Objective Industry Research
Any input → structured research, no judgment
Objective Industry Research
Any input → structured research, no judgment
Showcase
Description
An essential tool for investors. In-depth research to support decisions, but no judgments — very important, and those in the know understand. Author: Former engineer/entrepreneur, now a primary market investor, reviewed over 10,000 pitch decks, and has had in-depth discussions with more than 1,000 companies. Usage: Trigger via direct conversation. Example: "Research the triacetate cellulose (TAC film) industry." → The skill will automatically identify and activate. What it does: 1. Automatically identify input type and define research scope. 2. Phase 1: 3-5 search rounds, output a 1,500-word quick panoramic scan (data tables + industry chain + key players + drivers/bottlenecks + information gaps). 3. Phase 2: After you reply "Continue," output a full report covering 7 sections and 21 dimensions (5,000-15,000 words). 4. All output is pure facts, without judgments like "Is it worth investing?" --- # industry-research — In-Depth Industry Research ## Core Principles ## Division of Work ## Step 1: Identify and Define Scope ## Step 2: Phase 1 — Quick Panoramic Scan ### Phase 1 Output Structure ## Step 3: Phase 2 — Complete In-Depth Report ### Phase 1 Output Structure #### Part 1: Macro Overview #### Part 2: Market and Scale #### Part 3: Industry Chain Panorama #### Part 4: Global Perspective #### Part 5: Policy and Regulation #### Part 6: Capital and Market #### Part 7: In-Depth Understanding ## Data Quality Marking ## Phase 2 Parallel Search Strategy (Optional) ## Pre-Output Check
Related Skills
View all
ResearchRapid Industry Understanding
📋 Usage Guide This Skill is an industry research engine based on McKinsey methodology, using the eight-dimension framework from Xiao Jing's "How to Quickly Understand an Industry". Tell it an industry name, and it produces a systematic research report. —————————————————————————————— 🚀 Basic Usage Just tell me the industry you want to research—the more specific, the better: a. "Analyze the solid-state battery industry" b. "Look at the humanoid robot supply chain from an entrepreneurial perspective" c. "Is the solar industry still investable now?" You can optionally provide three details (if missing, I'll use defaults): 1. Industry name: be specific, e.g., "perovskite solar" instead of "new energy"—required; 2. Goal: investment / career / entrepreneurship / competitive analysis / education, default: investment; 3. Region: China market / global / US / Southeast Asia..., default: China market; —————————————————————————————— ⚙️ What it does automatically? The entire process has 4 stages: 1. Multi-round web searches for market size/growth/penetration rate, supply chain, competitive landscape, moat evidence, policy, valuation—every conclusion has a source and timestamp, never fabricated; 2. Lifecycle positioning: use penetration rate to determine if the industry is in introduction/growth/maturity/decline—different stages have completely different research focuses; 3. Eight-dimension deep dive: business model → market size → moat (forced deep dive into dynamic trends) → competitive landscape (forced scoring on each of Porter's Five Forces) → valuation → PEST → business cycle; 4. Contrarian check: distinguish market priced-in consensus from overlooked real issues, and provide decision recommendations; —————————————————————————————— 📊 What it outputs? A professional research report in Markdown format, structured as: 1. ⚡ 30-second verdict — stage / core profit logic / biggest opportunity / biggest risk / one-sentence conclusion; 2. Research object and boundary definition; 3. Lifecycle positioning (with penetration rate data); 4. Eight-dimension analysis (moat includes dynamic trend table, Porter's Five Forces scoring table); 5. Contrarian check; 6. Conclusion and decision recommendations; 7. Key risk list; 8. Data sources and time notes; —————————————————————————————— 🔑 Two Core Highlights 1. Forced deep dive on moat: not just the type of barrier, but must answer "has it widened or narrowed in the past 2-3 years?" using market share/gross margin/pricing power data; 2. Porter's Five Forces scored individually: all five forces scored to avoid shortcuts, determining who has the strongest bargaining power now and whether the landscape is favorable or deteriorating for leaders; —————————————————————————————— ⏱️ Time Approximately 2-4 minutes, due to multiple rounds of search + dimension-by-dimension analysis + report writing —————————————————————————————— 🧩 Subsequent Extensions After the report is generated, you can continue with two specialized analyses (requires manual confirmation, won't run automatically): 1. "Unchain to find bottlenecks": identify physical bottlenecks in the supply chain that can't be bypassed when trends scale, locking in true beneficiary targets; 2. "DCF valuation": run a full discounted cash flow model for a specific company within the industry; —————————————————————————————— ▶️ Want to try? Just tell me an industry name, e.g., "Take a look at the AI agent industry from an entrepreneurial perspective" or "What's the situation with the hydrogen energy supply chain?"
ResearchMulti-Agent: A-Share Pick & IC
It's not an AI assistant, but a virtual investment research team. Common AI stock-picking tools suffer from three problems: fabricating financial figures and target prices, giving vague "bullish/bearish" remarks, and offering "buy" recommendations without clear reasoning. The Multi-Agent Investment Research Team tackles these with a three-pronged approach: 6 parallel roles, cross-validation, and mandatory source attribution. It convenes researchers, fundamental analysts, technical analysts, sentiment analysts, risk officers, and investment managers to work in parallel, deliberating like a real investment committee. What you get is not fuzzy opinions, but a professional research document with facts, signals, disagreements, risks, and every number traceable to its source. Two modes covering "researching a single stock" and "screening a batch of stocks" Mode A: Single-Stock Committee Deep Analysis — Just provide a stock (e.g., "Analyze BYD 002594"), and the skill automatically convenes a full investment committee: the researcher aggregates market data, financial reports, research reports, and industry chain positioning, presenting only objective facts; the fundamental analyst issues a financial health scorecard, key changes in the three financial statements, and PEG valuation; the technical analyst evaluates trends, moving averages, MACD, support and resistance levels, and provides a five-point buy signal hit table; the sentiment analyst scans institutional divergence, retail investor sentiment, and potential misinterpretations; the risk officer digs up counter-evidence, systematically refuting optimistic conclusions from other roles; finally, the investment manager, without adding new data, integrates everything to produce committee minutes and a one-page summary. Mode B: Multi-Condition Stock Screening — From a specified universe (e.g., CSI 300, a sector/theme basket, or your own stock pool), apply a three-layer funnel: L1 financial hard screen (three consecutive quarters of growth, ample cash flow, PEG<1 or huge increase in contract liabilities), L2 technical timing (base breakout, moving average golden cross, volume breakout, strong pullback on low volume, MACD crossing above zero line), L3 information validation (research report ratings and industry chain logic, eliminating "pure technical without fundamental basis" picks). After obtaining a candidate list, the top N stocks can automatically proceed to Mode A for deep analysis. What you will get Mode A delivers a fixed "five-piece set": ① Full analysis report integrating all six roles; ② Data source and evidence table, with each key conclusion mapped to "data → source → date"; ③ Meeting-style committee minutes (agenda → each role's view → disagreements → consensus → variables to track); ④ Risk list sorted by high/medium/low severity; ⑤ One-page investment manager summary condensing core logic, key variables, verification points, and confidence level. Mode B delivers: Candidate stock list table (ticker | name | triggered conditions | key data | source | trigger date) plus screening criteria and methodology description, optionally with the full five-piece set for top candidates. All outputs are saved as files with ticker and date in the filename for easy reuse and archiving.
Research & Implementation
For a specified topic, this Skill produces a focused research report that combines expert judgment with practical execution. It helps beginners understand the problem, compare options, and complete their first hands-on project. The report first defines the research scope, intended audience, and time-sensitivity boundaries. It then reviews mainstream options by cost, barriers to entry, maturity, suitable use cases, and risks, providing a clear, evidence-based recommendation instead of a vague comparison that simply says “each has its pros and cons.” The report also explains the recommended option’s basic principles, capability boundaries, and common pitfalls. For information that may change easily—such as pricing, policies, and versions—it identifies the supporting evidence, validity period, and verification method. When information is insufficient, it clearly points out the gaps rather than making things up. All technical terms are explained in plain language, and key facts are accompanied by verifiable sources or reproducible steps whenever possible. You’ll also receive a beginner-focused, from-scratch implementation guide covering the tools, accounts, budget, and time needed in advance, along with specific actions, decision criteria, and common troubleshooting steps for each stage. After your first hands-on experience, the guide provides 30-day and 90-day progression plans and highlights the steps people are most likely to abandon. It’s suitable for individuals and teams conducting focused research, selecting among options, or putting a plan into practice.
Information
- Version
- v7
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
