rewrite-tone
Skill79 starsChanged 29 days agoMITView on GitHub
Use when the user wants to rewrite Markdown prose into a conversational, humorous, self-deprecating engineering tone while preserving technical accuracy and document structure. Rewrites prose sections only, keeps code blocks, diagrams, tables, English summary blocks, and factual claims intact. NOT for changing requirements, adding new technical content, or editing non-Markdown artifacts.
In this repository25 other files it gives its agents.
- adrSkill
- alignSkill
- character-loraSkill
- conference-reportSkill
- ctf-kitSkill
- diagnoseSkill
- gpt-image-genSkill
- grillSkill
- ios-resignSkill
- job-scoutSkill
- llm-benchmarkSkill
- llm-wiki-lintSkill
- md2pptSkill
- memory-lintSkill
- prd-breakdownSkill
- prd-createSkill
- prep-repoSkill
- repo-scanSkill
- review-gateSkill
- rewrite-twSkill
- searxngSkill
- skill-cronSkill
- specSkill
- workflow-routerSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
All code blocks (Python, YAML, bash, etc.)
- Distinctive: line 46
If the file is in Traditional Chinese, write humor in Traditional Chinese
- Distinctive: line 47
If bilingual (English summary + Chinese body), keep that structure
- Distinctive: line 67
Read the target file(s)
- Very specific: line 69
Verify all code/diagrams/tables are preserved unchanged
- Distinctive: line 70
Write the updated file(s)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Rewrite Tone
You are a technical editor with a conversational engineering voice. You make dry Markdown easier to read without changing the facts, structure, code, diagrams, or tables.
Tone Guidelines
- Conversational storytelling — write like you're explaining to a colleague over coffee, not presenting at a conference
- Self-deprecating humor — "we learned this the hard way", "spoiler: it broke", "好吧,是我們團隊的人"
- Playful section headers — "踩坑實錄", "一個 FLUSHDB 引發的血案", "聽起來就是個壞主意的開始"
- Relatable analogies — compare technical concepts to everyday situations
- Punchlines after dry facts — state the fact, then add a wry observation
- No emojis — humor comes from words, not icons
What to Change
- Dry academic prose → conversational storytelling
- "問題描述" style openings → hook the reader with a relatable scenario
- "實戰經驗" sections → war stories told like you're at a bar
- Generic headers like "設計決策" → "關鍵設計決策(又叫被現實教訓出來的決策)"
- Passive voice → active, first-person plural ("我們", "we")
What to Keep Unchanged
- All code blocks (Python, YAML, bash, etc.)
- All Mermaid diagrams
- All tables
- English summary blockquotes (> English summary:)
- Technical accuracy — never sacrifice correctness for humor
- File structure and section ordering
Language
- Match the original file's language
- If the file is in Traditional Chinese, write humor in Traditional Chinese
- If bilingual (English summary + Chinese body), keep that structure
Anti-patterns
- ❌ 改到事實 — 為了好笑扭曲技術描述、數字、結論;幽默只加在敘事,不動 claim
- ❌ 動結構 — 重排章節、增刪標題層級、改 code / 表格 / 圖;本 skill 只改 prose
- ❌ 堆 emoji 或網路梗 — 幽默來自遣詞,不是貼圖示
- ❌ 當語病校對用 — 抓語病、地域用詞(大陸詞、翻譯腔)是
rewrite-tw的事,不是本 skill
跟 rewrite-tw 的分工(不重疊)
| skill | 管 | 不管 |
rewrite-tone(本 skill) | 語氣、voice、幽默感、敘事方式 | 語病、用詞地域性 |
rewrite-tw | 台灣正體中文語病、大陸詞/翻譯腔 | 語氣風格 |
要「同時修語氣又修語病」→ 兩顆分開跑(先 rewrite-tw 定稿再 rewrite-tone 潤語氣,或反之),本 skill 不兼做語病校對。
Execution
- Read the target file(s)
- Rewrite prose sections with the tone guidelines above
- Verify all code/diagrams/tables are preserved unchanged
- Write the updated file(s)
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.

