aigc-detector-rewriter
aigc-detector-rewriter is a Writing style & humanising skill for AI agents, published by Moonlit-Pages in the AIGC-Detector-Rewriter-Skill repository on GitHub. Skillspace rates aigc-detector-rewriter F (52/100) and it passed the safety scan; the rating is based on static analysis only.
Detect AI-generated writing-risk patterns in English and Chinese thesis text, score paragraphs by external-detector-informed risk, and revise selected high-risk passages while preserving meaning, citations, variables, hypotheses, data, statistical conclusions, and document structure. Uses iterative, externally re-tested, chapter-by-chapter, minimal-edit revision rounds that never regenerate whole paragraphs, never accept a rewritten candidate as a new baseline when a comparable external re-test shows regression (before re-test it is only a candidate), never shrink the paper, never merge paragraphs or displace section headings, and keep every sentence grammatically complete, correctly punctuated, a sensible length, and free of jarring meta-commentary. The objective is to bring each target chapter and, where measurable, the whole document below the user-defined target (default 30 percent); it does not guarantee a detector outcome and must stop or redesign the strategy when fatigue,…
- Grade
- F
- Quality
- 52 / 100
- Safety
- Passed
- GitHub stars
- 307
Unproven: rated by static analysis only, not yet compared head-to-head.
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
- 56 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
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.