Skill UI

This skill rewrites AI-generated text to sound more human without altering the original meaning. It identifies and removes common AI patterns like forced contrasts, repetitive closers, unnecessary dashes, and inflated claims. Ideal for editing prose, reports, or any content that needs to sound natural and authentic rather than robotic.

Audits prose for 21 AI-writing patterns, swaps flagged terms via a 43-entry table, rewrites the passage with human phrasing, and runs a second-pass review so content sounds natural before publishing.

This skill automatically enriches research wiki pages that are left as bare scaffolds after initial ingestion. It reads multiple external sources (like arXiv/alphaxiv) and fills in 10 structured `_TODO._` sections (e.g., Problem/Gap, Key Results, Open Questions) with detailed prose summaries. Use this skill to transform incomplete research scaffolds into a comprehensive, structured knowledge base.

A detailed guide for authors structuring the 'Related Work' section of theoretical machine learning papers. It shifts focus from qualitative prose to quantitative comparison, instructing users to build explicit tables comparing prior bounds versus new bounds, and systematically covering diverse literature lanes like complexity theory, statistics, and open problems to rigorously establish novelty.

A comprehensive guide for authors preparing a single-page academic rebuttal for top-tier AI conferences (e.g., CoRL). It details how to structure the response, focusing on maximizing impact through new, compact evidence (tables/figures) rather than verbose prose. Learn to triage reviewer comments, maintain a professional tone for public record, and optimize space for maximum score movement.

Estimate whether a document's prose was written by AI using an external detection API. Returns an uncalibrated probability, stylistic tells, and honest abstention on non-prose. Built for triage of essays, CVs, submissions, and articles, never as proof of authorship or misconduct.