Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

AIGC Detector & Thesis Writing Assistant

Scores academic papers for AI-generated writing across five dimensions, then produces a detection report, a format-preserving rewritten .docx, or a full thesis draft.

Content & WritingIntermediate★ 114⑂ 8AI score 9/10Last updated: Jun 2, 2026

What it does

  • Reads a .docx file (or pasted text) and analyzes it on five dimensions — sentence regularity, connector density, voice characteristics, vocabulary diversity, argumentation depth — combining them into a weighted overall risk score.
  • Emits a Markdown detection report with per-dimension scores, paragraph-level High/Medium/Low risk tags, rationale for each flag, and a rewrite-priority table.
  • On your confirmation, rewrites only the high/medium-risk paragraphs using seven rewrite techniques and writes them back via docx_io.py replace, preserving the original formatting and images while keeping a _backup.docx.
  • Thesis Writing mode inspects templates, sample papers, and source code in an About/ folder, then walks through outline → chapter drafts → Mermaid diagrams rendered to PNG and inserted with captions → template formatting.
  • Auto-detects Chinese vs. English and switches dimension definitions and report templates accordingly.

Who it's for

  • Graduate and undergraduate students checking a thesis for AI-sounding prose before submission.
  • Researchers polishing English manuscripts full of formulaic transitions and passive constructions.
  • Advisors and writing tutors who need structured, per-dimension feedback on student drafts.

Examples

  1. "Analyze this paper for AI-generated content: ~/thesis.docx" → get a per-paragraph risk table plus a prioritized rewrite plan.
  2. "Rewrite the high-risk paragraphs and export a .docx" → get thesis_rewritten.docx with a summary of which techniques were applied.
  3. "Start thesis writing mode, template is in About/" → approve an outline, then receive chapter drafts with auto-inserted architecture diagrams.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/free-revalution/AIGC-Detector-Pro/HEAD/.claude/skills/aigc-detector/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .claude/skills/aigc-detector folder from the GitHub repo free-revalution/AIGC-Detector-Pro into my ~/.claude/skills/aigc-detector/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/free-revalution/AIGC-Detector-Pro.git && mkdir -p ~/.claude/skills && cp -r AIGC-Detector-Pro/.claude/skills/aigc-detector ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and confirm Python 3 is available: python3 -V
  2. Clone the repository: git clone https://github.com/free-revalution/AIGC-Detector-Pro.git
  3. Copy the skill into your user skills directory: mkdir -p ~/.claude/skills && cp -r AIGC-Detector-Pro/.claude/skills/aigc-detector ~/.claude/skills/
  4. Smoke-test the helper script: python3 ~/.claude/skills/aigc-detector/scripts/docx_io.py read ~/sample.docx
  5. If imports fail, install dependencies: pip3 install python-docx (diagram generation may additionally require a Mermaid renderer).
  6. Restart Claude Code and prompt it with something like "Analyze this paper for AI-generated content: <file path>".
  7. Always diff the rewritten output against the _backup.docx, and check your institution's academic-integrity policy before using the rewrite mode.
View source on GitHub ↗License: MIT