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "YouTube转文字", "提取字幕".

Translate English or Japanese tech articles into natural, fluent Chinese. Use whenever the user asks for Chinese translation, says "translate to Chinese" or "翻译", or provides English/Japanese content (pasted text or a file) to convert into Chinese. Chinese output only — not for translating into other languages.

Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.

Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, or edit an image and does NOT name another provider. Triggers: "nanobanana", "generate image", "create image", "edit image", "图片生成", "生成图片", "AI绘图", "图片编辑". Do NOT use for diagrams (架构图/流程图/时序图) — draw those with Mermaid or code instead.

将当前对话压缩为交接文档（handoff document / session handoff brief），供下一个 agent 接续工作。手动调用 /handoff。

针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。

Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a provider, use nanobanana-skill instead. Do NOT use for diagrams (架构图/流程图) — draw those with Mermaid or code.

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for local uncommitted changes — this skill only reviews pull requests on GitHub.

Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing a GitHub issue, says "fix issue

Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregate results into a polished report file. Use for systematic web/document research, competitive or industry analysis, batch link/dataset processing, and long-form evidence synthesis. Triggers: "深度调研", "deep research", "wide research", "多 Agent 调研", "系统调研".

Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "let openai", "full-auto", "adversarial review", "second opinion review", "用codex", "让gpt实现", "对抗式审查", "让codex审查计划", "第二意见". Use this skill whenever the user wants to delegate coding tasks to OpenAI models, run code or plan reviews via codex, get a second-opinion review from a different model, or execute tasks in a sandboxed environment.