Skip to content

jianshuo/claude-skills / wjs-x-improving-content

wjs-x-improving-content

Verified

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 prompt", "X 内容改进", "哪版 prompt 最好", "什么内容 impression 高", "improve my tweets", "A/B test the X prompt", "/wjs-x-improving-content".

FileKindSize
SKILL.mdskill md6.2 KB
inbox/.gitignoreother12 B
scripts/_common.pyexecutablescript1.5 KB
scripts/analyze-content.pyexecutablescript4.1 KB
scripts/evaluate.pyexecutablescript3.1 KB
scripts/ingest-tweets.pyexecutablescript4.3 KB
scripts/ledger.pyexecutablescript2.9 KB
scripts/scoreboard.pyexecutablescript3.7 KB
state/.gitignoreother6 B
state/SCOREBOARD.mdmarkdown1.1 KB
state/tweets.jsonlother42.1 KB
state/versions.jsonlother523 B

state/SCOREBOARD.md

View on GitHub
# X 内容改进 — Scoreboard
_generated 2026-05-30_

## 📈 现状

- 成熟推 86 条(≥3天),中位 impression **841.0**,最高 333474
- ⚠ impression 主要由源文章/话题决定,prompt 是二阶因素——版本判决弱信号,内容特征才是杠杆

## 🏷️ Prompt 版本

| 版本 | n | 中位imp | 状态 | 假设 |
|---|---|---|---|---|
| f6b47a3 | 18 | 579.0 | active  | 收紧到≤60字(短=更高触达)+拿不准时优先金句体A |
| pre-prompt | 68 | 982.5 |  样本不足 |  |

> 目前 1 个正式版本——版本对比要等下一版 prompt。先看下面的内容特征。

## 🎯 内容特征(angle = prompt 主旋钮)

| angle | n | 中位imp | 互动率 |
|---|---|---|---|
| A 金句 | 3 | 4193 | 1.3% |
| B 反差 | 4 | 901.0 | 2.5% |
| C 小灾难 | 1 | 392 | 1.3% |

## ✅ To-do(下一步)

- [ ] 据内容特征分析,提一版 prompt 改动(带假设)→ 改 `prompts/x/prompt.md` + commit → `ledger.py register <新SHA>`
- [ ] v1 (f6b47a3) 测量中 — 攒够 5 条成熟推后 evaluate
- [ ] v2 (c060c9a) 测量中 — 攒够 5 条成熟推后 evaluate
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall