🧬 Taiwan.md — Rewrite(極簡薄殼)
SkillDev toolsWrite or rewrite a Taiwan.md article via canonical REWRITE-PIPELINE. TRIGGER when: user says "寫 X", "重寫 X", "EVOLVE X", "走 rewrite", "rewrite-pipeline", or asks to write/improve any knowledge/ article.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the 🧬 Taiwan.md — Rewrite(極簡薄殼) skill
What this skill tells your AI
The instructions your AI receives, as published by frank890417/taiwan-md in .claude/skills/twmd-rewrite/SKILL.md and read by ahel’s review.
故意極簡。所有 SOP(Stage 0-5 / hard gates / 搜尋配額 / SSOT 八段 / 自檢工具 / 鐵律 / cron 規則)100% 在 pipeline canonical。本 skill 只做三件事,不在這裡複寫或補充任何 pipeline 內容(複寫 = drift = 退化)。
1. STRICT BECOME GATE(不可省)
跑 /twmd-become write 完整 BECOME_TAIWANMD.md Step 0-9,Write mode self-test 全過才動工。
2. 完整讀 REWRITE-PIPELINE 索引+執行到哪讀哪個 contract(不可 head / tail / 取樣)
用 Read tool 一次讀完 docs/pipelines/REWRITE-PIPELINE.md(v9.0 薄索引,無 limit / offset)。執行每個 stage 前,完整讀該 stage 的 contract 檔(docs/pipelines/REWRITE-STAGE-*.md,派發表在索引 §Stage contract 派發表)。contract 叫你讀的(RESEARCH.md / EDITORIAL.md / RESEARCH-TEMPLATE.md / 對應 FACTCHECK 等)也完整讀。
3. 嚴格照 pipeline 執行
pipeline 怎麼寫就怎麼做:Stage 0-5 不跳步、每個 hard gate 都跑(research-report-health.py / article-health.py …)、不加碼、不憑記憶。
Signals
- GitHub stars
- 1k
- Forks
- 185
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
twmd-rewrite- Source
- github.com/frank890417/taiwan-md