What problem does it solve? AI-assisted drafts of papers and grant proposals come out generic and verbose, with formulaic openers, inflated phrasing, over-claimed results, and a voice that drifts from the author's own. General-purpose humanizer tools flatten the precision that scholarly writing depends on. ## Core Features & Use Cases - AI-tell removal for academic prose: detects and fixes formulaic openers, over-claiming verbs, empty intensifiers, novelty padding, citation dumping, and overlong sentences across six layered rule sets. - Claim-evidence discipline: checks every empirical claim against its number, figure, table, or citation, downgrades verbs stronger than the evidence, and never alters a number, equation, or reference. - Funding-proposal mode (NSF/NIH): applies a separate register for Project Summaries and Specific Aims pages, keeping vision language while enforcing claim-to-feasibility matching and first-page primacy. - Use Case: Paste an AI-drafted Related Work section or an NIH Specific Aims page, optionally supply a prior accepted paper for voice calibration, and receive a cleaned rewrite plus a change log of patterns removed and claims softened. ## Quick Start Ask the agent to run the academic-humanizer skill on your draft section or main.tex, optionally naming a prior paper for voice matching and the target venue or funding agency.
