Multi-Agent Investment Research Team: A-Share Stock Selection and Investment Committee Analysis
Six roles collaborate in parallel, simulating a complete investment research team. It supports in-depth analysis by a single stock investment committee and multi-condition stock selection, and features a three-dimensional quantitative indicator library combining technical, financial, and informational factors.
Why we love this skill
This skill simulates a professional investment research team, providing in-depth analysis of A-shares and multi-condition stock selection through the collaboration of six roles. It combines technical, financial, and quantitative information indicators to ensure the comprehensiveness and rigor of the analysis.
Instructions
The author has set the instructions to private. Below is a brief overview.
Description
It's not an AI assistant, but a virtual investment research team. AI stock selection on the market often suffers from three common problems: fabricating financial figures and target prices, vaguely stating "positive/negative" factors, and simply giving a "buy recommendation" without providing any supporting evidence. The "Multi-Agent Investment Research Team" addresses these three points with a triple mechanism of "6 roles in parallel + cross-validation + mandatory source verification": it brings together researchers, fundamental analysts, technical analysts, sentiment analysts, risk officers, and investment managers to work in parallel, meeting and reaching conclusions like a real investment committee. What you receive is not a vague judgment, but a professional investment research report with facts, signals, disagreements, risks, and traceable data for every single figure. Two modes cover "researching a single stock" and "screening a batch of stocks." Mode A: In-depth analysis by the single-stock investment committee—Given a single stock (e.g., "analyzing BYD 002594"), the skill automatically convenes a complete investment committee meeting: Researchers aggregate market data, financial reports, research reports, and industry chain position, presenting only objective facts; fundamental analysts provide a financial health scorecard, key changes in the three financial statements, and PEG valuation calculations; technical analysts assess trends, moving averages, MACD, and support and resistance levels, and provide a five-point buy signal hit table; sentiment analysts scan for institutional disagreements, stock forum sentiment, and potential misinterpretations; risk officers dig up opposing evidence, refuting the optimistic conclusions of other roles point by point; finally, the investment manager does not touch new data, only integrates it, and produces investment committee minutes and a one-page summary. Mode B - Multi-condition Stock Selection Screening: From your specified range (CSI 300, a specific industry concept sector, or your own stock pool), a three-layer funnel filtering process is used: First, L1 financial hard screening (three consecutive quarters of growth, ample cash flow, PEG < 1 or a significant increase in contract liabilities); then L2 technical timing (platform breakout, golden cross of moving averages, breakout with increased volume, strong pullback with reduced volume, MACD crossing above the zero line); finally, L3 information verification (research report ratings and industry chain logic, eliminating targets with "purely technical analysis without fundamental logic"). After the candidate list is generated, the Top N targets can be automatically connected to Mode A for in-depth analysis. You will receive the following deliverables: Option A: Fixed delivery of the "five-piece set": ① A comprehensive analysis report integrating all six roles; ② Data sources and evidence tables, with each key conclusion corresponding to "Data → Source → Date"; ③ Meeting minutes of the investment committee (topics → viewpoints → disagreements → consensus → variables to be tracked); ④ A risk list sorted by severity (high/medium/low); ⑤ A one-page summary by the investment manager, condensing the core logic, key variables, validation points, and confidence levels. Option B: Delivery of a candidate stock list (code | name | hit criteria | key data | source | trigger date) + explanation of screening criteria and definitions, with the option to optionally include the complete five-piece set for top candidates. All deliverables are saved as files, with filenames including the target and date for easy reuse and archiving.
Related Skills
View all
LearnHow to quickly understand an industry
📋 User Guide: This Skill is an industry research engine driven by McKinsey methodologies, based on the eight-dimensional framework in Xiao Jing's "How to Quickly Understand an Industry." You tell it an industry name, and it generates a systematic industry research report for you. —————————————————————————————— 🚀 Basic Usage: Simply tell me what industry you want to research, the more specific the better: a. "Please analyze the solid-state battery industry for me" b. "Look at the humanoid robot industry chain from an entrepreneurial perspective" c. "Is the photovoltaic industry still worth investing in?" You can include three pieces of information (not mandatory, I will use the default if missing): 1. Industry Name: The more specific the better, such as "perovskite photovoltaics" rather than "new energy," this is "required"; 2. Goal: Investment/Career Selection/Entrepreneurship/Competitive Analysis/Popular Science, default: Investment; 3. Region: China Market/Global/USA/Southeast Asia..., default: China Market; —————————————————————————————— ⚙️ What will it do automatically? The entire process is divided into four stages: 1. Multiple rounds of online searches to gather evidence of market size/growth rate/penetration rate, industry chain, competitive landscape, moat, policies, and valuation—every conclusion has a source and timeframe, and is never fabricated; 2. Life cycle positioning: using penetration rate to determine whether the industry is in the introduction/growth/maturity/decline stage, with completely different research focuses at each stage; 3. In-depth analysis across eight dimensions: business model → market size → moat (mandatory in-depth analysis of dynamic trends) → competitive landscape (mandatory scoring of each of the five forces) → valuation → PEST analysis → business climate; 4. Anti-consensus testing: distinguishing between market-priced, obvious trends and overlooked real problems, and providing decision-making suggestions; —————————————————————————————— 📊 What will be produced? A professional industry research report in Markdown format is structured as follows: 1. ⚡ 30-Second Quick Assessment — Stage / Core Profitability Logic / Greatest Opportunity / Greatest Risk / One-Sentence Conclusion; 2. Research Subject and Boundary Definition; 3. Life Cycle Positioning (including penetration rate data); 4. Eight-Dimensional Item-by-Item Analysis (Moat includes dynamic trend table and Porter's Five Forces scoring table); 5. Anti-Consensus Test; 6. Conclusions and Decision Recommendations; 7. Key Risk List; 8. Data Sources and Time Explanation; —————————————————————————————— 🔑 Two Core Highlights 1. In-depth Moat Analysis: Not just discussing barrier types, but requiring an answer to "has it widened or narrowed in the past 2-3 years," using market share / gross profit margin / pricing power data; 2. Porter's Five Forces Scoring: All five criteria are assessed, leaving no room for shortcuts, determining who currently has the strongest bargaining power and whether the market structure is favorable or deteriorating for leading companies; —————————————————————————————— ⏱️ This takes approximately 2-4 minutes, as it requires multiple rounds of searching, dimension-by-dimensional analysis, and report writing. —————————————————————————————— 🧩 After the report output is expanded, we can continue with two specialized analyses (you will need to manually confirm these; they won't run automatically): 1. "Dissecting the Chain to Find Bottlenecks": Identifying unavoidable physical bottlenecks in the industry chain during a trend surge, and pinpointing the true beneficiaries; 2. "DCF Valuation": Running a complete discounted cash flow model for specific companies within the industry; —————————————————————————————— ▶️ Want to try? Just tell me an industry name, such as "Please take a look at the AI Agent industry from a startup perspective" or "What's the current situation of the hydrogen energy industry chain?"
LearnHow to quickly understand a company
Enter a company name or stock, and use Charlie Munger's multidimensional thinking model to conduct in-depth investment research and analysis of the stock from the perspective of value investing. SKILL automatically connects to the Internet to mine in-depth information, forces a search before judgment, cross-references two sources, and labels the scope and source. It conducts in-depth analysis according to the seven-dimensional framework of value investing, provides three-scenario valuation and 2×2 quality/price decision, and produces an actionable "In-Depth Analysis of Value Investing" report.
LearnThree-element analysis: Understanding the paper
Using the three-element decomposition method of identifying key elements, understanding the small loop, and mastering the large loop, this tool automatically or interactively dissects the argumentation framework of any paper. It includes 14 built-in AI Prompt templates, suitable for all academic readers.
Multi-Agent Investment Research Team: A-Share Stock Selection and Investment Committee Analysis
Six roles collaborate in parallel, simulating a complete investment research team. It supports in-depth analysis by a single stock investment committee and multi-condition stock selection, and features a three-dimensional quantitative indicator library combining technical, financial, and informational factors.
Why we love this skill
This skill simulates a professional investment research team, providing in-depth analysis of A-shares and multi-condition stock selection through the collaboration of six roles. It combines technical, financial, and quantitative information indicators to ensure the comprehensiveness and rigor of the analysis.
Instructions
The author has set the instructions to private. Below is a brief overview.
Description
It's not an AI assistant, but a virtual investment research team. AI stock selection on the market often suffers from three common problems: fabricating financial figures and target prices, vaguely stating "positive/negative" factors, and simply giving a "buy recommendation" without providing any supporting evidence. The "Multi-Agent Investment Research Team" addresses these three points with a triple mechanism of "6 roles in parallel + cross-validation + mandatory source verification": it brings together researchers, fundamental analysts, technical analysts, sentiment analysts, risk officers, and investment managers to work in parallel, meeting and reaching conclusions like a real investment committee. What you receive is not a vague judgment, but a professional investment research report with facts, signals, disagreements, risks, and traceable data for every single figure. Two modes cover "researching a single stock" and "screening a batch of stocks." Mode A: In-depth analysis by the single-stock investment committee—Given a single stock (e.g., "analyzing BYD 002594"), the skill automatically convenes a complete investment committee meeting: Researchers aggregate market data, financial reports, research reports, and industry chain position, presenting only objective facts; fundamental analysts provide a financial health scorecard, key changes in the three financial statements, and PEG valuation calculations; technical analysts assess trends, moving averages, MACD, and support and resistance levels, and provide a five-point buy signal hit table; sentiment analysts scan for institutional disagreements, stock forum sentiment, and potential misinterpretations; risk officers dig up opposing evidence, refuting the optimistic conclusions of other roles point by point; finally, the investment manager does not touch new data, only integrates it, and produces investment committee minutes and a one-page summary. Mode B - Multi-condition Stock Selection Screening: From your specified range (CSI 300, a specific industry concept sector, or your own stock pool), a three-layer funnel filtering process is used: First, L1 financial hard screening (three consecutive quarters of growth, ample cash flow, PEG < 1 or a significant increase in contract liabilities); then L2 technical timing (platform breakout, golden cross of moving averages, breakout with increased volume, strong pullback with reduced volume, MACD crossing above the zero line); finally, L3 information verification (research report ratings and industry chain logic, eliminating targets with "purely technical analysis without fundamental logic"). After the candidate list is generated, the Top N targets can be automatically connected to Mode A for in-depth analysis. You will receive the following deliverables: Option A: Fixed delivery of the "five-piece set": ① A comprehensive analysis report integrating all six roles; ② Data sources and evidence tables, with each key conclusion corresponding to "Data → Source → Date"; ③ Meeting minutes of the investment committee (topics → viewpoints → disagreements → consensus → variables to be tracked); ④ A risk list sorted by severity (high/medium/low); ⑤ A one-page summary by the investment manager, condensing the core logic, key variables, validation points, and confidence levels. Option B: Delivery of a candidate stock list (code | name | hit criteria | key data | source | trigger date) + explanation of screening criteria and definitions, with the option to optionally include the complete five-piece set for top candidates. All deliverables are saved as files, with filenames including the target and date for easy reuse and archiving.
Related Skills
View allLearnHow to quickly understand an industry
📋 User Guide: This Skill is an industry research engine driven by McKinsey methodologies, based on the eight-dimensional framework in Xiao Jing's "How to Quickly Understand an Industry." You tell it an industry name, and it generates a systematic industry research report for you. —————————————————————————————— 🚀 Basic Usage: Simply tell me what industry you want to research, the more specific the better: a. "Please analyze the solid-state battery industry for me" b. "Look at the humanoid robot industry chain from an entrepreneurial perspective" c. "Is the photovoltaic industry still worth investing in?" You can include three pieces of information (not mandatory, I will use the default if missing): 1. Industry Name: The more specific the better, such as "perovskite photovoltaics" rather than "new energy," this is "required"; 2. Goal: Investment/Career Selection/Entrepreneurship/Competitive Analysis/Popular Science, default: Investment; 3. Region: China Market/Global/USA/Southeast Asia..., default: China Market; —————————————————————————————— ⚙️ What will it do automatically? The entire process is divided into four stages: 1. Multiple rounds of online searches to gather evidence of market size/growth rate/penetration rate, industry chain, competitive landscape, moat, policies, and valuation—every conclusion has a source and timeframe, and is never fabricated; 2. Life cycle positioning: using penetration rate to determine whether the industry is in the introduction/growth/maturity/decline stage, with completely different research focuses at each stage; 3. In-depth analysis across eight dimensions: business model → market size → moat (mandatory in-depth analysis of dynamic trends) → competitive landscape (mandatory scoring of each of the five forces) → valuation → PEST analysis → business climate; 4. Anti-consensus testing: distinguishing between market-priced, obvious trends and overlooked real problems, and providing decision-making suggestions; —————————————————————————————— 📊 What will be produced? A professional industry research report in Markdown format is structured as follows: 1. ⚡ 30-Second Quick Assessment — Stage / Core Profitability Logic / Greatest Opportunity / Greatest Risk / One-Sentence Conclusion; 2. Research Subject and Boundary Definition; 3. Life Cycle Positioning (including penetration rate data); 4. Eight-Dimensional Item-by-Item Analysis (Moat includes dynamic trend table and Porter's Five Forces scoring table); 5. Anti-Consensus Test; 6. Conclusions and Decision Recommendations; 7. Key Risk List; 8. Data Sources and Time Explanation; —————————————————————————————— 🔑 Two Core Highlights 1. In-depth Moat Analysis: Not just discussing barrier types, but requiring an answer to "has it widened or narrowed in the past 2-3 years," using market share / gross profit margin / pricing power data; 2. Porter's Five Forces Scoring: All five criteria are assessed, leaving no room for shortcuts, determining who currently has the strongest bargaining power and whether the market structure is favorable or deteriorating for leading companies; —————————————————————————————— ⏱️ This takes approximately 2-4 minutes, as it requires multiple rounds of searching, dimension-by-dimensional analysis, and report writing. —————————————————————————————— 🧩 After the report output is expanded, we can continue with two specialized analyses (you will need to manually confirm these; they won't run automatically): 1. "Dissecting the Chain to Find Bottlenecks": Identifying unavoidable physical bottlenecks in the industry chain during a trend surge, and pinpointing the true beneficiaries; 2. "DCF Valuation": Running a complete discounted cash flow model for specific companies within the industry; —————————————————————————————— ▶️ Want to try? Just tell me an industry name, such as "Please take a look at the AI Agent industry from a startup perspective" or "What's the current situation of the hydrogen energy industry chain?"
LearnHow to quickly understand a company
Enter a company name or stock, and use Charlie Munger's multidimensional thinking model to conduct in-depth investment research and analysis of the stock from the perspective of value investing. SKILL automatically connects to the Internet to mine in-depth information, forces a search before judgment, cross-references two sources, and labels the scope and source. It conducts in-depth analysis according to the seven-dimensional framework of value investing, provides three-scenario valuation and 2×2 quality/price decision, and produces an actionable "In-Depth Analysis of Value Investing" report.
LearnThree-element analysis: Understanding the paper
Using the three-element decomposition method of identifying key elements, understanding the small loop, and mastering the large loop, this tool automatically or interactively dissects the argumentation framework of any paper. It includes 14 built-in AI Prompt templates, suitable for all academic readers.
Find your next favorite skill
Explore more curated AI skills for research, creation, and everyday work.