What is zhy-wechat-publish?

A tool for sending HTML articles to the draft area of a WeChat Official Account, China's account-based publishing platform. It can prepare article images, cover images, styling, author details, and comment settings for the draft.

Use it to upload an article and cover, generate a cover when configured, rewrite image links, and set author or comment options before publishing.

It handles WeChat-specific preparation that ordinary HTML does not provide, such as uploading body images and adapting CSS variables and lists.

zhy-wechat-publish — Skill for Claude Code by zhylq/yuan-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add zhylq/yuan-skills --skill zhy-wechat-publish

Clone the repo

git clone --depth 1 https://github.com/zhylq/yuan-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zhylq/yuan-skills/zhy-wechat-publish/github.svg)](https://agentmods.dev/skills/zhylq/yuan-skills/zhy-wechat-publish)

Your own site

<a href="https://agentmods.dev/skills/zhylq/yuan-skills/zhy-wechat-publish"><img src="https://agentmods.dev/badge/skills/zhylq/yuan-skills/zhy-wechat-publish/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zhylq/yuan-skills/zhy-wechat-publish"><img src="https://agentmods.dev/badge/skills/zhylq/yuan-skills/zhy-wechat-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,416 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00047	$0.01416
Opus 5.5	$0.00019	$0.00566
Sonnet 5.5	$0.00009	$0.00283
Haiku 4.5	$0.00005	$0.00142

Measured 2mo ago against content hash a4a3de2bc4b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zhy-wechat-publish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/publish_with_cover.js, scripts/upload_image.js, scripts/wechat_draft.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/zhy-wechat-publish/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

微信公众号草稿箱发布技能

本技能用于将文章发布到微信公众号草稿箱。脚本仅依赖 Node.js 内置模块；自动封面生成步骤会复用现有 bun 生图脚本。

前置条件

Node.js >= 16
若要自动生成封面，还需本机可用 bun
技能目录下 .env 至少包含：

WECHAT_APP_ID=你的公众号AppID
WECHAT_APP_SECRET=你的公众号AppSecret
WECHAT_DEFAULT_THUMB_MEDIA_ID=默认封面图media_id（可选）
WECHAT_DEFAULT_AUTHOR=AI源来如此（可选）

运行机器公网 IP 已加入公众号后台 IP 白名单
自动生成封面时，需保证 zhy-article-illustrator 的生图环境可用

安装说明

本 skill 适合与 npx skills add ... --skill zhy-wechat-publish 一起安装到 OpenCode、Claude Code 等支持 SKILL.md 的 agent 工具中。

安装后请在本地 skill 目录手动创建 .env，不要将真实凭据提交回仓库。

脚本清单

脚本位于 scripts/：

脚本	用途
`wechat_draft.js`	上传正文到公众号草稿箱
`upload_image.js`	上传本地封面图到永久素材库，获取 `media_id`
`publish_with_cover.js`	读取文章、生成封面、上传封面并推送草稿

核心能力

自动处理正文 CSS 变量兼容
自动将正文图片上传到微信正文图片接口并替换 URL
自动将 ul/ol 降级为微信公众号编辑态更稳定的段落列表
支持默认作者、评论开关、仅粉丝评论设置
支持从文章内容生成单张公众号封面，并自动上传为 thumb_media_id

工作流

方式一：已准备好 HTML 与封面 media_id

node scripts/wechat_draft.js --title "文章标题" --file "post.html" --author "AI源来如此" --thumb "MEDIA_ID" --need-open-comment "1" --only-fans-can-comment "1"

参数说明：

参数	必填	说明
`--title`	是	文章标题
`--file`	是	HTML 正文文件路径
`--author`	否	作者，不传时默认 `WECHAT_DEFAULT_AUTHOR` 或 `AI源来如此`
`--digest`	否	摘要
`--thumb`	否	封面 `media_id`，不传时读取 `.env` 默认值
`--source-url`	否	原文链接
`--need-open-comment`	否	是否开启评论，默认 `1`
`--only-fans-can-comment`	否	是否仅粉丝可评论，默认 `1`

方式二：自动生成封面并发布

当你已有文章源文件，以及最终用于上传的 HTML 文件时，可直接运行：

node scripts/publish_with_cover.js --article "article.md" --html "post.html" --author "AI源来如此" --source-url "https://example.com"

该脚本会自动完成：

读取文章内容并提取标题/摘要
调用 zhy-article-illustrator/scripts/image-gen.ts 生成单张 16:9 封面图
调用 upload_image.js --json 上传封面，获得 thumb_media_id
调用 wechat_draft.js 推送草稿，并自动带上：
- author
- thumb_media_id
- need_open_comment=1
- only_fans_can_comment=1

可选参数：

参数	说明
`--article`	原始文章文件，推荐 Markdown，也可 HTML
`--html`	最终上传到公众号的 HTML 文件
`--title`	显式覆盖标题
`--author`	显式覆盖作者
`--cover-output`	自定义封面输出路径
`--cover-ar`	封面宽高比，默认 `16:9`
`--source-url`	原文链接
`--need-open-comment`	是否开启评论，默认 `1`
`--only-fans-can-comment`	是否仅粉丝可评论，默认 `1`

Read the full file on GitHub · 135 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 135 lines · 47 tokens per session scan A a4a3de2bc4b9

Subscribe to this mod's changes

zhy-wechat-publish is a skill published in the GitHub repository zhylq/yuan-skills (35 stars, last pushed 7mo ago), licensed MIT. It adds 47 tokens to every session and 1,416 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEO agent ai article-generator skill wechat

zhy-wechat-publish next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zhy-wechat-publishzhylq/yuan-skills	Skill	35	7mo ago	MIT	A	47	Claude Code
tong-jincheng-perspective863401402/she-love-me	Skill	999	17d ago	MIT	A	160	Claude Code, Codex
langbot-devlangbot-app/LangBot	Skill	19k	yesterday	Apache-2.0	A	136	Claude Code, Codex
edgeone skill scannerTencent/AI-Infra-Guard	Skill	7.4k	2d ago	Apache-2.0	A	148	Claude Code, Codex
langbot-plugin-devlangbot-app/LangBot	Skill	19k	yesterday	Apache-2.0	A	115	Claude Code, Codex
langbot-space-opslangbot-app/LangBot	Skill	19k	yesterday	Apache-2.0	A	101	Claude Code, Codex
langbot-skills-maintenancelangbot-app/LangBot	Skill	19k	yesterday	Apache-2.0	A	49	Claude Code, Codex