xhs-weekly-retro
Skill1 starsChanged 14 days agoMITView on GitHub
Weekly Xiaohongshu retro for @bawbaw using CTR, saves, comments, and topic mix. Use when 复盘, 周报, 为什么没量, CTR 低, or planning next week.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/00-agents-standard.mdcCursor rule
- .cursor/rules/dy-publish.mdcCursor rule
- .cursor/rules/jev-claude.mdcCursor rule
- .cursor/rules/xhs-bundesliga.mdcCursor rule
- .cursor/rules/xhs-package-dod.mdcCursor rule
- .cursor/rules/xhs-publish-plain-text.mdcCursor rule
- .cursor/rules/xhs-series-v2.mdcCursor rule
- .cursor/rules/xhs-traffic.mdcCursor rule
- football-content-opsSkill
- atutun-xhs-coverSkill
- dbs-xhs-titleSkill
- douyin-cliSkill
- dy-content-complianceSkill
- dy-culture-rxSkill
- dy-flowus-dbSkill
- dy-note-adaptSkill
- ip-character-systemSkill
- jev-judgeSkill
- tt-note-adaptSkill
- xhs-account-positioningSkill
- xhs-content-complianceSkill
- xhs-flowus-dbSkill
- xhs-note-structureSkill
- xhs-pipelineSkill
- xhs-title-ab-testSkill
- xhs-title-skillSkill
- xhs-topic-bankSkill
- xhs-voice-polishSkill
- xiaohongshu-cliSkill
The file
Files
xhs-weekly-retro
门槛来自定位卡:CTR ≥12–15% 才进更大池;<10% 先换封面/标题,不先怪算法。
步骤
- 拉本周笔记(有登录就用 CLI,否则让用户贴后台 4 个数:曝光、CTR、收藏、评论):
xhs my-notes --json- 每条标:类型(足球 / 心理×足球)、CTR、互动、封面是否钩子、结尾是否提问。
- 对照定位配比:足球是否≈70%。纯心理且低曝光 → 下周改挂球场或停。
- 归因只用四个桶,不要同时怪 10 件事:
| 桶 | 信号 | 下周动作 |
| 封面 | CTR<10% | 换大字/换图,备选在 title-ab.md |
| 完读/互动 | 曝光高评论低 | 结尾改成 A/B 问题;发后自回 1 条 |
| 选题 | 两域互打 | 回到 70/30,纯心理降权 |
| 时效 | 快讯隔夜 | 热点改为 12–14 / 19–22 发出 |
- 写出
doc/周复盘/YYYY-Wxx.md:- 三句话结论
- 停做 / 加倍做(各 ≤3 条)
- 写回
doc/选题库.md本周优先 - 若定位要收敛,补丁写进
doc/账号定位.md
- 给用户的聊天里只放结论和「下周 3 条题」,表格留在文件。
不要
- 没有数字却写「爆了/扑了」
- 用万字公众号复盘腔
- 建议再装一堆外部 skill 当解决方案
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.

