Equity Research

Equity Research Skill

This skill generates institutional-grade investment research in two modes: Tear Sheet (3-5 page PDF, single session) and Equity Report (≥25 page PDF, 3-task architecture with financial model). Both modes share the same analytical philosophy — the difference is depth, scope, and delivery structure.

Your first job: figure out what the user wants. Then carry the Core Principles into the next file.

Phase 0.0: Router — Intent Clarification + Output Type Detection

Step 1: Detect Language

Detect the user's language from their message. Use that language for ALL follow-up questions and the final report.

Step 2: Classify Intent (3 Tiers)

Not every company analysis request needs a full report. Before committing resources, determine what the user actually wants.

Step 2a: Clarify Intent (Tier B only)

When the user's request is ambiguous (Tier B), ask them what level of output they want. Do not assume they want a full report — that wastes their time and tokens.

Present 3 clear options (in the user's language):

Chinese example:

我可以用以下几种方式帮你分析 [公司名]:

1. 投资速览 (Tear Sheet) — 3-5页专业机构级投资简报，包含估值、催化剂、产业链、情景分析等，适合快速决策参考
2. 深度研究报告 (Equity Report) — ≥25页机构级深度研报，包含完整财务模型、DCF估值、敏感性分析等，适合深入研究
3. 简单回答 — 不生成报告，直接用对话回答你的问题，最节省时间

你想要哪种？

English example:

I can analyze [company] at different levels of depth:

1. Tear Sheet — A concise 3-5 page professional investment brief with valuation, catalysts, supply chain, and scenario analysis
2. Full Equity Report — An in-depth ≥25 page institutional report with a complete financial model, DCF valuation, and sensitivity analysis
3. Quick answer — No report generation, just a conversational response to your question

Which would you prefer?

If user chooses option 3: Answer their question conversationally. Do NOT proceed with this skill. End here.

Step 3: Determine Output Type

Once output_type is set, record it. This variable determines which mode-specific file to read next.

Step 3a: Equity Report Valuation Depth Selection (only when output_type = EQUITY_REPORT)

When the user wants an equity report, ask one more question before starting analysis. The report can be built at two valuation depths — this significantly affects time and complexity.

Present the choice (in the user's language):

Chinese:

深度研报可以按两种估值深度生成：

1. 完整版（含财务模型） — 构建完整的三表财务模型（利润表/资产负债表/现金流表）+ DCF绝对估值 + 可比公司估值 + 敏感性分析 + 历史估值带。适合需要深入研究、精确目标价的场景。大约需要 3 步完成。
2. 精简版（Level 1 估值） — 基于可比公司估值（PE/PB/PS 倍数）+ 一致预期 + 情景分析，快速生成专业研报。无复杂 Excel 建模，速度更快。大约需要 2 步完成。

你选哪种？

English:

The equity report can be built at two valuation depths:

1. Full version (with financial model) — Complete 3-statement financial model (IS/BS/CF) + DCF absolute valuation + comparable companies + sensitivity analysis + historical valuation band. Best for in-depth research with precise target price. Approximately 3 steps.
2. Streamlined version (Level 1 valuation only) — Comparable company valuation (PE/PB/PS multiples) + consensus expectations + scenario analysis, generating a professional report without complex Excel modeling. Faster turnaround. Approximately 2 steps.

Which would you prefer?

Record the user's choice:

Key difference:

• L2: Task 2 produces a real Excel model (8+ tabs) with DCF. Task 3 reads numbers from Excel via openpyxl.
• L1: Skip Task 2 entirely. Task 1's research document contains all valuation inputs. Task 3 generates valuation tables directly from the research document (no Excel model needed).

If output_type = TEAR_SHEET: Skip this step entirely. Tear sheets always use Level 1.

⚠️ Core Principles — CARRY THESE INTO THE NEXT FILE

These principles apply to BOTH modes. Read them now. They are NOT repeated in the mode-specific files. If you skip them, you will produce a bad report.

Data Authenticity Rule

Prohibit fabricating data, eliminate scaffold/placeholders. See references/data-sources.md §Data Missing Handling + quality checklist A6-A8.

Step 4: Route NOW

Before starting Task 1: Tell the user the full flow and step count:

Chinese (L2):

我将为你生成深度研报（完整版），共 3 步：

• 第 1 步：深度研究分析（数据收集 + 六维分析 + 行业研究）→ 输出研究文档
• 第 2 步：财务建模与估值（Excel 三表模型 + DCF 估值 + 敏感性分析）
• 第 3 步：生成最终 PDF 研报（≥25页）

现在开始第 1 步。

English (L2):

I'll generate the full equity report in 3 steps:

• Step 1: Deep research analysis (data collection + six-dimension analysis + industry research) → Research Document
• Step 2: Financial modeling & valuation (Excel 3-statement model + DCF + sensitivity)
• Step 3: Generate final PDF report (≥25 pages)

Starting Step 1 now.

Chinese (L1):

我将为你生成深度研报（精简版），共 2 步：

• 第 1 步：深度研究分析（数据收集 + 六维分析 + 可比公司估值）→ 输出研究文档
• 第 2 步：生成最终 PDF 研报（≥25页，基于可比公司估值）

现在开始第 1 步。

English (L1):

I'll generate the streamlined equity report in 2 steps:

• Step 1: Deep research analysis (data collection + six-dimension analysis + comps-based valuation) → Research Document
• Step 2: Generate final PDF report (≥25 pages, comparable-company valuation)

Starting Step 1 now.

Stop sequential reading here. The mode-specific file you read next has all execution instructions you need. The REFERENCE SECTION below (Output Type Comparison, Task architecture, File Index, Common Rules) is a look-up resource — consult specific sub-sections when you need to locate a file or confirm a mode detail. Do not read it cover-to-cover.

REFERENCE SECTION

You do not need to read this section sequentially. It is reference material for when you need to look up mode details, task architecture, or file locations. The mode-specific files will tell you which files to read and when.

Output Type Comparison

Mode A: Tear Sheet / 投资速览 (Single Session)

A concise 3-5 page PDF produced entirely within one session.

Phase 0 → Phase 1 → Phase 2 → Phase 3 → Phase 4 → Phase 5 → PDF delivered
(Router)   (Data)    (Analysis) (Synthesis) (Layout)  (QA)

• Entry file: SKILL-tearsheet.md
• Output document: Analysis Brief → references/analysis-brief-template.md
• Layout: output/tearsheet-layout.md → output/tearsheet.css
• QA: output/tearsheet-qa.md

Mode B: Equity Report / 深度研究 (Multi-Task Architecture)

An in-depth ≥25 page PDF built across 2 or 3 Tasks depending on valuation depth. Both L1 and L2 share the same Task 1.

L2 (Full Version — 3 Tasks)

Task 1 (SKILL-equity-task1.md):  Phase 0 → Phase 1 → Phase 2 → Phase 3 → Research Document (.md)
                                                                                  ↓
Task 2 (SKILL-task2-model.md):   Financial Model (.xlsx) + Valuation Analysis (.md)
                                                                                  ↓
Task 3 (SKILL-task3-report.md):  Final PDF Report (≥25 pages)

L1 (Streamlined Version — 2 Tasks)

Task 1 (SKILL-equity-task1.md):  Phase 0 → Phase 1 → Phase 2 → Phase 3 → Research Document (.md)
                                                                                  ↓
Task 3 (SKILL-task3-report.md):  Final PDF Report (≥25 pages, L1 mode)

Universal Task Rules (Apply to Both L1 and L2)

1. Never chain Tasks automatically. Each Task ends with delivery + STOP.
2. User continues with a single word: "下一步", "继续", or "continue" — no file uploads needed.
3. Session context carries files. The agent maintains the file list internally. When the user says "continue", the agent reads the previously generated files from the session automatically.
4. Data flows via files, not memory. Task 2 reads Task 1's document. Task 3 reads Task 2's Excel (L2) or Task 1's document (L1). All financial numbers in Task 3's PDF must tie back to either the Excel model (L2) or the research document (L1).

File Index

All paths are relative to this skill's root directory.

Entry Points

Analysis Frameworks (read on-demand per Hard Gate)

Moat classification, earnings-quality checks, management assessment, TAM/SAM/SOM, and competitive deep dive are all defined inline in the two handoff templates (references/research-document-template.md for equity reports, references/analysis-brief-template.md for tear sheets). No separate per-framework files.

Deep Research Modules (Equity Report Only — Phase 2.7)

Valuation Methods

Report Module Specs

References

Output Layer (Phase 4 layout + Phase 5 QA + CSS)

Scripts