Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
An English and Chinese academic-writing workflow that identifies detector-informed risks at paragraph and chapter level, then applies minimal edits without regenerating whole passages. It protects citations, hypotheses, data, statistical conclusions, headings, and document structure while requiring comparable external retests before reporting measured improvement.
WHO IT'S FOR
Graduate students and PhD candidates
reducing AI-writing risk in academic theses
Academic researchers
refining papers for journal submission
Academic editors and proofreaders
performing minimal-edit revisions on AI-assisted drafts
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
I’m using
Manual custom-skill installation
Installs: AIGC Detector & Rewriter Skill, including its required reference files · Openclaw, Hermes-Agent
Copy `SKILL.md` into the target agent's skill environment.
Keep all accompanying reference files in the `references/` folder, provide thesis text, chapter text, or detector reports as input, and run the task according to the skill's routing rules.
Externally re-test rewritten chapters before accepting a new baseline.
One English thesis paragraph supplied in place of `[Paste one English thesis paragraph here.]`
Using the aigc-detector-rewriter skill, please revise the following thesis paragraph to reduce AI-generated writing patterns. Keep the meaning, citations, variables, and academic logic unchanged. Do not over-polish the language. Do not shorten the paragraph.
[Paste one English thesis paragraph here.]
OpenClaw
Hermes