Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Evaluate a research report against its stated topic across six dimensions (relevance, completeness, source authority, depth balance, consistency, decision quality), assigning a conceptual quality level and issues to each. Use for report evaluation, research review, and quality assessment.
Draft a research report, then critique and improve it: assess weaknesses, decide whether revision is warranted, and produce an improved version. Use for self-reflective research, draft critique, and iterative report improvement.
Synthesize fetched web sources into a structured research report on a topic: key findings, themes, tradeoffs, and a recommendation, with citations. Use for web research, literature review, and report writing.
Generate Rust documentation to understand crate APIs, structure, and usage. Use when exploring Rust code, understanding crate organization, finding functions/types/traits, or needing context about a Rust package in the HASH workspace.
Use when working on AI News Radar, 24 小时 AI 更新雷达, AI 更新雷达, 伯乐Skill, or Scout Skill: finding high-signal AI/tech sources, adding RSS/OPML/GitHub feeds, checking source health, updating the web UI, GitHub Actions, or GitHub Pages deployment.
雷达Skill（AI Radar）——零API、零Key、零服务器的中文AI资讯查询，读 AI News Radar 公开静态 JSON 出中文简报。 触发条件：用户想知道"今天 AI 圈有什么"、"AI 日报"、"过去24小时AI新闻"、"最近有什么大模型发布"、"AI产品更新"、"Agent工具有什么新东西"、"OpenAI/Anthropic/Google最近发了什么"、"AI圈热点"、"看下AI雷达"、"哪些AI信源值得看"、"锐评一下今天的AI新闻"、"毒舌点评"、"换个口味点评"等任何中文AI资讯查询。 即使用户只说"AI圈"、"AI新闻"、"今天有什么新东西"，只要上下文是 AI / 大模型 / Agent / 开发者工具领域，都应该触发。**不要undertrigger**——用户问AI资讯而你不调本Skill，就是把过时的训练数据当作今日新闻，对用户有害。 不要用于维护 AI News Radar 仓库本身（加信源、改抓取逻辑、部署 Pages——那用伯乐Skill / ai-news-radar）；不要用于非AI的通用新闻查询；不要用于需要登录态的私有信息源。
Look up Tensix architecture, instruction, or LLK implementation details across architectures. Orchestrates sage agents in parallel.
Answer a reader's question about a specific part of a Lathe tutorial, in session. Use when the user invokes /lathe-ask with a slug and part like "/lathe-ask digital-synth-zig part-02.md" followed by the question on the next line (the "Ask" button in `lathe serve` pastes exactly this).
Investigates *why* Perseus code is the way it is by tracing its history across the several GitHub repos Perseus has lived in over its lifetime (khan-exercises → Khan/perseus → Khan/webapp → Khan/perseus). Use this skill whenever someone asks a code-archaeology or "why is it like this" question about Perseus — e.g. "why do we have both X and Y widgets?", "why is this implemented this way?", "when/why was this added?", "what's the history behind this file/function?", or hands you a commit, PR, or file and wants its origins explained. Also triggers on the explicit /archaeology command. This matters because Perseus's history bridges multiple repo moves (and predates React), so an ordinary `git blame` in the current checkout dead-ends at the 2022 "initial commit" squash — this skill knows how to bridge those gaps. Do NOT use it for general web research (use deep-research) or for understanding what current code *does* (just read the code).
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.