# Thesis Drift

AI Berkshire skill: 投资论文漂移检测：分清事实变化与措辞变化.

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

## Description

AI Berkshire skill: 投资论文漂移检测：分清事实变化与措辞变化. Source: skills/thesis-drift.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/thesis-drift.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.

# 投资论文漂移检测：分清事实变化与措辞变化

对 $ARGUMENTS 执行投资论文漂移检测。

**支持输入格式**：
- `公司名 旧报告路径 新报告路径`, 指定两份研究报告或论文快照进行对比
- `公司名 reports/{公司名}-thesis-旧日期.md reports/{公司名}-thesis-新日期.md`, 对比两份带日期的论文快照
- `公司名`, 自动查找 `reports/{公司名}-thesis.md` 及同目录历史快照；如果没有基线则转入缺失基线处理

> "当事实改变时，我就改变想法。你呢？", , 凯恩斯
>
> "股价波动不是论文漂移，事实变了才是。", , AI Berkshire

## 设计理念

长期持仓最难的不是每天读新闻，而是区分三件事：
- **事实改变**：收入、利润率、竞争格局、管理层行为、资本配置发生可验证变化
- **价格改变**：市场情绪或估值倍数变化，但生意本身未变
- **措辞改变**：两份报告表达不同，但底层证据和判断没有变化

投资论文漂移检测的目标是：**只在证据变化时承认论文变化**。不能因为报告换了写法就制造漂移，也不能因为股价涨跌就误判基本面。

本 Skill 依赖 `/thesis-tracker` 输出的结构化维度：核心假设清单、红线清单、估值锚点、追踪记录表。没有这些结构时，先补齐基线，再做漂移检测。

## 执行流程

### 第一步：判断操作模式

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