lark-to-wechat-mp

lark-to-wechat-mp is a skill for Claude Code from CookiesHaha/ash-claude-skills. It costs 75 tokens per session (2,010 once invoked), scanned A, original, MIT.

A workflow for turning a Feishu document or Wiki page into a draft in a WeChat Official Account, a publishing account for messages and articles.

In plain words
What is it for?
Use it to transfer Feishu content, migrate hosted images, convert Markdown into WeChat-formatted HTML, and create a cover thumbnail.
Why use it?
It moves images and formatting between the two services so the draft does not need to be rebuilt manually.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the ash-workflow plugin — 7 skills, 1 command shipped together

Good fit Use it to transfer Feishu content, migrate hosted images, convert Markdown into WeChat-formatted HTML, and create a cover thumbnail.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp
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 CookiesHaha/ash-claude-skills --skill lark-to-wechat-mp
Clone the repo
git clone --depth 1 https://github.com/CookiesHaha/ash-claude-skills

Made for: Claude Code.

Or install ash-workflow, the plugin that ships this one along with the rest of its 7 skills, 1 command.

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.

agentmods badge for lark-to-wechat-mp

README.md
[![agentmods](https://agentmods.dev/badge/skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp/github.svg)](https://agentmods.dev/skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp)
Your own site
<a href="https://agentmods.dev/skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp"><img src="https://agentmods.dev/badge/skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp/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.

agentmods 80×15 button for lark-to-wechat-mp

Your own site · 80×15
<a href="https://agentmods.dev/skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp"><img src="https://agentmods.dev/badge/skills/cookieshaha/ash-claude-skills/lark-to-wechat-mp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,010 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. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.02010
Opus 5 $0.00037 $0.01005
Sonnet 5 $0.00015 $0.00402
Haiku 4.5 $0.00007 $0.00201

Measured 12d ago against content hash dc255c7ca97e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lark-to-wechat-mp 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (draft.py), 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.

plugins/ash-workflow/skills/lark-to-wechat-mp/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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-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

cat > ~/.claude/wechat-mp.json << 'EOF'
{
  "app_id": "wx...",
  "app_secret": "YOUR_APP_SECRET"
}
EOF
chmod 600 ~/.claude/wechat-mp.json

2. IP Whitelist(首次必做,只做一次)

  1. 打开 微信公众平台 → 设置与开发 → 基本配置
  2. IP白名单 → 添加当前机器 IP
  3. 获取当前 IP:curl -s ifconfig.me

Workflow(每次同步执行以下步骤)

Step 1 — 读取配置,获取 Access Token

APP_ID=$(python3 -c "import json; c=json.load(open(os.path.expanduser('~/.claude/wechat-mp.json'))); print(c['app_id'])" 2>/dev/null || \
  python3 -c "import json,os; c=json.load(open(os.path.expanduser('~/.claude/wechat-mp.json'))); print(c['app_id'])")
APP_SECRET=$(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)

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 ![](feishu-url) 图片:

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/..."}

Read the full file on GitHub · 189 lines

Files

What ships with it

1 file 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.

  1. 12d ago First seen · 189 lines · 75 tokens per session scan E dc255c7ca97e

Subscribe to this mod's changes

lark-to-wechat-mp is a skill published in the GitHub repository CookiesHaha/ash-claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 2,010 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

pdf-text-replace

Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.

instavm/coderunner · 42 tokens

suede-product-marketing

Suede-owned product-marketing context discipline. Use when a project needs a shared record of product, audience, ICP, positioning, objections, customer language, proof, and goals, or when that record needs updating. NOT FOR: writing a campaign (use suede-campaign-in-a-box), conducting new customer interviews (use…

JasonColapietro/suede-creator-skills · 81 tokens

design-export-repair

Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and corrupted .pptx package structure that shows up only once you export to PDF, not while looking at it in the app. Use this skill whenever the user uploads a zip, .pptx…

OneWave-AI/claude-skills · 219 tokens

google-apps-script

Build Google Apps Script automation for Sheets and Workspace. Custom menus, triggers (onEdit / time-driven / form submit), dialogs, sidebars, email batches, PDF export, external API. Use whenever the user wants to automate a Google Sheet, build a Sheets menu / sidebar / dialog, hit a Sheets row from email or a…

jezweb/claude-skills · 89 tokens

financial-document-parser

Extract and analyze data from invoices, receipts, bank statements, and financial documents. Categorize expenses, track recurring charges, and generate expense reports. Use when user provides financial PDFs or images.

OneWave-AI/claude-skills · 42 tokens

csv-excel-merger

Merge multiple CSV/Excel files with intelligent column matching, data deduplication, and conflict resolution. Handles different schemas, formats, and combines data sources. Use when users need to merge spreadsheets, combine data exports, or consolidate multiple files into one.

OneWave-AI/claude-skills · 56 tokens