humanize
humanize is a Writing style & humanising skill for AI agents, published by tzengyuxio in the skills repository on GitHub. Skillspace rates humanize C (71/100) and it passed the safety scan; the rating is based on static analysis only.
Remove AI-generated writing tics (grandiose wording, tricolon abuse, vague attribution, hollow parallel structures) and rewrite flagged passages in a more natural voice. Works on markdown files or inline text; checklist is tuned for Traditional Chinese but principles apply to any language. **Scope boundary**: humanize targets *AI-flavored tone*. If the issue is Europeanized sentence structure (翻譯腔 / 歐化) — passive voice, abstract subjects, 的/們/性/地 overuse, long pre-modifiers, calque prepositions — use `dewesternise` instead, which has a specific 25-item 歐化 checklist. Triggers on "/humanize", "make it sound human", "remove AI tone", "去 AI 味", "寫得更像人", "降低 AI 感" — but if the user says "翻譯腔" / "太歐化" / "去歐化", route to `dewesternise` first.
- Grade
- C
- Quality
- 71 / 100
- Safety
- Passed
- GitHub stars
- 43
Unproven: rated by static analysis only, not yet compared head-to-head.
Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it is a near-duplicate variant of another skill. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 82 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.