Strips AI writing patterns from prose so it sounds like a human actually wrote it. Load it when you're editing docs, polishing release notes, or reviewing anything that went through ChatGPT first and came out sounding like a corporate press release. It handles both English and Chinese, grounds product claims in actual artifacts instead of letting them drift into marketing speak, and has dedicated modes for bilingual consistency checks and social posts. The Chinese release note mode follows tw93/Mole's numbered style. One thing worth knowing: it edits in place and shuts up after the rewrite. No change lists, no explanations, just the fixed text unless you explicitly ask for commentary.

skills.sh installs
15.9K
GitHub stars
7.5K
last updated
Aug 21, 2026

Install

$ npx -y skills add tw93/waza --skill write --agent claude-code

Installs into .claude/skills of the current project.

Files

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: edited prose for pasted text; for repository edits, a scoped diff and the requested verification or delivery receipt.

Durable Context Preflight

See references/durable-context.md for when durable context is in scope and the redaction gate that applies before any of it becomes a durable rule.

Sponsors

Details

Repository
github.com/tw93/waza
Categories
Git & Pull Requests, Documentation, AI & Agent Building, Release Management
First seen
Apr 16, 2026

More from tw93/waza

All 10
1tw93 avatarhunttw93/wazaFinds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report 15.2Kskills.sh installs
2yuan1z0825 avatarnature-revieweryuan1z0825/nature-skillsSimulate Nature-style or general pre-submission peer review from the referee perspective, not an author rebuttal. Use for reviewer reports, mock peer review, ma14.8Kskills.sh installs
3callstackincubator avatarupgrading-react-nativecallstackincubator/agent-skillsUpgrades React Native apps to newer versions by applying rn-diff-purge template diffs, updating package.json dependencies, migrating native iOS and Android conf13.7Kskills.sh installs
4marimo-team avatarmarimo-pairmarimo-team/marimo-pairDrive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use 13.6Kskills.sh installs
5googlechrome avatarchrome-extensionsgooglechrome/modern-web-guidanceBuild and publish Chrome Extensions using Manifest V3 best practices. Use this skill whenever the user asks to create, modify, debug, or understand Chrome brows12.8Kskills.sh installs
6openai avatarsecurity-best-practicesopenai/skillsPerform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best pr12.2Kskills.sh installs