Commit graph

2 commits

Author SHA1 Message Date
wangzhuc
87c4a7d293 feat: effect feedback loop, evergreen topics, merged search, content quality checks
- Topic selection: add historical effect analysis (framework/strategy/title
  performance weighting when stats available), add 2-3 evergreen topics
  alongside trending ones
- Step 3: merge material collection and content enhancement into single
  search pass, with framework-specific search strategies
- Step 5: split verification into writing quality (A) and content quality (B),
  add checks for hook strength, quote density, angle sharpness per framework
- Fix exemplar category mapping for new frameworks (opinion → hot-take,
  retrospective → story-emotional)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 16:20:17 +08:00
wangzhuc
1ab34fa450 Initial release — 公众号文章全流程 AI Skill
热点抓取 → 选题 → 框架 → 写作 → SEO → 视觉AI → 排版 → 微信草稿箱,
一句话触发完整流程。适用于 Claude Code skill 格式。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 22:16:18 +08:00