# Industry Funnel

AI Berkshire skill: 行业漏斗筛选：从全市场到 3 家的价值投资精选流程.

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

## Install

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

## Description

AI Berkshire skill: 行业漏斗筛选：从全市场到 3 家的价值投资精选流程. Source: skills/industry-funnel.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/industry-funnel.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.

# 行业漏斗筛选：从全市场到 3 家的价值投资精选流程

对 $ARGUMENTS 行业/方向执行漏斗式价值投资筛选，从全市场扫描逐层精选到 3 家终选标的。

## 适用场景

当你说出一个行业或投资方向（如"AI 算力"、"创新药"、"机器人"），想要：
1. 不遗漏任何重要标的（含 A 股、港股、美股、未上市候选）
2. 用统一标准过滤掉"故事股"和质量不足的公司
3. 把精力聚焦到真正值得深度研究的 3 家头部
4. 每层有明确的留/弃标准，可复盘可追溯

与 `industry-research` 的区别：
- `industry-research` 偏重产业链结构与全景，环节切片
- `industry-funnel` 偏重个股筛选漏斗，从全市场逐层精选到 3 家

两者可以互补：先用 `industry-research` 看清产业链格局，再用 `industry-funnel` 精选标的。

---

## 漏斗结构总览

```
第一层：全市场扫描     30-60 家   （活跃度+涨幅+市值前 30 的并集）
        ↓ 价值投资 5 条硬指标
第二层：粗筛             ≤ 10 家   （5 条全部及格 + 护城河 ★★★ 以上）
        ↓ 精细分析
第三层：精细分析          ≤ 10 家  （每家 300-500 字结构化分析）
        ↓ 终选
第四层：四大师深度分析     3 家     （每家 800-1200 字，巴芒段李四视角）
        ↓
输出：投资建议 + 操作信号 + 仓位建议
```

每层"过滤掉的标的"必须留下淘汰理由，不能黑箱。

---

## 第一步：全市场扫描入口

### 1.1 活跃股票定义（三类并集）

The rest: https://github.com/xbtlin/ai-berkshire/blob/HEAD/codex-skills/industry-funnel/SKILL.md