OpenSkillIndex← back to search
claude-codeopenclawautomation

Skills wechat-collect

Fetch a public WeChat article URL, archive the raw HTML, and convert the article into a stage-1 compatible brief in `content-production/inbox/`. Use when Codex needs to collect公众号文章素材 or start the Stage 2 collect-to-create pipeline from a public `mp.weixin.qq.com` URL.

install
source · Clone the upstream repo
git clone https://github.com/openclaw/skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/abigale-cyber/wechat-collect" ~/.claude/skills/openclaw-skills-wechat-collect && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/openclaw/skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/abigale-cyber/wechat-collect" ~/.openclaw/skills/openclaw-skills-wechat-collect && rm -rf "$T"
manifest: skills/abigale-cyber/wechat-collect/SKILL.md
tags
#wechat#web-scraping#content-extraction#html-parsing#data-ingestion#content-processing
source content

WeChat Collect

Collect a public WeChat article and transform it into a brief that can be passed directly to 

case-writer-hybrid
.

Quick Start

Run the default command:

.venv/bin/python -m skill_runtime.cli run-skill wechat-collect --input content-production/inbox/20260403-wechat-collect-url.txt

Prepare Input

Pass a text file containing at least one URL. The first detected URL is used.

Example input file:

content-production/inbox/20260403-wechat-collect-url.txt

Follow Collection Workflow

  1. Fetch the public article HTML from the first detected URL.
  2. Extract title, author, date, and candidate正文段落 from the page.
  3. Build a stage-1 compatible brief that downstream writing steps can reuse.
  4. Archive the raw HTML for traceability and later extraction tuning.

Write Output

Write the brief to:

content-production/inbox/<date>-<slug>-gzh-brief.md

Write the raw archive to:

content-production/inbox/raw/wechat/<date>-<slug>.html

Respect Constraints

  • Only works for publicly reachable article URLs
  • Deleted articles or anti-crawl variants may produce reduced-quality extraction or fail explicitly
  • Current extraction is usable for pipeline intake, but still needs quality tuning for cleaner argument mining

Read Related Files

  • Shared runtime: 
    skills/wechat-collect/runtime.py
  • Pipeline entry: 
    skill_runtime/engine.py
  • Stage 2 workflow: 
    workflows/stage2-wechat-pipeline.json
  • Planning reference: 
    docs/content-skills-implementation-plan.md