# Wechat Article

AI Berkshire skill: 微信公众号文章：作者-编辑-读者三Agent协作.

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

## Description

AI Berkshire skill: 微信公众号文章：作者-编辑-读者三Agent协作. Source: skills/wechat-article.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/wechat-article.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.

# 微信公众号文章：作者-编辑-读者三Agent协作

对 $ARGUMENTS 进行深度研究，产出一篇可直接发布的微信公众号文章。三个Agent各司其职：作者写深度初稿，编辑精修结构和表达，读者从目标受众视角审读。

**支持输入格式**：主题描述，例如：`大模型OPD技术解读`、`Qwen3技术报告解读`、`为什么巴菲特不买科技股`

---

## 设计理念

一篇好的公众号文章需要同时满足三个维度：
1. **深度**, , 对得起花时间读完的人（作者负责）
2. **可读性**, , 结构清晰、节奏好、不劝退（编辑负责）
3. **真的能看懂**, , 目标读者不会在中途放弃（读者负责）

单人写作容易"自嗨", , 写的人觉得清楚，读的人看不懂。三Agent协作的本质是**强制引入外部视角**。

---

## 阶段一：研究与素材收集

### 第一步：明确文章定位

在开始写作之前，先确认以下信息（如用户未指定则主动询问）：

| 维度 | 需要确认 | 默认值 |
|------|---------|--------|
| **目标读者** | 技术背景程度 | 有点技术背景但非该领域专家 |
| **文章深度** | 科普/中深度/硬核 | 中深度（有公式但要解释清楚） |
| **文章长度** | 字数范围 | 3000-4000字 |
| **是否需要下载原始论文/资料** | 需要PDF/配图 | 是 |
| **写作风格** | 正式/对话式/犀利 | 对话式（像写给聪明的朋友） |

### 第二步：深度研究

使用 Agent 工具**并行**启动2-3个研究Agent，收集足够的素材：

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