Pesquisa e Web

深度阅读非技术素材，输出完整研究文章。四阶段流水线：捕获→精读→综合→撰写。素材类型：论文（arxiv、期刊）、书籍章节、新闻报道、长文、访谈记录、行业报告、政策文件。一个 skill 从头到尾完成，不依赖外部 skill。当用户想要：深度阅读论文、研究非技术主题、把多份素材综合成文章、对论文做深度解析、把报告整理成研究文章、综合分析多份素材、理解一篇论文的核心思想并写成文章、深度研究某个话题（社会现象、商业模式、理论框架等非代码主题）时，都应该触发。即使用户只说"分析这篇论文"或"帮我读一下这个"——只要素材不是代码或技术项目，就应该用 deep-read 而不是其他 skill。用户分享论文 PDF/URL、arxiv 链接、报告文件并要求分析时，一律触发。不触发：GitHub URL / 源码分析 / 技术框架深度解析 → source-dive；纯 URL 抓取不分析 → read

Curated skill combinations for specific roles - founder, PM, manager, growth leader, and more. Each playbook combines essential Lenny skills.

Search the web via DuckDuckGo. Use when you need to find current information, discover URLs for deeper reading, or research a topic beyond your training data.

Obsidian-centered knowledge management toolkit - 3 format skills, 4 templates, and adjacent productivity skills for knowledge capture, organization, and visualization.

管理本地代理架构（Proxifier + Clash Verge + Charles），诊断网络问题，按需抓包，确保 VPN 和抓包隔离共存

Realiza uma verificação de qualidade nos nós folha da Árvore de Metas, assegurando que cada um seja específico, acionável e que o conjunto cubra totalmente o objetivo principal, sinalizando problemas para decomposição.

Interpreta relatórios de pesquisa para indústrias, setores, conceitos e temas, focando no consenso do lado vendedor, lógica central, oportunidades, riscos e direções chave. Identifica automaticamente entidades de indústria ou conceito via uma interface de dados financeiros para gerar relatórios estruturados de pesquisa de setor.

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers

进行用户研究，包括访谈、调研和画像创建。当用户需要了解用户需求、创建用户画像、分析用户反馈、进行用户访谈，或说"和用户谈谈"、"用户想要什么"、"用户研究"时使用。即使没有明确说"用户研究"，当用户试图理解用户行为、需求或痛点时也应激活。

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Utilize ao escrever qualquer código de implementação, corrigir bugs ou modificar código existente. Delega a pesquisa a um subagente rápido que destila resultados de busca em resumos compactos e eficientes para RAG, garantindo que o contexto principal nunca veja a saída bruta.

Product management advisor drawing from 269+ Lenny's Podcast episodes, established PM frameworks (JTBD, RICE, Opportunity Solution Trees), and practitioner wisdom. Use when asking for PM advice, product strategy, prioritization, user research, growth, roadmapping, metrics, or product decisions. Triggers on: product strategy, PM advice, prioritization, roadmap, user research, product-market fit, OK