# Lark To Wechat Mp

> Use when syncing a Feishu (Lark) document or Wiki page to a WeChat Official Account (微信公众号) draft box. Handles Feishu CDN image migration to WeChat CDN, Markdown-to-WeChat HTML conversion (inline styles, callout blocks), and cover thumbnail creation. Requires WeChat AppID/AppSecret pre-configured.

- **Type:** Skill
- **Install:** `agentstack add skill-cookieshaha-ash-claude-skills-lark-to-wechat-mp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [CookiesHaha](https://agentstack.voostack.com/s/cookieshaha)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [CookiesHaha](https://github.com/CookiesHaha)
- **Source:** https://github.com/CookiesHaha/ash-claude-skills/tree/main/plugins/lark-prd-workflow/skills/lark-to-wechat-mp

## Install

```sh
agentstack add skill-cookieshaha-ash-claude-skills-lark-to-wechat-mp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# lark-to-wechat-mp

Sync a Feishu doc/wiki → WeChat Official Account draft in one workflow. Images are migrated, formatting is preserved.

## Prerequisites

**CRITICAL — 执行前 MUST 先用 Read 工具读取 [`../lark-shared/SKILL.md`](../lark-shared/SKILL.md)**（lark-cli 认证、权限）

1. lark-cli configured with user identity
2. WeChat config at `~/.claude/wechat-mp.json` (see Setup)
3. Current machine IP in WeChat IP Whitelist

## Setup

### 1. WeChat Config File

```bash
cat > ~/.claude/wechat-mp.json /dev/null || \
  python3 -c "import json,os; c=json.load(open(os.path.expanduser('~/.claude/wechat-mp.json'))); print(c['app_id'])")
APP_SECRET=$(python3 -c "import json,os; c=json.load(open(os.path.expanduser('~/.claude/wechat-mp.json'))); print(c['app_secret'])")
TOKEN=$(curl -s "https://api.weixin.qq.com/cgi-bin/token?grant_type=client_credential&appid=${APP_ID}&secret=${APP_SECRET}" | python3 -c "import sys,json; print(json.load(sys.stdin)['access_token'])")
echo "Token OK: ${TOKEN:0:20}..."
```

### Step 2 — 拉取飞书文档（Markdown 格式）

```bash
DOC_URL="https://xxx.feishu.cn/wiki/..."
lark-cli docs +fetch --api-version v2 --doc "$DOC_URL" --doc-format markdown > /tmp/lark_doc.json
```

⚠️ **飞书图片 URL 有时效性，必须立即进行 Step 3，不可搁置。**

### Step 3 — 下载飞书图片 & 上传到微信 CDN

对文档中每个 `` 图片：

```bash
mkdir -p /tmp/wx_imgs
# 下载
curl -L -o /tmp/wx_imgs/imgN.png "FEISHU_IMAGE_URL" -s
# 上传到微信（返回 wechat_cdn_url）
curl -s -X POST "https://api.weixin.qq.com/cgi-bin/media/uploadimg?access_token=${TOKEN}" \
  -F "media=@/tmp/wx_imgs/imgN.png;type=image/png"
# → {"url":"http://mmbiz.qpic.cn/..."}
```

记录 `{feishu_url: wechat_cdn_url}` 映射表，后续替换用。

### Step 4 — 制作封面缩略图（首张图片）

```bash
# 缩放为 JPEG，控制在 64KB 以内（微信 thumb 上限）
sips -Z 700 /tmp/wx_imgs/img0.png -s format jpeg -s formatOptions 60 --out /tmp/wx_imgs/thumb.jpg
# 检查大小
wc -c /tmp/wx_imgs/thumb.jpg   # 应 ` | `font-family:'PingFang SC',...;line-height:1.8;color:#333;` |
| `` 一级标题 | `font-size:22px;border-bottom:2px solid #07C160;` |
| `` 二级标题 | `font-size:18px;border-left:4px solid #07C160;padding-left:10px;` |
| `` 正文 | `margin:12px 0;` |
| `` 图片 | `max-width:100%;display:block;margin:20px auto;` + **必须同时设置 `data-src` 和 `src`** |
| `` 链接 | `color:#07C160;` |
| `` 行内代码 | `background:#f0f0f0;padding:2px 6px;font-family:monospace;color:#e83e8c;` |

### Callout 块（飞书高亮块）→ 黄色信息框

```html

  🏖️ 标题
  ...

```

### 引用块 `>` → 灰色左边框

```html

  引用内容

```

---

## 草稿 API 结构

```python
payload = {
  "articles": [{
    "title": "标题",
    "author": "",
    "digest": "摘要（120字内）",
    "content": "...HTML...",
    "content_source_url": "飞书原文链接",
    "thumb_media_id": "封面图 media_id（必填）",
    "need_open_comment": 1,
    "only_fans_can_comment": 0
  }]
}
# POST https://api.weixin.qq.com/cgi-bin/draft/add?access_token=TOKEN
```

---

## 常见错误

| 错误 | 原因 | 解决 |
|------|------|------|
| `errcode:40164 invalid ip` | 当前 IP 未加白名单 | 微信公众平台 → IP白名单 → 添加 `curl ifconfig.me` 返回的 IP |
| `errcode:40001 invalid credential` | Token 过期（有效期 7200s）或凭证错误 | 重新获取 Token |
| Thumb upload: `errcode:40009` | 缩略图超过 64KB 或非 JPEG | 降低 `sips formatOptions`，确认文件格式 |
| 图片显示为空 | 微信 `` 需同时有 `src` 和 `data-src` | 两个属性都填 WeChat CDN URL |
| 飞书图片下载失败 | URL 已过期（搁置太久） | 重新 `docs +fetch` 获取新 URL |

---

## 手动创建草稿（精细控制）

当 draft.py 转换效果不满意时，手动在 Python 中构建 HTML 字符串并 POST：

```python
import json, urllib.request
TOKEN = "..."
payload = {"articles": [{"title": "...", "content": "...", "thumb_media_id": "..."}]}
data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
req = urllib.request.Request(
  f"https://api.weixin.qq.com/cgi-bin/draft/add?access_token={TOKEN}",
  data=data, headers={"Content-Type": "application/json; charset=utf-8"}
)
with urllib.request.urlopen(req) as r:
  print(json.loads(r.read()))
```

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [CookiesHaha](https://github.com/CookiesHaha)
- **Source:** [CookiesHaha/ash-claude-skills](https://github.com/CookiesHaha/ash-claude-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** yes
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-cookieshaha-ash-claude-skills-lark-to-wechat-mp
- Seller: https://agentstack.voostack.com/s/cookieshaha
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.