Agent skill

Wechat Article Pipeline

by davinci-seven in davinci-seven/wechat-article-pipeline

把定稿Markdown和本地配图生成公众号兼容内联HTML、图片内嵌稳定版、复制预览、390px手机长截图及完整性和隐私报告。适用于公众号文章定稿后的排版、检查和交付;不负责改稿,也不会在未经确认时创建公众号草稿。

MITAuto-check passedProductivity & Automation

Install Wechat Article Pipeline

skills CLI
$ npx skills add davinci-seven/wechat-article-pipeline --skill wechat-article-pipeline -a claude-code

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

GitHub CLI
$ gh skill install davinci-seven/wechat-article-pipeline wechat-article-pipeline --agent claude-code

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

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

Facts

Skill name
wechat-article-pipeline
GitHub stars
158
Token cost
~1.1k tokens
SKILL.md length
95 words
Files
44
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

把定稿Markdown和本地配图生成公众号兼容内联HTML、图片内嵌稳定版、复制预览、390px手机长截图及完整性和隐私报告。适用于公众号文章定稿后的排版、检查和交付;不负责改稿,也不会在未经确认时创建公众号草稿。

  • Works in 7 steps: 计算原稿SHA256,并解析Markdown中的本地图片引用。 → 确认图片全部存在;缺图立即停止。 → 调用tools/render_wechat.py生成公众号兼容内联HTML、图片内… → …
  • Tasks that involve Messaging and chat bots
  • SKILL.md covers 输入, 必守规则, 执行 and 验收, plus 2 more sections
  • Calls python and pip

What it does

Wechat Article Pipeline is an agent skill from davinci-seven/wechat-article-pipeline. 把定稿Markdown和本地配图生成公众号兼容内联HTML、图片内嵌稳定版、复制预览、390px手机长截图及完整性和隐私报告。适用于公众号文章定稿后的排版、检查和交付;不负责改稿,也不会在未经确认时创建公众号草稿。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 49 other files (for example `README.md`, `docs/agent-prompt.md` and `docs/credits.md`).

It sits in Productivity & Automation, covering Messaging and chat bots and Markdown. It works with WeChat, OpenAI and Playwright. The repository describes itself as: 面向 Windows 和 AI Agent 的公众号文章排版流水线:Markdown + 本地配图 → 公众号兼容内联 HTML、发布稳定版、390px 手机预览、长截图与完整性校验报告。不改原稿,不自动发布。 The licence is MIT.

When your agent uses it

  • Tasks that involve Messaging and chat bots
  • Tasks that involve Markdown

Example prompts

  • “/wechat-article-pipeline”

Requirements

  • Python 3

Workflow steps

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

  1. 计算原稿SHA256,并解析Markdown中的本地图片引用。
  2. 确认图片全部存在;缺图立即停止。
  3. 调用tools/render_wechat.py生成公众号兼容内联HTML、图片内嵌发布稳定版、390px手机截图页、图片证据表和完整性数据。
  4. 使用已安装的gzh-design脚本校验组件和HTML,并用其wrap_preview.py生成带一键复制按钮的预览页。
  5. 调用tools/capture_mobile_screenshot.py在390px视口截取完整长图,超高页面由脚本自行分段拼接。没有浏览器或截图能力时,把长截图标为“未运行”,不得用截图页代替并声称完成。
  6. 再次计算原稿SHA256,确认原稿未变化。
  7. 调用tools/sanitize_public_output.py生成隐私报告。HTML只扫描,不改写;报告里的警告需要人工判断。

What it can do on your machine

Read from SKILL.md and the folder at commit ab90abb. 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:

    • python
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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 Article Pipeline loads about 1.1k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 95 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 davinci-seven/wechat-article-pipeline at commit ab90abb, republished under its MIT licence (© davinci-seven). 95 words, ~1,114 tokens.

Download SKILL.mdSave it as .claude/skills/wechat-article-pipeline/SKILL.md (or your agent's skills folder). This skill also uses 43 other files; get the full folder from GitHub.
name
wechat-article-pipeline
description
把定稿Markdown和本地配图生成公众号兼容内联HTML、图片内嵌稳定版、复制预览、390px手机长截图及完整性和隐私报告。适用于公众号文章定稿后的排版、检查和交付;不负责改稿,也不会在未经确认时创建公众号草稿。

公众号文章排版

把已经定稿的Markdown和本地配图交给本仓库现有脚本处理,输出可复制到公众号的HTML、手机预览和可核对的报告。

输入

  • 一份定稿Markdown
  • Markdown引用的全部本地图片
  • 可选主题;未指定时使用olive-journal
  • 可选输出目录;不得把产物写回或覆盖原稿

如果文章目录里有多份Markdown,先请用户明确指定。不得自行猜测哪份是定稿。

必守规则

  • 不改正文,不改写、缩写、合并或重排任何段落。
  • 不调整图片顺序和图注。
  • 不覆盖原稿。运行前后计算原稿SHA256;不一致立即停止。
  • 先检查全部本地图片。缺少任意一张,立即停止并列出缺失项,不继续生成残缺结果。
  • 只有实际执行过且拿到结果的检查才能写“通过”。无法运行的检查标为“未运行”,并说明原因。
  • HTML正文只扫描隐私,不自动改写。JSON、Markdown和日志可用现有清理脚本处理本机路径。
  • 未经用户明确确认,不创建公众号草稿,不调用发布接口。
  • 不调用md2wechat convert二次渲染已经生成的HTML。

执行

先定位仓库根目录、定稿Markdown和图片,再选择当前系统对应的入口。

Windows

优先调用仓库现有的一键脚本:

powershell
.\tools\公众号排版.ps1 -ArticleDir "F:\文章\我的文章" -Markdown "终稿.md" -OpenPreview

路径必须加引号。中文目录、空格和括号在不加引号时会被拆开,<和>在PowerShell里还是重定向符,直接写占位尖括号会报语法错误。

只有用户指定主题时才追加-Theme moyu-green(可选值用-ListThemes查看)。脚本失败后保留真实错误,不绕过图片、HTML或隐私检查。

该脚本已包含全部8个步骤,含长截图。未安装Playwright时第6步会告警并把screenshot_status标为“未运行”,其余步骤照常完成。

非Windows或ChatGPT代码执行环境

调用仓库现有脚本完成同一条流水线,不另写一套渲染器:

  1. 计算原稿SHA256,并解析Markdown中的本地图片引用。
  2. 确认图片全部存在;缺图立即停止。
  3. 调用tools/render_wechat.py生成公众号兼容内联HTML、图片内嵌发布稳定版、390px手机截图页、图片证据表和完整性数据。
  4. 使用已安装的gzh-design脚本校验组件和HTML,并用其wrap_preview.py生成带一键复制按钮的预览页。
  5. 调用tools/capture_mobile_screenshot.py在390px视口截取完整长图,超高页面由脚本自行分段拼接。没有浏览器或截图能力时,把长截图标为“未运行”,不得用截图页代替并声称完成。
  6. 再次计算原稿SHA256,确认原稿未变化。
  7. 调用tools/sanitize_public_output.py生成隐私报告。HTML只扫描,不改写;报告里的警告需要人工判断。

完整命令如下。把ARTICLE、LAYOUT、GZH三个变量换成实际路径即可,其余原样执行:

bash
ARTICLE="/path/to/我的文章"            # 文章目录
LAYOUT="$ARTICLE/公众号排版"            # 产物目录,不要写回原稿目录之外
GZH="$HOME/.codex/skills/gzh-design"   # 已安装的gzh-design

# 1. 渲染:正文HTML、发布稳定版、手机截图页、图片证据表、完整性数据
python tools/render_wechat.py \
  --markdown "$ARTICLE/终稿.md" \
  --output-root "$LAYOUT" \
  --theme olive-journal

# 渲染器按主题决定文件名,从报告里读,不要自己拼。
# 路径通过sys.argv传入,不要拼进Python字符串,否则Windows路径的反斜杠会被当转义符。
read_field() {
  python -c "import json,sys;print(json.load(open(sys.argv[1],encoding='utf-8'))[sys.argv[2]])" \
    "$LAYOUT/source-integrity.json" "$1"
}
CLEAN=$(read_field clean_html)
STABLE=$(read_field stable_html)
MOBILE=$(read_field mobile_screenshot_page)
PREVIEW="${STABLE/_发布稳定版.html/_预览.html}"

# 2. 组件与HTML校验,退出码非0即为不合规
python "$GZH/scripts/component_lint.py" "$GZH"
python "$GZH/scripts/validate_gzh_html.py" "$CLEAN"
python "$GZH/scripts/validate_gzh_html.py" "$STABLE"

# 3. 带一键复制按钮的预览页
python "$GZH/scripts/wrap_preview.py" "$STABLE" "$PREVIEW"

# 4. 390px手机端完整长截图(需要Playwright)
python tools/capture_mobile_screenshot.py \
  --page "$MOBILE" \
  --output "$LAYOUT/output/终稿_390px_手机长截图.png"

# 5. 清理本机路径并检查敏感信息
python tools/sanitize_public_output.py \
  --article-dir "$ARTICLE" \
  --layout-root "$LAYOUT"

第4步的退出码含义:0成功,2手机截图页不存在,3未安装Playwright,4浏览器执行失败。返回3时先尝试pip install playwright && python -m playwright install chromium;仍然不行就把长截图标为“未运行”,不得用手机截图页HTML冒充长截图。

tools/stitch_screenshot.py用于已经手动分段截好图、需要拼接的场合;走上面第4步时不需要它,脚本内部会自行处理超高页面的分段拼接。

后续校验、预览包装和截图必须依据当前环境中的实际脚本位置执行,不得伪造命令输出。

验收

至少核对并如实汇报:

  • 公众号兼容内联HTML
  • 图片内嵌的发布稳定版HTML
  • 带一键复制按钮的预览页
  • 390px手机端预览和完整长截图
  • 图片证据表,且顺序、路径和图注与原稿一致
  • 原稿运行前后SHA256及source_unchanged结果
  • HTML校验的实际结果
  • privacy-audit.json中的错误和警告
  • 未运行的检查及原因
  • ChatGPT环境中的轻量Preview和完整一键复制HTML是否都已交付,并且身份标注清楚

任何必需检查失败时,不把整套任务写成“已完成”。先返回失败位置、真实输出和可执行的下一步。

ChatGPT双交付

当执行环境是ChatGPT,并且已经生成带“一键复制到公众号”按钮的完整预览HTML时,最终必须同时交付以下两份HTML,不能互相替代。

ChatGPT截图预览

在最终回复中额外提供一个HTML代码块,供ChatGPT直接切换Preview、小窗或全屏查看和截图。

  • 输出完整可运行的HTML文档,包括<!doctype html>、顶部工具栏、预览容器和复制按钮。
  • 视觉主题与正式预览保持一致,至少展示标题、开头正文和代表性内容。
  • 为控制回复体积,可以只保留代表性图片、缩略图或少量内容;不要把数MB的data URI塞进聊天回复。
  • 在页面工具栏和回复说明中明确标记“轻量预览,非全文”。复制按钮也要提示复制的是预览片段,不能让用户误以为已经复制完整文章。
  • 不得把这份轻量HTML记作完整文章、发布稳定版或公众号终审文件。
  • 如果当前客户端没有HTML Preview入口,仍保留这份代码块,并以完整HTML附件作为可用回退。
公众号一键复制HTML

同时提供可下载的完整预览HTML,作为真实复制到公众号编辑器和发布前终审的唯一来源。

  • 保留全部正文、图片顺序、alt文本和图注。
  • 使用已经校验的发布稳定版正文;图片优先内嵌为data URI,避免依赖本地路径。
  • 保留顶部工具栏和“一键复制到公众号”按钮,按钮只复制完整正文容器,不复制工具栏或提示文字。
  • 不得为了生成轻量Preview而删减或覆盖这份完整HTML。
  • 没有实际测试复制按钮时,标为“未测试”,不能声称复制成功。

最终回复必须用这两个固定名称区分产物:

  • ChatGPT截图预览:聊天内轻量Preview,用于查看和截图,不是全文。
  • 公众号一键复制HTML:完整文章,用于真实复制和发布前终审。

不要因为已经提供完整HTML下载附件,就省略ChatGPT环境中的轻量Preview代码块;也不要只给轻量Preview而漏掉完整HTML附件。

发布边界

默认只生成本地文件,不登录公众号、不上传素材、不创建草稿。只有用户在看到本次产物后明确要求创建公众号草稿,才进入单独的发布步骤;即使进入发布步骤,也直接使用已生成HTML,不调用md2wechat convert。

安装方法见docs/skill-install.md,日常参数和输出说明见README.md。

© davinci-seven, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 43 other files in the repository root of davinci-seven/wechat-article-pipeline.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • docs/agent-prompt.md
  • docs/credits.md
  • docs/preview-copy-button-screenshot.svg
  • docs/privacy-check.md
  • docs/skill-install.md
  • docs/theme-gallery.png
  • docs/windows-install.md
  • examples/demo-article/assets/setup.png
  • examples/demo-article/assets/status.png
  • examples/demo-article/sample-output/image-map.json
  • examples/demo-article/sample-output/output/assets
  • … and 29 more

Open the folder on GitHubat commit ab90abb

Compare with similar skills

Wechat Article Pipeline 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 Article Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Wechat Article Pipeline this skilldavinci-seven/wechat-article-pipeline158—~1.1kAutomated safety check: PassMIT
Wechat Article Fetchcat-xierluo/legal-skills720—~793Automated safety check: PassMIT
Qiaomu Epub Book Generatorjoeseesun/qiaomu-epub-book-generator134—~1.1kAutomated safety check: PassNone
Web To Markdownrookie-ricardo/erduo-skills935—~894Automated safety check: PassMIT
Wechat Article Formatterhuangserva/servasyy_skills168—~688Automated safety check: NotesNone
Wechat Md PublisherLeoYeAI/openclaw-master-skills2.2k—~3kAutomated safety check: PassMIT

Similar skills

  • Wechat Article Fetch

    cat-xierluo/legal-skills

    抓取微信公众号文章(mp.weixin.qq.com)到本地。当用户发来公众号链接要求"抓取""保存""存下来""归档""留痕""转成 Markdown"时使用。默认双产出:Markdown 整理版(供检索引用)+ HTML 原件保真归档(离线双击可读,供回溯核对)。默认 HTTP 直抓零依赖,失败自动切浏览器兜底。

    720 GitHub stars~793 tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Qiaomu Epub Book Generator

    joeseesun/qiaomu-epub-book-generator

    Generate EPUB ebooks from Markdown files with SVG→PNG conversion, remote/local image embedding, compressed illustrations, and WeChat Reading compatibility.

    134 GitHub stars~1.1k tokensUpdated 6 mo ago
    Documents & OfficeAuto-check passed
  • Web To Markdown

    rookie-ricardo/erduo-skills

    Convert a web URL into cleaned Markdown with deterministic routing.

    935 GitHub stars~894 tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Wechat Article Formatter

    huangserva/servasyy_skills

    将 Markdown 文章转换为微信公众号 HTML 格式,支持自动插入配图、微信样式优化. An agent skill from huangserva/servasyy_skills.

    168 GitHub stars~688 tokensUpdated 8 days ago
    Productivity & AutomationAuto-check: notes
  • Wechat Md Publisher

    LeoYeAI/openclaw-master-skills

    发布 Markdown 文章到微信公众号,支持草稿管理、多主题、智能图片处理、自动封面图。推荐与 news-to-markdown-skill 配合使用实现一键转载。

    2.2k GitHub stars~3k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Wechat Publisher

    NeverSight/learn-skills.dev

    一键发布 Markdown 到微信公众号草稿箱。基于 wenyan-cli,支持多主题、代码高亮、图片自动上传. An agent skill from NeverSight/learn-skills.dev.

    217 GitHub starsUsed in 1 repo~1.2k tokens
    Productivity & AutomationAuto-check passed

Questions about Wechat Article Pipeline

What does Wechat Article Pipeline do?

把定稿Markdown和本地配图生成公众号兼容内联HTML、图片内嵌稳定版、复制预览、390px手机长截图及完整性和隐私报告。适用于公众号文章定稿后的排版、检查和交付;不负责改稿,也不会在未经确认时创建公众号草稿。. Wechat Article Pipeline is an agent skill from davinci-seven/wechat-article-pipeline.

When should I use Wechat Article Pipeline?

Wechat Article Pipeline fits situations like: tasks that involve Messaging and chat bots; tasks that involve Markdown.

How do I install Wechat Article Pipeline in Claude Code?

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

How do I install Wechat Article Pipeline in Codex?

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

Can I use Wechat Article Pipeline 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 davinci-seven/wechat-article-pipeline --skill wechat-article-pipeline -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-pipeline, .gemini/skills/wechat-article-pipeline, .github/skills/wechat-article-pipeline and .opencode/skills/wechat-article-pipeline in your project.

What does Wechat Article Pipeline need to run?

Going by SKILL.md and its folder, Wechat Article Pipeline needs the command-line tools its instructions call (python and pip). Our summary lists: Python 3.

Does Wechat Article Pipeline access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Wechat Article Pipeline 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 Article Pipeline use?

Wechat Article Pipeline is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Wechat Article Pipeline use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 Article Pipeline?

Skills that share tags, products or a category with Wechat Article Pipeline: Wechat Article Fetch (cat-xierluo/legal-skills, 720 stars), Qiaomu Epub Book Generator (joeseesun/qiaomu-epub-book-generator, 134 stars), Web To Markdown (rookie-ricardo/erduo-skills, 935 stars) and Wechat Article Formatter (huangserva/servasyy_skills, 168 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Wechat Article Pipeline?

davinci-seven (a GitHub user) maintains it in davinci-seven/wechat-article-pipeline, which has 158 GitHub stars. The repository was last updated on August 15, 2026.

Source: davinci-seven/wechat-article-pipeline on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.