yichen-wechat-mp-batch-exporter
批量下载微信公众号文章正文、历史文章列表、原创文章筛选、历史计数口径、阅读量、点赞/转发等指标、评论和评论回复。Use when the user asks to batch fetch mp.weixin.qq.com articles, export WeChat public-account history, distinguish publish groups vs expanded article URLs vs original articles, use wechat-article-exporter, use wxdown-service credentials, collec…
Install / Use
npx skills add mcncarl/yichen-skills --skill yichen-wechat-mp-batch-exporterInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of yichen-wechat-mp-batch-exporter
yichen-wechat-mp-batch-exporter scores 94/100 on our quality scale, 503rd of 4,698 Development & Engineering skills we index (top 11%).
Its SKILL.md is 6.0 KB long, well organised into 10 sections with 9 code examples: a thorough specification that gives an agent plenty to work with.
With 4,169 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so yichen-wechat-mp-batch-exporter is actively maintained.
- Our last check on 2026-11-16 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-29. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
yichen-wechat-mp-batch-exporter compared with similar skills
All 4 of these similar skills score higher than yichen-wechat-mp-batch-exporter; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| yichen-wechat-mp-batch-exporter (this skill)by mcncarl | 94 | 4.2k | 55d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install yichen-wechat-mp-batch-exporter?
- Run
npx skills add mcncarl/yichen-skills --skill yichen-wechat-mp-batch-exporter. The install tabs above show the steps for each supported agent. - Which AI agents does yichen-wechat-mp-batch-exporter work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is yichen-wechat-mp-batch-exporter safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is yichen-wechat-mp-batch-exporter still maintained?
- The repository was last updated about 2 months ago, so yichen-wechat-mp-batch-exporter is actively maintained.
Skill content
View source on GitHubname: yichen-wechat-mp-batch-exporter description: 批量下载微信公众号文章正文、历史文章列表、原创文章筛选、历史计数口径、阅读量、点赞/转发等指标、评论和评论回复。Use when the user asks to batch fetch mp.weixin.qq.com articles, export WeChat public-account history, distinguish publish groups vs expanded article URLs vs original articles, use wechat-article-exporter, use wxdown-service credentials, collect read/comment metrics, or create an archive for Obsidian/Feishu/local analysis. Do not use for ordinary one-off article summarization unless batch/enhanced data is requested.
WeChat MP Batch Exporter
Core Rule
Never operate the user's WeChat UI. Do not publish, delete, mass-send, follow, unfollow, send messages, or click inside WeChat. For any workflow requiring WeChat desktop, tell the user exactly what to do and wait for confirmation.
Never print raw cookies, auth-key, token, pass_ticket, key, uin, credentials JSON, or QR login secrets in chat or saved reports.
Downloaded article content belongs to the original authors or rights holders. Use exports only within the user's lawful/private-use scope unless the user confirms they have permission to republish or redistribute.
First Step
Run the local doctor before choosing a workflow:
python3 {baseDir}/scripts/doctor.py
Use --check-network only when the task needs the public exporter API or online download endpoint.
Decision Tree
- User provides known article URLs and only needs正文/Markdown: use
scripts/download_urls.py; no login or WeChat action is required. - User wants a public account's历史文章列表 or latest N articles: use exporter mode from
wechat-article-exporter; this requires a user-owned WeChat Official Account backend login/auth-key. - User needs阅读量、点赞、转发、评论、评论回复: use
wxdown-servicecredentials flow first, then export enhanced fields fromwechat-article-exporter. - User says“不登录”“代理模式” or exporter mode fails: use the proxy/history fallback only after explicit confirmation; read
references/manual-gates.mdfirst.
For simple single-URL extraction without batch/enhanced needs, prefer the existing $wechat-article skill.
Count Discipline
Never report a public account total as just “N 篇文章” until the count scope is clear.
After any history sync or imported history JSON, run:
python3 {baseDir}/scripts/analyze_history.py --history-json /path/to/history.dedup.json
python3 {baseDir}/scripts/analyze_history.py --chunk-dir /path/to/chunks --output-dir /path/to/output
Use these labels in user-facing answers:
publish_groups: uniquemsgidvalues; roughly one WeChat publish/message group.expanded_url_items: every unique article URL after expanding multi-article messages.original_articles: frontend-style original article count, usingcopyright_type=1,copyright_stat=1, andis_deleted=false.
If counts disagree with what the user sees in WeChat, explain the scope difference first and point to the generated history.summary.json / history.summary.md.
Known-URL Body Download
Use this path for pasted URLs, .txt, .csv, or .json URL lists:
python3 {baseDir}/scripts/download_urls.py --file /path/to/urls.txt --format markdown
python3 {baseDir}/scripts/download_urls.py "https://mp.weixin.qq.com/s/..."
Report only: success count, failure count, failed URLs, output directory, and index.csv.
Default output:
~/Downloads/wechat-mp-batch/<run-id>/
|-- index.csv
|-- errors.json
`-- articles/
`-- 001-<safe-title>.md
History And Enhanced Export
Read references/exporter-workflow.md before running exporter/history/enhanced-data tasks.
Start the local credential helper with:
python3 {baseDir}/scripts/start_wxdown_service.py
Use the mature upstream stack:
wechat-article/wechat-article-exporterfor account search, article history, body download, and multi-format export.wechat-article/wxdown-servicefor user-owned credential capture needed by read/comment metrics.
Local source paths are environment-specific. Prefer environment variables or explicit script flags:
export WECHAT_ARTICLE_EXPORTER_DIR=/path/to/wechat-article-exporter
export WXDOWN_SERVICE_DIR=/path/to/wxdown-service
python3 {baseDir}/scripts/doctor.py --exporter-path "$WECHAT_ARTICLE_EXPORTER_DIR" --wxdown-path "$WXDOWN_SERVICE_DIR"
python3 {baseDir}/scripts/start_wxdown_service.py --wxdown-dir "$WXDOWN_SERVICE_DIR"
If using the public exporter, default base URL is:
https://down.mptext.top
Manual Gates
Read references/manual-gates.md whenever the task involves login, credentials, comments, read counts, proxy, certificate trust, or WeChat desktop.
These actions always require explicit user confirmation:
- Scanning a QR code and selecting the user's Official Account or service account.
- Installing or trusting a mitmproxy certificate.
- Enabling or changing macOS system proxy settings.
- Asking the user to open an article/history page inside WeChat desktop and scroll.
- Using a pasted auth-key or credentials file.
Outputs
Read references/output-schema.md when building an archive or merging exporter results into another system.
Preferred enhanced archive fields:
account_name, fakeid, title, url, publish_time, author, digest, cover_url,
body_markdown_path, html_path, image_dir,
read_count, like_count, share_count, favorite_count, comment_count,
comments_path, comment_replies_path, fetch_mode, credential_status, exported_at
History analysis outputs should include:
history.summary.json, history.summary.md,
history.dedup.json, history.dedup.csv, urls.all.txt,
history.original.json, history.original.csv, urls.original.txt
What Cannot Be Done Automatically
- Do not bypass login, deleted content, paywalls, private articles, or platform permission checks.
- Do not guarantee read/comment metrics without fresh user-owned credentials.
- Do not operate WeChat UI or replace the user's required WeChat desktop actions.
- Do not promise comments when the article has comments disabled or hidden.
- Do not silently install system certificates, change proxies, or leave proxy settings enabled.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
