About wewrite-stats
wewrite-stats is a marketing skill for reviewing the performance of WeChat Official Account articles. It records available metrics, identifies stronger and weaker results, and suggests adjustments to future topics and formats.
Key features
- 01Fetch article metrics for the past seven days
- 02Add metrics to history records
- 03Analyze the strongest and weakest results
- 04Suggest topic, title, and format changes
Use cases
- 01Review the performance of published articles
- 02Adjust future topics and titles based on metrics
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ imraywang/ wewrite --skill wewrite-statsAfter installing, type/wewrite-statsin Claude Code to confirm it loaded.
Bundled filesreferences/effect-review.md
Details
From the project READMEwewrite-stats — 文章数据复盘
运行约定
- CLI:确定性操作走
wewrite命令(需在 PATH;缺失则引导uv tool install wewrite,或在仓库里bash install.sh)。 - {home}:用户状态目录 =
$WEWRITE_HOME或~/.wewrite(wewrite home可查)。config/style/history/playbook/output/exemplars 全在 {home},不在仓库;references 文档中的状态路径同此约定。 读取: <路径>= 用文件读取工具真实读完该文件再继续,不是注释。- references/:本 skill 自带
{skill_dir}/references/;references 文档内的{skill_dir}即本 skill 目录。
执行
读取: {skill_dir}/references/effect-review.md
按其流程执行:fetch_stats.py --days 7 拉数据 → 匹配并回填 history.yaml 的
stats 字段 → 分析最好/最差表现及原因 → 给出后续选题/标题/框架的调整建议。
前置:需要 config.yaml 里的微信 API 凭证。缺凭证 → 告知用户"数据复盘需要配置 公众号 API(config.yaml),当前只能基于 history.yaml 已有记录做定性分析",然后就 history.yaml 现有内容能分析多少分析多少。刚发布的文章 → 告知等 24h 后再看。
下游影响:回填的 stats 会被选题模块(wewrite-topic)读取——哪种框架/增强策略 表现好会加权到下次推荐。这是数据闭环的一半,另一半是 wewrite-learn 的改稿飞轮。
Comments
Markdown supported