全部能力

通过 Tavily CLI 执行带引用的全面 AI 驱动研究。当用户需要深度研究、详细报告、对比分析、市场分析、文献综述，或提及“research”、“investigate”、“analyze in depth”、“compare X vs Y”、“what does the market look like for”，以及需要带明确引用的多源综合分析时，请使用此技能。返回基于网络来源的结构化报告。耗时 30-120 秒。如需快速查找事实，请改用 tavily-search。

精选提示词及使用示例，涵盖研究、作品集审查、报价请求、审批门控草稿、NFT 发现、预测市场分析，以及……

通过 EmblemAI 进行 DeFi 收益研究与流动性质押。发现收益机会，比较各类协议，使用 Nansen 查看 DeFi 仓位，并通过代币兑换参与流动性质押。当用户想要研究收益、寻找质押选项或审查 DeFi 仓位时使用。

学术研究助手，用于文献综述、论文分析和学术写作。适用场景：审阅学术论文、开展文献综述、撰写研究摘要、分析方法论、格式化引用，或当用户提及学术研究、学术写作、论文或科学文献时。

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on…

Darwin Skill (达尔文.skill)：受 Karpathy 的 autoresearch 启发的自主技能优化器。使用 8 维度评估标准（结构 +…）评估 SKILL.md 文件

Smart contract development advisor based on Trail of Bits' best practices. Analyzes codebase to generate documentation/specifications, review architecture,…

学术写作、研究方法与学术交流工作流。适用于撰写论文、文献综述、项目申请书、开展……

English LaTeX academic paper assistant for existing `.tex` journal or conference manuscripts (IEEE, ACM, Springer, NeurIPS, ICML, etc.). Use whenever the user…

Chinese LaTeX thesis assistant for existing .tex degree thesis projects (XeLaTeX/LuaLaTeX/latexmk). Use this skill whenever a user works on a Chinese master's…

帮助用户综合客户反馈并采取行动。适用于分析 NPS 回复、处理支持工单、审阅用户研究等场景。

Run a comprehensive SEO audit — keyword research, on-page analysis, content gaps, technical checks, and competitor comparison. Use when assessing a site's SEO…

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need…

Research competitors and generate a positioning and messaging comparison with content gaps, opportunities, and threats. Use when building sales battlecards,…

Help users run effective post-mortems and retrospectives. Use when someone is reviewing a project that succeeded or failed, wants to establish learning…

Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment…

12智能体学术论文写作流程。10种模式（完整/规划/大纲/修订/修订指导/摘要/文献综述/格式转换/引用检查/披露声明）。6…

将来自访谈、问卷和反馈的用户研究综合为结构化的洞察。适用于当你有一堆访谈笔记、问卷回复或……

Build a persistent knowledge graph of your codebase so Claude reads only what matters — up to 49x fewer tokens on coding tasks.

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review,…