# AI Berkshire Industry Screening Skills: Complete Sector Analysis Toolkit

> Explore AI Berkshire's industry screening skills, including Industry Research and Industry Funnel. Automate sector analysis with value-chain mapping and quantitative filtering for high-conviction themes.

- Repository: [Xbt Lin/ai-berkshire](https://github.com/xbtlin/ai-berkshire)
- Tags: how-to-guide
- Published: 2026-07-27

---

**AI Berkshire provides two specialized industry-screening skills—Industry Research and Industry Funnel—that automate sector evaluation through value-chain mapping and quantitative filtering to surface high-conviction investment themes.**

The `xbtlin/ai-berkshire` repository delivers an open-source equity research framework designed for systematic sector analysis. Its industry-screening capabilities enable analysts to progress from broad market scans to deep-dive company assessments using structured markdown skill definitions and command-line automation tools.

## Industry Research Skill

The **Industry Research** skill performs comprehensive sector analysis by constructing investment logic chains and applying a rigorous "four-master" framework to headline companies.

### Core Capabilities

According to [`skills/industry-research.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/industry-research.md), this skill executes four critical functions:

- **Investment Logic Validation**: Builds and validates a complete investment thesis chain for the target sector
- **Value-Chain Mapping**: Generates a detailed industry-value-chain map covering global listed companies across A-share, HK, and US markets
- **Four-Master Analysis**: Applies the business, moat, risk, and management framework to sector leaders
- **Portfolio Allocation**: Outputs sector-level allocation recommendations based on the analysis

The skill leverages [`tools/report_audit.py`](https://github.com/xbtlin/ai-berkshire/blob/main/tools/report_audit.py) to perform data-integrity checks before finalizing reports, ensuring output quality meets institutional standards.

### Generated Outputs

When executed via `python3 scripts/run-skill.py industry-research`, the skill produces a markdown report (e.g., `~/新能源产业链投资研究报告.md`) containing the complete chain map, company comparison tables, four-master analyses, and allocation guidance.

## Industry Funnel Skill

The **Industry Funnel** skill acts as a quantitative pre-filter that rapidly screens dozens of sectors to identify the most promising themes for deeper investigation.

### Screening Methodology

Defined in [`skills/industry-funnel.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/industry-funnel.md), this skill implements a weighted scoring algorithm across four dimensions:

1. **Trend Strength**: Momentum and growth trajectory of the sector
2. **Market Size**: Total addressable market and expansion potential
3. **Competitive Dynamics**: Industry structure and competitive positioning
4. **Regulatory Environment**: Policy tailwinds or headwinds affecting the space

The skill ranks industries by composite score and outputs a shortlist of "funnel-passed" sectors ready for detailed research.

## Command-Line Usage Examples

Both skills expose CLI interfaces through [`scripts/run-skill.py`](https://github.com/xbtlin/ai-berkshire/blob/main/scripts/run-skill.py), enabling automation and integration into research workflows.

### Running Industry Research

Execute a full sector analysis for the new energy sector:

```bash
python3 scripts/run-skill.py industry-research "新能源"

```

This generates a comprehensive markdown report containing the value-chain map, four-master analyses, and portfolio allocation table saved to the home directory.

### Running Industry Funnel

Screen sectors using default parameters to generate a ranked shortlist:

```bash
python3 scripts/run-skill.py industry-funnel

```

The output displays a ranked table of sectors (e.g., "新能源", "半导体", "数字医疗") with funnel scores, highlighting the top three candidates for deep-dive research.

### Automating the Complete Workflow

Combine both skills to automate end-to-end sector screening:

```bash

# 1️⃣ Extract top-3 sectors from the funnel

SECTORS=$(python3 scripts/run-skill.py industry-funnel --top 3 --plain)

# 2️⃣ Generate detailed research for each shortlisted sector

for S in $SECTORS; do
    python3 scripts/run-skill.py industry-research "$S"
done

```

This pipeline first filters for high-probability sectors, then automatically launches comprehensive research reports for each candidate.

## Codex Integration and Quality Screening

Both skills are exposed as generated Codex slash-prompts for chat-based invocation:

- [`codex-prompts/industry-research.md`](https://github.com/xbtlin/ai-berkshire/blob/main/codex-prompts/industry-research.md) wraps the deep-research functionality
- [`codex-prompts/industry-funnel.md`](https://github.com/xbtlin/ai-berkshire/blob/main/codex-prompts/industry-funnel.md) provides the screening interface

Additionally, the **Quality-Screen** skill ([`skills/quality-screen.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/quality-screen.md)) complements the Industry Funnel by applying quantitative quality metrics—such as ROE consistency and cash-flow stability—to the initial sector shortlist, enabling a seamless transition from macro screening to micro fundamental analysis.

## Summary

- **Industry Research** ([`skills/industry-research.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/industry-research.md)) delivers deep sector analysis using value-chain mapping and four-master frameworks for companies across global exchanges.
- **Industry Funnel** ([`skills/industry-funnel.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/industry-funnel.md)) provides rapid quantitative screening across trend strength, market size, competitive dynamics, and regulatory factors.
- **CLI Integration** via [`scripts/run-skill.py`](https://github.com/xbtlin/ai-berkshire/blob/main/scripts/run-skill.py) enables automation of both individual skills and combined workflows.
- **Quality Integration** allows funnel results to flow directly into quantitative quality screening for refined investment candidates.

## Frequently Asked Questions

### What are the two main industry-screening skills in AI Berkshire?

AI Berkshire offers the **Industry Research** skill for deep-dive sector analysis and the **Industry Funnel** skill for high-level quantitative screening. Industry Research constructs value-chain maps and applies four-master analysis, while Industry Funnel ranks sectors by weighted scores across trend, size, competition, and regulatory criteria.

### How does the Industry Funnel skill determine which sectors to prioritize?

The skill evaluates sectors against four weighted criteria defined in [`skills/industry-funnel.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/industry-funnel.md): trend strength, market size, competitive dynamics, and regulatory environment. It calculates a composite funnel score for each sector and surfaces the highest-ranking candidates in a shortlist format suitable for immediate deep-dive research.

### Can I automate the transition from sector screening to detailed research?

Yes. Use [`scripts/run-skill.py`](https://github.com/xbtlin/ai-berkshire/blob/main/scripts/run-skill.py) to pipe the Industry Funnel output directly into Industry Research. Capture the top-ranked sectors using the `--top` and `--plain` flags, then iterate through the results to trigger comprehensive research reports for each sector automatically.

### What is the "four-master" analysis framework mentioned in the Industry Research skill?

The four-master framework evaluates companies across four dimensions: **business** model quality, competitive **moat** durability, operational **risk** factors, and **management** team capability. This structure is implemented in [`skills/industry-research.md`](https://github.com/xbtlin/ai-berkshire/blob/main/skills/industry-research.md) and applied to headline companies within the sector value chain to generate investment conviction levels.