#67 · Primary category: Writing & Content

academic-humanizer

academic-writing grant-writing llm nih nsf research scientific-writing writing-assistant

Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.

Project last updated:07/03/26

GitHub Stars

1.2K

Forks

118

Contributors

1

License

Other

Why we included this project

Anyone who drafts papers or grant proposals with an AI assistant will recognize the problem this skill targets: the same generic openers and inflated verbs that make AI-assisted drafts read like AI. It runs inside Claude Code, Codex, or MorphMind, and you can either paste a section or point it at a LaTeX file. It trims that telltale phrasing and shortens over-long sentences while leaving numbers, citations, and hedging exactly as written, and it is calibrated to scholarly conventions rather than blog or marketing prose, with a separate mode for NSF and NIH proposals that concentrates on the first pages reviewers actually score. The authors are clear that it is an editing aid for clarity and voice, not a detector-evasion tool, and that you still have to follow your venue's AI-disclosure policy. Because it ships as a plain SKILL.md plus examples, you can fork it and retune the rules to your own field and writing style.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category