Research skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

nyc-dob-violations

Look up open and resolved DOB and ECB violations for any NYC building, with class, status, and penalty detail. Use when the user asks whether a building has violations, stop-work orders, or outstanding ECB penalties. NYC only; for housing-code violations use /nyc-hpd.

251 repo starsObserved in 1 repos
Research

nyc-hpd

Look up HPD violations, complaints, and building registration for residential buildings.

251 repo starsObserved in 1 repos
Research

nyc-landmarks

Check if a NYC building is landmarked or in a historic district using LPC data.

251 repo starsObserved in 1 repos
Research

tapes-search

Search over stored LLM sessions using semantic search. Use when you need to find relevant conversations, recall previous session context, or search through historical LLM interactions stored in the tapes system.

251 repo starsObserved in 1 repos
Research

github-trending

Fetch and display GitHub trending repositories and developers. Use when building dashboards showing trending repos, discovering popular projects, or tracking GitHub trends. Triggers on GitHub trending, trending repos, popular repositories, GitHub discover.

249 repo starsObserved in 6 repos
Research

layers-observed-behaviour

Techniques for planning user research and synthesising it into grounded, confidence-rated findings about what users actually do

247 repo starsObserved in 3 repos
Research

GitHub Search & Discovery

当用户在开始开发前需要搜索现有的开源库、工具、MCP Server 或最佳实践代码时使用。帮助避免重复造轮子,找到最适合当前需求的现成解决方案。

247 repo starsObserved in 1 repos
Research

memo-coach

程序化扎根理论备忘录写作引导工具(Procedural GT Memo Coach)。 基于 Strauss & Corbin(1990, 1998)程序化扎根传统,通过连续追问帮助研究者 将编码过程中的分析直觉逐步提炼为符合典范模型规范的理论备忘录。 根据当前编码阶段自动调整追问方向: - 开放编码阶段 → 概念备忘录:属性与维度探查 - 主轴编码阶段 → 理论备忘录:典范模型关系推演 - 选择性编码阶段 → 整合备忘录:故事线与核心类属整合 所有分析内容由研究者自己写出,skill 只提问、不给答案。 当用户说"帮我想想这个编码""我在做主轴编码卡住了""陪我想想这个类属关系" "引导我写备忘录""这个条件和现象的关系我说不清""帮我把这个想法推下去"时触发。 注意与 qualitative-memo 的区别:qualitative-memo 由 AI 代写分析内容; memo-coach 的所有分析内容由研究者自己写,AI 只负责追问和整理。

247 repo starsObserved in 1 repos
Research

paper-reading

Read, summarize, and critically analyze an academic paper from a PDF, official HTML page, URL, or pasted full text. Use for requests such as "read this paper", "快速看懂", "精读论文", "analyze this paper", "paper summary", or strict paper critique. Produces evidence-traceable Markdown or a portable interactive HTML report at one complete, concise close-reading depth, with read-only inspection of authoritative source code when available and no reproduction run.

247 repo starsObserved in 1 repos
Research

phd-literature-review

博士论文文献综述(约2万字)工程化写作辅助系统(PhD-LitReview-Auto-Flow)。 根据用户提供的研究选题、研究问题、核心概念等核心资产,通过多阶段工作流系统性地 检索真实学术文献、核实文献真实性、确定综述结构与分类标准,并以博士论文标准 撰写约2万字的完整文献综述章节。采用主题式组织、多阶段单步输出机制,覆盖 概念界定、理论脉络、实证研究评述、研究空白识别等完整模块,最终生成Word文档 并提供跨章回填指引。 触发条件:当用户提到需要撰写博士论文文献综述/博士学位论文文献综述/PhD dissertation literature review、需要写2万字文献综述、需要写论文第二章文献综述、博士论文 文献梳理与评述时触发此skill。 注意:本skill专用于博士论文级别的长篇文献综述(约2万字),不同于 literature-review-writer(顶刊短篇文献综述,2-5页)和paper-analyzer(单篇论文拆解)。

247 repo starsObserved in 1 repos
Research