wechat-archiver
Skill9 starsChanged 3 days agoMITView on GitHub
Archive WeChat Official Account articles into structured knowledge assets with local Markdown, downloaded images, structured notes, and metadata. Use when archiving, indexing, or saving WeChat articles to an Obsidian vault or knowledge base.
- Installs packages
In this repository17 other files it gives its agents.
- brief-outputSkill
- google-go-styleSkill
- insight-collectorSkill
- insights-reportSkill
- json-canvasSkill
- md2wechatSkill
- note-creatorSkill
- obsidian-basesSkill
- obsidian-markdownSkill
- peleSkill
- portpilot-assistantSkill
- publication-ready-docs-jevSkill
- publication-ready-docsSkill
- readme-maintainerSkill
- sync-to-githubSkill
- tech-articleSkill
- wechat2mdSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 5 are distinctive, and 9 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Determine destination: Verify the target knowledge base directory.
- Distinctive: line 21
Fetch article: Run the bundled fetcher tool:
- Very specific: line 25
If the fetcher returns STATUS=skipped, the URL and article hash match an existing asset.
- Very specific: line 26
Inspect extracted content: Read generated article.md, images/, and meta.json.
- Very specific: line 27
Create structured note (
note.md): Write a clean analytical note directly in the asset directory: - Very specific: line 33
Update metadata: Ensure meta.json accurately reflects the generated asset paths.
- Very specific: line 34
Optional visual artifacts: Create diagram.canvas or table.base only when the user explicitly requests it or when complex spatial/comparison …
- Very specific: line 35
Verify output: Verify that article.md, images, note.md, and meta.json exist and pass verification.
- Distinctive: line 51
When processing multiple URLs:
- Distinctive: line 53
If an article fetch fails, record the error, preserve completed assets, and continue with remaining URLs.
- Distinctive: line 55
Do not modify the source inbox list unless directed by the user.
- Very specific: line 59
Faithful preservation: Never alter the original article's technical claims or author opinions in article.md.
- Very specific: line 60
Minimal optional artifacts: Never create optional diagram.canvas or table.base files without clear informational value.
- Distinctive: line 65
Before completing the task, verify:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
WeChat Archiver Skill
Archive WeChat Official Account articles into self-contained knowledge asset packages with clean Markdown, local images, a structured analytical note, and verified metadata.
Setup
Python 3.8+ and curl in PATH are required. Install dependencies in the Skill directory:
pip install -r "<skill-dir>/requirements.txt"Workflow
- Determine destination: Verify the target knowledge base directory. Default to
outputs/<folder>/<slug>/. - Fetch article: Run the bundled fetcher tool:
If the fetcher returnspython "<skill-dir>/tools/fetch_article.py" "<article-url>" --output-dir "<target-root>/outputs" --target-folder "<folder>"STATUS=skipped, the URL and article hash match an existing asset. Verify the existing asset and do not recreate it. Add--refreshonly when the user explicitly requests an update. - Inspect extracted content: Read generated
article.md,images/, andmeta.json. - Create structured note (
note.md): Write a clean analytical note directly in the asset directory:- 核心摘要:1-2 句直接说明文章解决的问题与核心结论。
- 关键技术机制与论据:系统原理解析、核心技术决策、支持论据。
- 可复用资产:可直接提取的代码、配置、命令或规则。
- 局限与边界:原文适用的范围、未解决的问题或作者主观偏见。
- 绝不编造泛泛而谈的寒暄、大而无当的空话或虚假深刻的升华。
- Update metadata: Ensure
meta.jsonaccurately reflects the generated asset paths. - Optional visual artifacts: Create
diagram.canvasortable.baseonly when the user explicitly requests it or when complex spatial/comparison relationships provide clear visual value. - Verify output: Verify that
article.md, images,note.md, andmeta.jsonexist and pass verification.
Output Package Structure
<target-root>/outputs/<folder>/<slug>/
├── article.md # Faithful Markdown of original article
├── images/ # Downloaded local images (if present)
├── note.md # Structured analytical note
├── meta.json # Machine-readable asset metadata (title, author, url, asset_id)
├── diagram.canvas # Optional (only when explicitly requested)
└── table.base # Optional (only when explicitly requested)Batch Processing
When processing multiple URLs:
- Process articles sequentially using the standard single-article workflow.
- If an article fetch fails, record the error, preserve completed assets, and continue with remaining URLs.
- Report a final summary listing successful paths and failed URLs.
- Do not modify the source inbox list unless directed by the user.
Guidelines & Boundaries
- Faithful preservation: Never alter the original article's technical claims or author opinions in
article.md. - Minimal optional artifacts: Never create optional
diagram.canvasortable.basefiles without clear informational value. - Completion definition: An archive is complete only when
article.md, downloaded images,note.md, andmeta.jsonexist and pass verification.
Verification Checklist
Before completing the task, verify:
article.mdexists and image references link to local files inimages/.- Local images exist on disk with non-zero file sizes.
note.mdcontains verified analytical sections and source attribution without AI fluff.meta.jsoncontains accurate artifact paths and metadata.- Output reports the exact asset directory path to the user.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

