QinghongLin/paperdoctor

prepare-paper

Organize a paper PDF and its codebase into clean reading artifacts. Use this before any other read-* skills.

read-bib

Verify each cited reference exists via web search.

read-claim

Deep extraction of all verifiable claims from a research paper. Actively proposes implicit claims, splits compound statements, and flags cross-reference inconsistencies.

read-code

Verify paper claims with evidence_type "code" against the actual codebase. Use after read-txt to check if code matches what the paper says.

read-exp

Review experiment design and produce a prioritized reproduction plan. Targets claims with evidence_type "experiment" from check_claim.json. Output feeds into run-exp.

read-prior

Web-search validation of citation and novelty claims from check_claim.json. Checks whether cited facts are accurate and novelty claims ("first", "pioneering") hold against published literature.

read-theory

Verify theoretical claims — mathematical derivations, proofs, and formal arguments. Targets claims with evidence_type "theoretical" from check_claim.json.

read-txt

Check writing quality — grammar, typos, unclear phrasing, inconsistent terminology, logical flow issues. Scans the full paper text and reports issues by page.

read-vis

Check a paper's visual presentation for layout, figure quality, spacing, and formatting issues. Use when reviewing paper polish before submission.

run-exp

Run experiments based on the plan from read-exp. Reads check_exp.json and check_code.json, creates environment, runs experiments, compares against paper numbers.

vis-preview

Generate an interactive HTML review with PDF page images (left) + code viewer with syntax highlighting (middle) + findings with bidirectional navigation (right). All findings are permanently highlighted on the PDF and clickable in both directions.