Skip to content
cccskills
FreePublished on GitHub

paper-claim-audit

Check whether a research paper reports its numbers, comparisons, and evaluation scope accurately by tracing claims to raw result and configuration files. A fresh reviewer receives only the paper and evidence, then produces a claim-by-claim audit report.

OriginalShow the original description

Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.

lisresearchgroup/math-rsi59 stars(GitHub 59 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Verify paper metrics against raw results
  • Check reported averages, comparisons, and percentage changes
  • Audit a paper before submission

Files included (1)

  • SKILL.md15.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

alphaxiv

FreeSummary

Understand a single arXiv paper through an AlphaXiv summary, with full text and LaTeX source available when needed. Use it to identify key findings or ask specific questions about methods, experiments, and equations.

  • Get a quick overview of a paper from its URL
  • Check a paper's methods and experimental results
  • Ask about equations, proofs, or appendix details
lisresearchgroup/math-rsi59Updated Nov 18, 2026

analyze-results

FreeSummary

Compare machine learning experiment results from JSON or CSV files. Calculate improvements over a baseline, summarize variation across repeated runs, identify trends and unusual results, and suggest experiments to test possible explanations.

  • Compare model performance across experimental conditions
  • Check variation across runs with different random seeds
  • Identify trends as a parameter changes
lisresearchgroup/math-rsi59Updated Nov 18, 2026

arxiv

FreeSummary

Search arXiv papers by topic or paper ID, review authors and abstracts, and summarize contributions stated in the abstracts. Download selected papers or all search results as PDFs to build a local paper library.

  • Find arXiv papers on a research topic
  • Retrieve details for a known arXiv paper ID
  • Download all PDFs from a set of search results
lisresearchgroup/math-rsi59Updated Nov 18, 2026

auto-review-loop

FreeSummary

Run an iterative review and revision cycle for research work. A selected external reviewer assesses the materials, the skill implements fixes, and the work is reviewed again until it meets the positive threshold or reaches the configured round limit, with assessments recorded.

  • Iteratively improve a research paper from reviewer feedback
  • Recheck revised work until it earns a positive assessment
  • Track review scores, criticisms, and fixes across rounds
lisresearchgroup/math-rsi59Updated Nov 18, 2026

auto-review-loop

FreeSummary

Use this skill to improve a research artifact through repeated independent review. It records each round, applies fixes, and requests another assessment, stopping when the review meets its acceptance policy or the four-round limit is reached.

  • Refining a research report through repeated review
  • Applying reviewer feedback and checking the fixes
  • Tracking scores and issues across review rounds
lisresearchgroup/math-rsi59Updated Nov 18, 2026

citation-audit

FreeSummary

Audit cited references in a paper by checking that each source exists, its bibliographic details are accurate, and the surrounding text uses it appropriately. Receive an entry-by-entry report of citation issues and suggested fixes.

  • Verify references before submitting a paper
  • Check whether cited sources support nearby claims
  • Find incorrect authors, dates, titles, or venues
lisresearchgroup/math-rsi59Updated Nov 18, 2026

See all skills by lisresearchgroup

Report a problem with this skill