← ClaudeAtlas

paper-reviewerlisted

Deep pre-submission review of a scientific manuscript, modeled on Google's Paper Assistant Tool (PAT). Segments the manuscript, allocates a reasoning budget per segment, dispatches deep reviewers in parallel (each with the full text as context), and consolidates into a single report with severity, quoted evidence, and anti-hallucination checks. Use when asked to review, audit, critique, or validate a paper, thesis, dissertation, chapter, or proposal before submission. Works in English and Brazilian Portuguese.
whoisraibolt/paper-skills · ★ 1 · AI & Automation · score 65
Install: claude install-skill whoisraibolt/paper-skills
# paper-reviewer — deep pre-submission review A reimplementation of the **Paper Assistant Tool (PAT)** architecture (Jayaram et al., Google Research, arXiv:2606.28277) on Claude Code subagents in place of Gemini Deep Think. The premise from PAT, which is what makes this skill worth more than "read the paper and criticize it": a single reading pass spends its reasoning budget uniformly and shallowly. Segmenting the manuscript, giving each reviewer **the whole text as context but only one segment to verify**, then consolidating with deduplication and grounding checks, raises real-error detection substantially. On the Math/CS subset of the SPOT benchmark, this orchestration took the same model from 55.2% to 89.7% detection. It produces no score, no ranking and no accept/reject recommendation. It produces **objective errors and actionable improvements**. Writing counterpart: `paper-writer`. Writing and reviewing are separate passes by design; whoever writes does not approve their own text in the same context. --- ## Stage 0 — Resolve the target 1. If the user named a file, use it. Otherwise look for the most likely manuscript in the current directory (a `.tex` with `\documentclass`, or a long `.md`) and **confirm with the user before spending agents** if there is more than one candidate. 2. **Accepted formats are `.tex`, `.md`, `.pdf` and `.docx`, and source beats the rest.** PAT lists PDF parsing failure among its three most reported limitations, and a `.do