# Private Company Research

AI Berkshire skill: 未上市公司研究：多Agent并行深度研究框架.

- Repository: https://github.com/xbtlin/ai-berkshire (16972 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add xbtlin/ai-berkshire --skill private-company-research -g -a claude-code -y`
Codex: `npx skills add xbtlin/ai-berkshire --skill private-company-research -g -a codex -y`
Cursor: `npx skills add xbtlin/ai-berkshire --skill private-company-research -g -a cursor -y`
Gemini CLI: `npx skills add xbtlin/ai-berkshire --skill private-company-research -g -a gemini-cli -y`

## Description

AI Berkshire skill: 未上市公司研究：多Agent并行深度研究框架. Source: skills/private-company-research.md.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

## Codex adapter note

This skill is generated from `skills/private-company-research.md` so Claude Code and Codex users share one canonical workflow.

- Treat `$ARGUMENTS` as the user's request in the current Codex thread.
- When the source mentions Claude-only surfaces such as Task, Agent, WebSearch, Bash, Read, or Write, use the closest Codex capability available in this session: subagents when available, web search when needed, shell commands for local tools, and normal file edits for workspace files.
- Use shared project tools from `tools/` in this repository. Prefer running commands from the repository root with paths like `python3 tools/financial_rigor.py ...`; if the current thread starts outside the repo, locate the actual checkout path first instead of assuming a fixed home-directory path.
- Before starting research, run the `date` command to confirm today's date; treat it as the baseline for "latest" data and state the data cutoff date in the report header. Never assume the current date from training data.
- Preserve the research quality rules from `AGENTS.md`: cross-check financial data, use exact arithmetic tools for valuation/math, and clearly label uncertainty and source gaps.

# 未上市公司研究：多Agent并行深度研究框架

对 $ARGUMENTS 进行团队化深度研究分析。专为蚂蚁集团、小红书、SpaceX、Stripe 等未上市公司设计。

**最终目标**：在信息天然稀缺的条件下，尽可能还原这家公司的**真实价值**, , 不是市场给的估值，而是生意本身值多少钱。

## 框架特点

未上市公司 vs 上市公司研究的核心差异：
- **无标准化财报**：需多源拼凑、交叉验证
- **估值锚定少**：依赖融资轮次、可比公司法、情景推演
- **信息不对称大**：需要更多"拼图式"研究方法
- **退出路径不确定**：IPO/并购/二级转让均有可能

## AI研究偏见自觉（本框架的核心前提）

未上市公司是AI研究偏见最严重的领域。必须时刻警惕以下陷阱：

**核心矛盾**：AI擅长结构化已有信息，但未上市公司的信息天然稀缺。这会导致：
1. **虚假保守**：因为资料少，AI倾向给出保守/模糊的结论，但资料少≠公司不好
2. **虚假精确**：为了填满报告模板，AI可能用"合理推测"伪装成"有据分析"
3. **对标陷阱**：强行与上市公司对标时，会继承上市公司的估值逻辑，忽略未上市公司的独特价值
4. **幸存者偏差**：网上能搜到的公司信息往往有正面偏向（公司主动传播的多是好消息）

The rest: https://github.com/xbtlin/ai-berkshire/blob/HEAD/codex-skills/private-company-research/SKILL.md