Agent skill · Content & Marketing

write

Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask in any language to draft, rewrite, proofread, localize, polish release notes, remove AI-like wording, or prepare launch and social copy. Not for code comments, commit messages, or inline docs.

Tw935,692★ · +38/wk · 1 repos on radarProfile →
claude-codeships scriptsMIT
Install
npx skills add tw93/Waza --skill write --agent claude-code

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

Facts
Files in the skill folder: 13
SKILL.md size: 16 KB
Bundled scripts: yes
Path: skills/write/SKILL.md
Open the folder on GitHub →
Where it comes from
Source: tw93/Waza
Stars: 6,760
Language: Python
Read our review of the source →

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

From the SKILL.md

# Write: Cut the AI Taste Prefix your first line with 🥷 inline, not as its own paragraph. Strip AI patterns from prose and rewrite it to sound human. Do not improve vocabulary; remove the performance of improvement. ## Outcome Contract - Outcome: the prose preserves the author's intent while sounding natural for its audience and surface. - Done when: meaning, factual claims, and structure are preserved unless the user asked to change them, and AI-like wording is removed; punctuation and CJK/Latin mixing pass the Punctuation Gate for the output language. - Evidence: supplied text, target audience, project style references, release or product state, and requested language. - Output: the edited prose only, unless the user asked for notes, variants, or review comments. ## Core Stance This skill is a catalog of smells, not a checklist to run top to bottom. Use it to recognize AI taste, then make judgment calls. The reference files (especially `write-zh.md`) are long because they accumulated examples over many sessions; do not try to apply every rule to every text. Applying more rules is not doing a better job. - **Over-editing is failure, equal to under-editing.** If a sentence is alre

What's inside
Steps it walks through
  1. Outcome Contract
  2. Core Stance
  3. Pre-flight
  4. Mode Picker
  5. Durable Context Preflight
  6. Hard Rules
  7. Punctuation Gate
  8. Bilingual Review Mode
  9. Product Localization Review Mode
  10. Document Review Mode
  11. Paragraph Coherence Mode
  12. Tweet / Social Post Mode
  13. Gotchas
  14. Output
Ships with 12 files
  • references/durable-context.md
  • references/mode-long-form.md
  • references/mode-public-reply.md
  • references/mode-release-notes.md
  • references/write-en.md
  • references/write-product-localization.md
  • references/write-zh-bilingual.md
  • references/write-zh-prose.md
  • references/write-zh-release-notes.md
  • references/write-zh.md
  • scripts/check-punctuation.sh
  • scripts/check_punctuation.py
Commands it runs
for candidate in \
done
bash "$GATE" --lang <zh|en|ja|auto> <file>   # or pipe text via stdin
More from Waza
All skills →
About this skill
What does the write skill do?

Rewrites and polishes prose in Chinese or English, removes AI-like wording, and reviews product localization copy while preserving intent for drafts, docs, release notes, launch copy, and social posts. Use when users ask in any language to draft, rewrite, proofread, localize, polish release notes, remove AI-like wording, or prepare launch and social copy. Not for code comments, commit messages, or inline docs.

How do I install it?

Run `npx skills add tw93/Waza --skill write --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 tw93/Waza, a repository with 6,760 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