# Earnings Review

AI Berkshire skill: 财报精读：一手资料深度解读.

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

## Description

AI Berkshire skill: 财报精读：一手资料深度解读. Source: skills/earnings-review.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/earnings-review.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.

# 财报精读：一手资料深度解读

对 $ARGUMENTS 进行财报精读分析。

**支持输入格式**：`公司名 季度`，例如：`腾讯 2025Q4`、`PDD 2025年报`、`美团 最新`（默认读取最近一期）

> "我从不看卖方研报，只读原始财报。", , 李录
>
> "我每天读500页。知识就是这样积累的，像复利一样。", , 巴菲特

## 设计理念

大多数AI投研工具依赖二手信息（新闻、研报摘要、数据网站）。但巴菲特和李录的核心能力是**读一手资料**, , 年报、季报、电话会纪要。

二手信息的问题：
- 被筛选过, , 分析师选择性呈现对其观点有利的数据
- 有时滞, , 等别人消化完，alpha已经没了
- 缺乏语境, , "收入增长15%"脱离了管理层对增长质量的讨论

本Skill直接解读一手资料，关注巴菲特和李录真正会看的内容。

## 执行流程

### 前置步骤：资料可得性评级

| 等级 | 特征 | 影响 |
|------|------|------|
| A级 | 获取到完整原文（10-K/年报/电话会纪要） | 正常执行全部步骤 |
| B级 | 仅获取到部分原文或第三方汇总 | 标注"非原始来源"，降低附注分析权重 |
| C级 | 仅有新闻报道和数据网站摘要 | 聚焦核心财务数据变化，跳过附注挖掘，标注"一手资料不足" |

### 第一步：获取一手资料

使用 Task 工具启动多个后台 Agent **并行**获取以下原始材料：

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