Agent skill

WeChat Official Account Article

Produces a publish-ready WeChat official account article on a technical or business topic with three agents: an author, an editor and a reader who reviews from the audience's side.

MITAuto-check passedWriting & Content

SKILL.md written in Chinese; this summary is our English description.

Install WeChat Official Account Article

skills CLI

$ npx skills add xbtlin/ai-berkshire --skill wechat-article -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install xbtlin/ai-berkshire wechat-article --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex-skills/wechat-article .claude/skills/wechat-article && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "wechat-article" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article into .claude/skills/wechat-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wechat-article", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add xbtlin/ai-berkshire --skill wechat-article -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install xbtlin/ai-berkshire wechat-article --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .agents/skills && cp -r skills-src/codex-skills/wechat-article .agents/skills/wechat-article && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "wechat-article" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article into .agents/skills/wechat-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wechat-article", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add xbtlin/ai-berkshire --skill wechat-article -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install xbtlin/ai-berkshire wechat-article --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/codex-skills/wechat-article .cursor/skills/wechat-article && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "wechat-article" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article into .cursor/skills/wechat-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wechat-article", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/xbtlin/ai-berkshire.git --path codex-skills/wechat-article

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add xbtlin/ai-berkshire --skill wechat-article -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install xbtlin/ai-berkshire wechat-article --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/codex-skills/wechat-article .gemini/skills/wechat-article && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "wechat-article" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article into .gemini/skills/wechat-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wechat-article", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install xbtlin/ai-berkshire wechat-article

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add xbtlin/ai-berkshire --skill wechat-article -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .github/skills && cp -r skills-src/codex-skills/wechat-article .github/skills/wechat-article && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "wechat-article" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article into .github/skills/wechat-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wechat-article", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add xbtlin/ai-berkshire --skill wechat-article -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install xbtlin/ai-berkshire wechat-article --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/xbtlin/ai-berkshire.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/codex-skills/wechat-article .opencode/skills/wechat-article && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "wechat-article" agent skill from https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/wechat-article into .opencode/skills/wechat-article/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wechat-article", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: wechat-article
GitHub stars: 17k
Token cost: ~1.5k tokens
SKILL.md length: 362 words
Files: 1
Skills in repo: 22
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Produces a publish-ready WeChat official account article on a technical or business topic with three agents: an author, an editor and a reader who reviews from the audience's side.

Works in 3 steps: 深度——对得起花时间读完的人（作者负责） → 可读性——结构清晰、节奏好、不劝退（编辑负责） → 真的能看懂——目标读者不会在中途放弃（读者负责）
Turning a research paper or technical report into a readable WeChat article
SKILL.md covers Codex adapter note, 设计理念, 阶段一：研究与素材收集 and 阶段二：作者Agent写初稿, plus 4 more sections
Calls python3 and pdftoppm

What it does

The skill takes a topic, such as an explainer of a technical report, and produces an article for a WeChat official account. It confirms positioning first: the target reader, the depth (popular science, medium or hardcore), the length (3000 to 4000 characters by default), whether source papers and figures should be downloaded, and the writing style, which defaults to conversational.

Work runs in stages. Two or three research agents run in parallel to collect core content, industry background and optional comparisons, and the results are condensed into a core argument, key data points, a figure list and an outline of six to eight sections. An author agent then writes the draft from a detailed prompt, an editor agent refines structure and wording, and a reader agent reads as the intended audience, bringing in the outside view that a single writer lacks.

When your agent uses it

Turning a research paper or technical report into a readable WeChat article
Writing a long-form WeChat post with research, drafting and review stages
Checking whether a draft is clear to a non-expert reader
Planning an outline and figure list before writing

Example prompts

“Write a WeChat article explaining the Qwen3 technical report for readers with some technical background.”
“Produce a medium-depth article on why Buffett avoids tech stocks, around 3000 characters.”
“Draft a conversational WeChat article on large model OPD, starting with an outline and a figure list.”

Requirements

Web search access for the research agents

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

深度——对得起花时间读完的人（作者负责）
可读性——结构清晰、节奏好、不劝退（编辑负责）
真的能看懂——目标读者不会在中途放弃（读者负责）

What it can do on your machine

Read from SKILL.md and the folder at commit efa220f. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- python3
- pdftoppm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

WeChat Official Account Article loads about 1.5k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 362 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~24
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xbtlin/ai-berkshire at commit efa220f, republished under its MIT licence (© xbtlin). 362 words, ~1,454 tokens.

Download SKILL.mdSave it as .claude/skills/wechat-article/SKILL.md (or your agent's skills folder).

name: wechat-article
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.

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：

深度——对得起花时间读完的人（作者负责）
可读性——结构清晰、节奏好、不劝退（编辑负责）
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）

Show full SKILL.md (152 more words)Show less

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：

研究Agent A：核心内容研究

如果是论文解读：下载论文PDF、提取核心贡献、关键图表、实验结果
如果是技术主题：搜索最新进展、关键论文、技术细节
如果是商业/投资主题：搜索最新数据、行业报告、竞争格局

研究Agent B：行业背景与应用

搜索该技术/主题的行业落地情况
哪些公司在用？效果如何？
最新的发展趋势和里程碑事件

研究Agent C（可选）：竞品/对比研究

同类方法/产品的对比
历史发展脉络
未来演进方向

第三步：整理素材框架

研究Agent全部完成后，整理出：

核心论点（一句话概括文章要传达的核心信息）
关键数据（3-5个最有冲击力的数据点）
配图清单（需要哪些图，来源是什么）
文章大纲（6-8个章节的标题和核心内容）

阶段二：作者Agent写初稿

使用 Agent 工具启动作者Agent，给出详细的写作指令。

作者Agent的Prompt模板

你是一位深度技术写作者（Author Agent），需要写一篇微信公众号文章。

## 目标读者
{根据第一步确认的读者画像}

## 写作风格要求
- 纯中文表达，避免中英文夹杂（技术术语首次出现时给英文，后续用中文）
- 像写给聪明的朋友看的技术科普，不是学术论文翻译
- 用类比帮助理解，但类比要贴切、不俗套
- 关键公式/数据要有，但每个都要用大白话解释
- 不用emoji
- 段落不超过4行（公众号阅读环境）

## 核心内容
{整理好的素材、数据、论点}

## 文章结构要求
1. **开头（前3段）**：必须有强钩子——用数据冲击力或反直觉的结论开场，不要用温和的类比开场
2. **背景**：为什么这件事重要？解决什么问题？
3. **核心内容（2-3节）**：技术深度在这里体现，但每个技术点都要有"大白话翻译"
4. **实证/案例**：用数据和案例说话，不要空谈
5. **行业影响/展望**：这件事对行业意味着什么
6. **结尾**：一句有传播力的判断收束，适合被截图转发

## 配图要求
- 论文解读类文章：必须从论文PDF中提取原图，直接用 `![描述](相对路径)` 插入文章，不要用 [图X：描述] 占位符
- 提取方法：用 pdftoppm 将PDF页面渲染为高分辨率PNG（至少900 DPI），再用 PIL 裁切目标图表区域
- 每张图不小于500KB，确保高清
- 图片统一存放在 `assets/{主题简称}/` 目录下
- 非论文类文章：如需配图，搜索并下载合适的图片，同样直接插入

## 公式要求
- 所有数学公式使用 LaTeX 格式：行内用 `$...$`，独立公式用 `$$...$$`
- 禁止用纯文本写公式（如 `> D_KL(P || Q) = ...`），必须用 LaTeX 渲染格式
- 每个公式后面仍然要配"大白话翻译"

请写出完整的文章初稿，约{目标字数}字。

作者Agent完成后

检查初稿文件是否生成，阅读全文确认内容完整性。

阶段三：编辑Agent + 读者Agent并行审阅

初稿完成后，使用 Agent 工具在同一条消息中启动编辑Agent和读者Agent。

编辑Agent的Prompt模板

你是一位资深公众号编辑（Editor Agent）。请对以下文章进行精修审阅。

## 审阅标准
1. **标题**：是否在朋友圈能吸引点击？是否会被截断（超过30字）？
2. **开头**：前3段能否留住读者？钩子是否足够强？
3. **结构**：逻辑链是否流畅？有无跳跃或断层？
4. **深度与可读性平衡**：公式/技术部分是否真的通俗？有无"假装通俗但没解释清楚"的地方？
5. **节奏**：有无太长的段落？每节长度是否合适？
6. **配图**：图片是否已实际插入（非占位符）？位置是否在读者最需要视觉辅助时出现？
7. **结尾**：有无传播力？读者看完会想转发吗？

## 文章全文
{完整初稿}

## 输出格式
1. 总体评价（3-5句话）
2. 标题修改建议（给2-3个备选）
3. 逐节修改建议（给出"原文→建议修改为"的具体对照）
4. 最关键的3个改进点

读者Agent的Prompt模板

你是一位{目标读者画像}（Reader Agent）。请从读者视角审读以下文章。

## 你的背景
{具体描述目标读者的知识水平和阅读习惯}

## 文章全文
{完整初稿}

## 请回答以下问题
1. 读完前3段，你会继续读下去吗？为什么？
2. 哪些地方"看不懂"或"需要重读才能理解"？具体是哪句话？
3. 技术/公式部分你看懂了吗？"大白话翻译"是否帮到你了？
4. 文章的核心类比贴切吗？有更好的类比吗？
5. 太长还是太短？会在哪里失去耐心？
6. 读完后你能用一句话概括文章核心观点吗？
7. 你会转发这篇文章吗？转发时你会说什么？
8. 有没有你想了解但文章没覆盖的问题？

阶段四：定稿

第一步：综合两个Agent的反馈

重点关注以下高频问题：

问题类型	编辑常见反馈	读者常见反馈	处理方式
开头太弱	钩子不够强	前3段没动力继续	用数据/反直觉结论重写开头
技术段劝退	公式太密集	某段需要重读3遍	删公式或图片化，加更直觉的类比
节奏拖沓	某节太长	某处失去耐心	合并或删减（尤其是后半段重复的技术解释）
结尾无力	缺传播力	不会转发	重写为一句可截图传播的判断
概念跳跃	逻辑有断层	某处"突然看不懂了"	补过渡句或背景解释

第二步：执行修改

根据反馈重写文章。核心修改原则：

编辑和读者都指出的问题，必须改
只有编辑指出的问题，大概率要改（编辑的专业判断通常准确）
只有读者指出的问题，视情况改（读者反馈代表真实体验，但不一定每条都需要响应）
两者矛盾时，偏向读者（编辑追求完美，但读者体验是最终标准）

第三步：提取配图

论文解读类文章必须在定稿前完成配图提取：

渲染：pdftoppm -png -r 900 -f {页码} -l {页码} 论文.pdf /tmp/page（900 DPI起步，如果图片不到500KB则升到1200或1500 DPI）
定位：先用150 DPI渲染全页，目视确认各图表的像素坐标
裁切：用 PIL 按坐标裁切，compress_level=1 保存，确保每张 ≥ 500KB
存储：保存到 assets/{主题简称}/ 目录，命名为 fig{序号}-{描述}.png
插入：文章中用 ![描述](../../assets/{主题简称}/fig{序号}-{描述}.png) 引用

第四步：产出最终文件

将定稿保存为 md 文件，文件末尾附上论文/资料原文链接：

markdown

**论文原文：**
- arXiv: {链接}

文件命名与存储

类型	路径	命名格式
技术主题	`reports/AI产业研究/`	`公众号-{主题关键词}-{YYYYMMDD}.md`
投资主题	`reports/{公司名}/`	`{公司名}-公众号-{YYYYMMDD}.md`
通用主题	`reports/`	`公众号-{主题关键词}-{YYYYMMDD}.md`

写作红线

不虚构数据。引用的数据必须有来源，搜不到就标注"估计"
不用AI腔调。禁止"让我们一起来看看"、"值得关注的是"、"不得不说"等套话
不过度承诺。技术文章不说"颠覆性的"、"革命性的"，用数据说话
公式必须配大白话。每个公式后面都要有一段"翻译成人话就是……"
公式必须用LaTeX。$$...$$ 格式，禁止纯文本公式
配图必须实际插入。论文解读类从PDF提取高清原图（≥500KB），禁止用 [图X] 占位符
表格括号注释要精确。描述概念时用准确的定义，不用模糊的动宾短语（如"文本来自教师"而非"学教师的文本"）
类比要一以贯之。全文用一个主线类比，不要每节换一个新类比
结尾必须有传播力。最后一句话要值得被单独截图转发

Files

Just SKILL.md in codex-skills/wechat-article of xbtlin/ai-berkshire.

Open the folder on GitHubat commit efa220f

Compare with similar skills

WeChat Official Account Article next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

WeChat Official Account Article compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
WeChat Official Account Article this skillxbtlin/ai-berkshire	17k	—	~1.5k	Automated safety check: Pass	MIT	yesterday
Khazix WeChat Article WriterKKKKhazix/khazix-skills	21k	2 repos	~2.9k	Automated safety check: Pass	MIT	6 days ago
WeChat Article Publisherjiji262/wechat-publisher	272	—	~4.4k	Automated safety check: Pass	None	2 mo ago
WeChat Article Rewritingaiworkskills/wechat-article-skills	667	1 repos	~2.2k	Automated safety check: Pass	Apache-2.0	15 days ago
Web Content Fetcheryaomindong1996/forge-admin	125	—	~898	Automated safety check: Pass	Apache-2.0	today
WeChat Article Writerliuyueyi/spring-ai-demo	138	1 repos	~244	Automated safety check: Pass	None	2 mo ago

Similar skills

Khazix WeChat Article Writer
KKKKhazix/khazix-skills
Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.
21k GitHub starsUsed in 2 repos~2.9k tokens
Writing & ContentAuto-check passed
WeChat Article Publisher
jiji262/wechat-publisher
Researches a topic, writes an illustrated WeChat Official Account article in a chosen author voice and sends it to the account's draft box.
272 GitHub stars~4.4k tokensUpdated 2 mo ago
Writing & ContentAuto-check passed
WeChat Article Rewriting
aiworkskills/wechat-article-skills
Rewrites, continues, or polishes an existing WeChat article draft using a configurable language model, sending the full draft text to that endpoint.
667 GitHub starsUsed in 1 repo~2.2k tokens
Writing & ContentAuto-check passed
Web Content Fetcher
yaomindong1996/forge-admin
Extract article content from any URL as clean Markdown. An agent skill from yaomindong1996/forge-admin.
125 GitHub stars~898 tokensUpdated today
Writing & ContentAuto-check passed
WeChat Article Writer
liuyueyi/spring-ai-demo
Runs a four-step workflow for WeChat official account articles: research the topic, draft in your saved style, produce five headline options, and tune the layout.
138 GitHub starsUsed in 1 repo~244 tokens
Writing & ContentAuto-check passed
WeChat Official Account Pipeline
aiworkskills/wechat-article-skills
Orchestrates the full WeChat official account workflow from topic to draft, chaining sub-skills for writing, review, layout, images and publishing.
667 GitHub stars~2k tokensUpdated 15 days ago
Writing & ContentAuto-check passed

Questions about WeChat Official Account Article

What does WeChat Official Account Article do?

Produces a publish-ready WeChat official account article on a technical or business topic with three agents: an author, an editor and a reader who reviews from the audience's side. The skill takes a topic, such as an explainer of a technical report, and produces an article for a WeChat official account. It confirms positioning first: the target reader, the depth (popular science, medium or hardcore), the length (3000 to 4000 characters by default), whether source papers and figures should be downloaded, and the writing style, which defaults to conversational.

When should I use WeChat Official Account Article?

WeChat Official Account Article fits situations like: turning a research paper or technical report into a readable WeChat article; writing a long-form WeChat post with research, drafting and review stages; checking whether a draft is clear to a non-expert reader; planning an outline and figure list before writing.

How do I install WeChat Official Account Article in Claude Code?

Run `npx skills add xbtlin/ai-berkshire --skill wechat-article -a claude-code`. Or copy the skill folder (codex-skills/wechat-article in xbtlin/ai-berkshire) into .claude/skills/wechat-article in your project. Claude Code loads it when a task matches its description.

How do I install WeChat Official Account Article in Codex?

Run `npx skills add xbtlin/ai-berkshire --skill wechat-article -a codex`. Or copy the skill folder (codex-skills/wechat-article in xbtlin/ai-berkshire) into .agents/skills/wechat-article in your project. Codex loads it when a task matches its description.

Can I use WeChat Official Account Article in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xbtlin/ai-berkshire --skill wechat-article -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wechat-article, .gemini/skills/wechat-article, .github/skills/wechat-article and .opencode/skills/wechat-article in your project.

What does WeChat Official Account Article need to run?

Going by SKILL.md and its folder, WeChat Official Account Article needs the command-line tools its instructions call (python3 and pdftoppm). Our summary lists: Web search access for the research agents.

Does WeChat Official Account Article access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is WeChat Official Account Article safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does WeChat Official Account Article use?

WeChat Official Account Article is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does WeChat Official Account Article use?

About 1.5k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to WeChat Official Account Article?

Skills that share tags, products or a category with WeChat Official Account Article: Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars), WeChat Article Publisher (jiji262/wechat-publisher, 272 stars), WeChat Article Rewriting (aiworkskills/wechat-article-skills, 667 stars) and Web Content Fetcher (yaomindong1996/forge-admin, 125 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains WeChat Official Account Article?

xbtlin (a GitHub user) maintains it in xbtlin/ai-berkshire, which has 16,652 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 6, 2026.

Source: xbtlin/ai-berkshire on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install WeChat Official Account Article

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Codex adapter note

微信公众号文章：作者-编辑-读者三Agent协作

设计理念

阶段一：研究与素材收集

第一步：明确文章定位

第二步：深度研究

第三步：整理素材框架

阶段二：作者Agent写初稿

作者Agent的Prompt模板

作者Agent完成后

阶段三：编辑Agent + 读者Agent并行审阅

编辑Agent的Prompt模板

读者Agent的Prompt模板

阶段四：定稿

第一步：综合两个Agent的反馈

第二步：执行修改

第三步：提取配图

第四步：产出最终文件

文件命名与存储

写作红线

Files

Compare with similar skills

Similar skills

More from xbtlin/ai-berkshire

Related

Questions about WeChat Official Account Article