Individual skill

AIGC-Detector-Rewriter-Skill

Not available

SKILL.md

Read pinned source

Source commit 84f93cd4ac15477e363229e0dfa690091bb689d9

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

Repository context

Repository stars (not skill ratings)
495
Repository last updated
Jun 19, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Declared tags are partial or unavailable.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt
---
name: aigc-detector-rewriter
title: AIGC Detector & Rewriter
description: >
  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
Back to top