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.
npx skills add chubbyguan/chubbyskills --skill wechat-article-ingestgit clone --depth 1 https://github.com/chubbyguan/chubbyskillsWrote 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.
[](https://agentmods.dev/skills/chubbyguan/chubbyskills/wechat-article-ingest)<a href="https://agentmods.dev/skills/chubbyguan/chubbyskills/wechat-article-ingest"><img src="https://agentmods.dev/badge/skills/chubbyguan/chubbyskills/wechat-article-ingest/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.
<a href="https://agentmods.dev/skills/chubbyguan/chubbyskills/wechat-article-ingest"><img src="https://agentmods.dev/badge/skills/chubbyguan/chubbyskills/wechat-article-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.01043 |
| Opus 5 | $0.00019 | $0.00522 |
| Sonnet 5 | $0.00008 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
wechat-article-ingest 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 10d ago.
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.
What it actually says
微信公众号文章处理 Skill
将微信公众号文章转换为 Markdown，生成 A 层观点提取 + B 层问题链，存入知识库。
两种模式
模式 1：直接链接抓取（推荐）
python scripts/fetch_article.py "https://mp.weixin.qq.com/s/xxxxx"
公众号文章 URL 是公开的，不需要登录，直接抓取即可。
模式 2：PDF 提取
python scripts/extract.py "path/to/article.pdf"
适用于通过「笔记同步助手」等工具导出的 PDF。
环境要求
# Python 3.10+
pip install beautifulsoup4 markitdown pymupdf
# 或者用 uv
uv pip install beautifulsoup4 markitdown pymupdf
使用方法
单篇处理（链接）
python scripts/fetch_article.py "https://mp.weixin.qq.com/s/xxxxx" --output ./output
链接模式会尽量保留：
- 标题层级：
h1/h2/h3会转成 Markdown 标题 - 图片：
data-src/src会转成 Markdown 图片引用 - 链接：正文里的
<a>会转成 Markdown 链接
单篇处理（PDF）
python scripts/extract.py "path/to/article.pdf" --output ./output
A+B 处理（需要 Agent）
帮我处理这篇文章：https://mp.weixin.qq.com/s/xxxxx
提取观点 + 问题链
核心流程
公众号链接/PDF → 提取内容 → A层观点提取 + B层问题链 → 存入知识库
A层：观点提取
生成 观点提取-{作者}-{主题}.md：
- 🔴 支柱观点（P1-P6）：文章最核心的论点
- 🟡 支撑观点（S1-S8）：支撑支柱的论据
- 🟢 延伸观点（E1-E4）：可以延伸思考的方向
- Takeaway：每条含核心观点 + 行动指向
B层：问题链
生成 问题链-{作者}-{主题}.md：
- 3-5 条问题链，每条对应一个核心主题
- 每条链分 L1（安全区）→ L2（边缘区）→ L3（核心区）
- 每条链 6 道问题
- 终局种子：一个带回家的问题
知识库目录结构
知识库/
├── 素材库/
│ └── 公众号文章/
│ └── {公众号名}/
│ └── article.md
└── wiki/
└── 外部输入/
└── 公众号/
└── {公众号名}/
└── {主题}/
├── 观点提取.md
└── 问题链.md
已知限制
- 部分公众号文章有防盗链，可能抓取失败
- 纯图片文章无法提取文字
- MarkItDown 需要 Python ≥ 3.10
- PDF 提取质量取决于原文排版；链接模式比 PDF 模式更能保留图片和链接
- 长文档拆分需要 Agent 判断
参考项目
- microsoft/markitdown - PDF/文档转 Markdown
- pymupdf/PyMuPDF - PDF 处理库
- beautifulsoup4 - HTML 解析
⚖️ 合规声明
仅供个人学习与研究使用。请遵守目标平台的服务条款（ToS）与 robots 规则，控制请求频率，不要用于批量抓取、商用爬取或侵犯他人权益的场景。下载内容的版权归原作者所有。
What ships with it
3 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.
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.
- 10d ago First seen · 135 lines · 39 tokens per session scan A b47ae0dd2c5d
wechat-article-ingest is a skill published in the GitHub repository chubbyguan/chubbyskills (665 stars, last pushed 21d ago), licensed MIT. It adds 39 tokens to every session and 1,043 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
note-organizer
Use this skill whenever the user wants to organize course materials, lecture notes, PPT/PDF/DOCX files, textbooks, personal notes, senior-student notes, historical exams, review questions, standards, manuals, or scattered study resources into a structured Markdown note library. Use it even when the user only says…
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
deck-ai
Generate modern presentation decks (PDF) from markdown content. Local open-source alternative to Gamma — uses Slidev for layouts and Unsplash for imagery. Invoke when the user asks to "make a deck", "build slides from this", or "turn this into a presentation".
reduce
Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract…
verify
Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify", "/verify [note]", "verify note quality", "check note health".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis with two-column tables. Left column preserves the chapter content; right column maps every idea to the reader's actual life using brain context. Output is a single brain page at media/books/ -personalized plus an optional PDF via brain-pdf.