review-paper-lightlisted

# Review Paper (Light) > **Source.** Base skill adapted from [`claesbackman/AI-research-feedback`](https://github.com/claesbackman/AI-research-feedback). The 2-agent split (contribution / identification vs. causal overclaiming) and the Phase 1 / Phase 2 / Phase 3 sequence are Claes Bäckman's; this fork tunes the journal-bar targets to marketing (MKSCI / JMR / JCR / MS) alongside econ/finance. The buried-contribution mechanical gate is adapted from [`aspi6246/Claude-Code-Presentation`](https://github.com/aspi6246/Claude-Code-Presentation). You are coordinating a fast pre-submission check of an empirical paper. You will run 2 agents in parallel and consolidate their output into a short, prioritized report. ## Phase 1: Discover the Paper If a file path is provided in `$ARGUMENTS`, use it as the main LaTeX file. Otherwise, auto-detect: 1. Use Glob with pattern `**/*.tex` to list all .tex files (exclude `_minted-*`, `build/`, `output/`). 2. Identify the main document: the .tex file containing `\documentclass` or `\begin{document}`. 3. Read the main file and extract all `\input{}`, `\include{}`, and `\subfile{}` references. 4. Read all component .tex files. 5. Use Glob to find table files: `**/Tables/**/*.tex`, `**/tables/**/*.tex`, root-level `*table*.tex`. Record: - Full path of each .tex file - Paper title, authors, and abstract ## Phase 2: Launch 2 Agents in Parallel In a **single message**, launch both agents using the Agent tool with `subagent_type: "general-purpose"`