productivity▌

Comprehensive research assistant that synthesizes information from multiple sources with citations. \n \n Follows a systematic five-step research process: clarifying the question, identifying key aspects, gathering information, synthesizing findings, and documenting sources \n Structures output with executive summary, key findings, detailed analysis by subtopic, areas of consensus and debate, and source evaluation \n Evaluates source credibility across peer-reviewed journals, official reports, r

Intelligently organizes files and folders by analyzing structure, finding duplicates, and automating cleanup tasks. \n \n Analyzes current folder organization, identifies duplicate files, and proposes logical restructuring based on file types, dates, and content \n Supports multiple organization patterns: by file type (documents, images, videos), by purpose (work vs. personal, active vs. archive), or by date ranges \n Executes moves, renames, and deletions with user approval, preserving file met

Web search with LLM-optimized results, content snippets, and relevance scores. \n \n Supports four search depths (ultra-fast, fast, basic, advanced) with configurable result counts up to 20, plus domain filtering and time-range constraints \n Returns structured JSON output with content snippets, relevance scores, and metadata optimized for LLM consumption \n Includes specialized search modes for news and finance topics, with optional AI-generated answers and full page content extraction \n Integ

Make applications fast, scalable, and cost-efficient.

Comprehensive research on any topic with automatic source gathering, analysis, and citations. \n \n Conducts multi-source web research with explicit citations, ideal for comparisons, current events, market analysis, and detailed reports \n Offers three model options: mini for targeted single-topic research (~30s), pro for comprehensive multi-angle analysis (~60-120s), and auto for API-driven complexity detection \n Authenticates via OAuth through Tavily MCP server with automatic browser-based lo

Transform raw data into compelling narratives that drive stakeholder decisions and action. \n \n Three-pillar framework combining data evidence, narrative meaning, and visual clarity to structure insights for maximum impact \n Includes five story templates (Problem-Solution, Trend, Comparison, Executive Summary, One-Page Dashboard) with ready-to-use structures for common business scenarios \n Progressive reveal and annotation techniques to layer complexity, build understanding, and highlight key

SQL, pandas, and statistical analysis expertise for data exploration and insights. \n \n Covers SQL fundamentals through advanced techniques including JOINs, subqueries, CTEs, window functions, and query optimization \n Handles pandas workflows for data manipulation, transformation, grouping, filtering, pivoting, and time series analysis \n Provides statistical capabilities including descriptive statistics, hypothesis testing, correlation analysis, and basic predictive modeling \n Delivers code

Default to execution, not instruction. When the user expresses execution intent, carry the change through directly: run the needed shell commands, edit the real files, and verify the result instead of only replying with example commands. Treat requests like "configure", "set up", "wire", "change", "add", "fix", "migrate", "deploy", "run", or "make this use Xget" as execution intent unless the user clearly asks for explanation only.

You are a business advisor channeling the philosophy of The Minimalist Entrepreneur by Sahil Lavingia. Help the user find their community — the foundation of a minimalist business.

最小产物（所有模式）：