Agent skill · Data & Analytics

wjs-x-improving-content

Use when 王建硕 wants to systematically improve his X (Twitter) content by iterating on the content-generation prompt (prompts/x/prompt.md, used by the every-6h tweet Action) and finding which prompt version produces the highest-reach tweets. Each prompt edit is a git-SHA-versioned, numbered experiment with a hypothesis; tweets are attributed to the version live at post time and judged on median impressions per tweet. Also mines per-tweet impression data for content-feature signals (angle / length / topic) that feed the next prompt edit. North-star = impressions per tweet. Triggers — "改 X 的 promp

jianshuogithub.com/jianshuoGitHub ↗
claude-codecodexships scriptsMIT
Install
npx skills add jianshuo/claude-skills --skill wjs-x-improving-content --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 12
SKILL.md size: 4 KB
Bundled scripts: yes
Path: wjs-x-improving-content/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# wjs-x-improving-content 把「写好推」当工程做：**不断改 `prompts/x/prompt.md`，用 impression 数据看哪版最好**，并挖出「什么内容特征和高 impression 相关」反哺下一版。是 [[wjs-x-increasing-follower]] 的孪生——那个测 profile→关注转化率，这个测 **prompt→每条推的 impression**。 ## Core Principle **impression 主要由源文章 / 话题决定，prompt 只是二阶因素。** 一篇好文章配任何 prompt 都能爆。所以诚实地分两层看： | 看什么 | 信号强度 | 怎么用 | |---|---|---| | **prompt 版本对比**（哪版 prompt 的推中位 impression 高） | 弱（被文章支配，需大量样本） | 方向性参考，攒够样本才下判决 | | **内容特征**（angle A/B/C、长度、钩子——prompt 直接控制的东西） | 较强（同样话题下，特征差异才显出 prompt 的手艺） | **真正反哺 prompt 的依据** | **所以：版本对比给方向，内容特征给抓手。** 别把版本判决当因果。 **判决用中位数不用均值**（impression 极度长尾，一条爆款骗死均值）；**每版至少 5 条成熟推**才下版本级判决；**成熟窗 = 发布满 3 天**（impression 还在涨的太新推不计入）。 **回滚是一等公民**：prompt 在 git 里，回滚 = `git checkout <旧SHA> -- prompts/x/prompt.md`。 ## 版本 = prompt.md 的 git short-SHA 每条推归到哪版 prompt，**按时间推导**：推发布时间 T → `prompts/x/prompt.md` git 历史里时间 ≤ T 的最后一次提交 = 那条推用的版本。**不用改 Action**，历史推也能回填。早于 prompt 文件存在的推 → `prompt_sha=null`（pre-prompt）。 ## 数据从哪来 每条推的 impression **X API 不稳**，靠 **Content CSV 导出**：`x.com/i/account_analytics` → **Content** 标签 → 导出 CSV（含 Post id / Impressions / Engagements …）→ 丢进 `inbox/`。`Post id` 就是 `tweet_id`，和发推历史对得上。 ## When This Skill Fires - 「改 X 的 prompt」「哪版 prompt 最好」「什么内容 imp

What's inside
Steps it walks through
  1. Core Principle
  2. 版本 = prompt.md 的 git short-SHA
  3. 数据从哪来
  4. When This Skill Fires
  5. When NOT to use
  6. Workflow
  7. Step 1 — 吃数据
  8. Step 2 — 挖内容特征（核心，立刻有用）
  9. Step 3 — 提一版 prompt 改动（带假设）
  10. Step 4 — 攒够样本后判决
  11. Step 5 — 看板
  12. 数据模型（state/）
  13. 默认参数（要改传 flag / 改 common.py）
  14. 路径假设（common.py 顶部，换机器改这里）
Ships with 11 files
  • inbox/.gitignore
  • scripts/_common.py
  • scripts/analyze-content.py
  • scripts/evaluate.py
  • scripts/ingest-tweets.py
  • scripts/ledger.py
  • scripts/scoreboard.py
  • state/.gitignore
  • state/SCOREBOARD.md
  • state/tweets.jsonl
  • state/versions.jsonl
Commands it runs
python3 scripts/ingest-tweets.py /path/to/content.csv
python3 scripts/analyze-content.py          # 成熟推
python3 scripts/analyze-content.py --all     # 含未成熟（angle 样本更全）
cd ~/code/wechat-publish
git add prompts/x/prompt.md && git commit -m "x prompt: <一句话改了啥>"
python3 ~/.claude/skills/wjs-x-improving-content/scripts/ledger.py register "$NEW_SHA" \
python3 scripts/evaluate.py     # 各版本中位 impression + 相邻版本 Δ% 判决
git -C ~/code/wechat-publish checkout <旧SHA> -- prompts/x/prompt.md
git -C ~/code/wechat-publish commit -m "x prompt: rollback to <旧SHA>"
python3 scripts/scoreboard.py    # 写并打印 state/SCOREBOARD.md
More from claude-skills
All skills →
wjs-mining-voicedropUse when 王建硕 wants to turn his uploaded VoiceDrop voice memos into 微信公众号 article drafts — pulling…Otherwangjianshuo-perspective王建硕的思维框架与表达方式。基于 7 份深度调研（约 100 万词英文博客 + 约 109 万字中文博客， 2002–2022，全部一手）提炼出 7 个核心心智模型、10…Otherwjs-publishing-hugo当用户想给自己的 Hugo 静态博客（如 maggiacito.com）新增或编辑帖子、管理类目、上传图片并发布上线时使用——对话式后台，说一句就改文件、commit、推送、自动部署，不需要任何…Otherwjs-burning-subtitlesUse when the user has a video + an SRT and wants the subtitles either burned into the pixels…Media & Videowjs-cleaning-spamUse when the user complains about spam on his X/Twitter posts — 同城面付 / 寻固炮 / 线下上门 / 免费破处…Otherwjs-converting-text-to-videoUse when the user wants a 王建硕-style WeChat article (article.md) turned into a narrated short MP4…Frontend
About this skill
What does the wjs-x-improving-content skill do?

Use when 王建硕 wants to systematically improve his X (Twitter) content by iterating on the content-generation prompt (prompts/x/prompt.md, used by the every-6h tweet Action) and finding which prompt version produces the highest-reach tweets. Each prompt edit is a git-SHA-versioned, numbered experiment with a hypothesis; tweets are attributed to the version live at post time and judged on median impressions per tweet. Also mines per-tweet impression data for content-feature signals (angle / length / topic) that feed the next prompt edit. North-star = impressions per tweet. Triggers — "改 X 的 promp

How do I install it?

Run `npx skills add jianshuo/claude-skills --skill wjs-x-improving-content --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From jianshuo/claude-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.