A seven-stage deep-research workflow that takes a structured research task and coordinates several agents working in parallel. It produces a comprehensive report with citations.
A question-refinement tool for stock-investment research. It turns a stock name or code into an eight-stage due-diligence task after asking about goals, time frame, risk, and research focus.
A stock-investment research engine that runs an eight-stage due-diligence process. It uses multiple agents in parallel and creates a cited investment report.
Claude Code instructions for liangdabiao/Claude-Code-Stock-Deep-Research-Agent, covering claude.md, project overview, stock investment research system (股票投资尽调系统), key commands and primary stock research command.
A command that runs a complete research process on a specified topic, from refining the question to producing a final report. The description is provided in Chinese.
A command that creates a detailed plan for researching a topic, including smaller questions and a strategy for assigning work to agents. The description is provided in Chinese.
A command for combining findings from multiple research agents into one research report. A research agent is an automated worker that investigates part of a question.
A research-report checking skill that reviews whether claims have accurate, trustworthy, and properly formatted citations. A citation is a source reference showing where a fact came from.
A controller for a research graph, where connected steps represent different parts of an investigation. It can generate, combine, refine, and score research paths.
A question-planning skill that turns a rough research question into a clearly scoped research task and structured prompt. It asks follow-up questions when details are missing.
A skill that runs a seven-stage deep-research process. It takes a structured research task, sends parts of it to several agents in parallel, and produces a cited report.
A research-writing skill that combines findings from multiple research agents into one structured report. It handles disagreements and extracts shared conclusions.
Claude Code instructions for liangdabiao/Claude-Code-Deep-Research-main, covering claude.md, project overview, quick start commands, primary research command and step-by-step commands.
An analyser for A/B tests, which compare two versions of a product, campaign, or feature with different user groups. It covers experiment design, statistical tests, user segments, and visual reports.
Perform multi-touch attribution analysis using Markov chains, Shapley values, and custom attribution models. Use when you need to analyze marketing channel effectiveness, calculate conversion attribution, optimize marketing budgets, or understand customer journey paths. Supports channel transition analysis, ROI…
Analyze text content using both traditional NLP and LLM-enhanced methods. Extract sentiment, topics, keywords, and insights from various content types including social media posts, articles, reviews, and video content. Use when working with text analysis, sentiment detection, topic modeling, or content optimization.
A six-stage guide for working through a data-analysis project: checking data quality, exploring it, forming hypotheses, visualising results, generating code, and writing a report.
An automated workflow for exploring data and creating visual reports. It covers data loading, quality diagnosis, charts, modelling evaluation, and HTML report generation.
Performs exploratory data analysis, statistical analysis, and pattern discovery. Invoke when user wants to analyze data, find patterns, statistical testing, or get deep insights.
Analyze user conversion funnels, calculate step-by-step conversion rates, create interactive visualizations, and identify optimization opportunities. Use when working with multi-step user journey data, conversion analysis, or when user mentions funnels, conversion rates, or user flow analysis.