claesbackman

10 mods across 1 repository, 474 stars between them.

audit-analysis

01

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects. Runs in an isolated subagent. Use before circulating results or submitting. This is not a reproducibility or…

474 4d ago A 71 tokens original MIT

explain-diff

02

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Explain a code change as a standalone offline HTML page with a five-question quiz. Reads the diff and the surrounding code from scratch, states the consequences for the empirical results, and saves the page outside the repository under a dated filename.

474 4d ago A 51 tokens original MIT

paper-version

03

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Convert a LaTeX research paper into a policy brief, 1-page summary, or 5-page summary for a general audience, with factual review and a standalone HTML page for GitHub Pages.

474 4d ago A 43 tokens original MIT

pdf-to-markdown

04

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Split a PDF into chunks and convert it to readable markdown text. Use when the user wants to read, extract, or convert a PDF document.

474 4d ago A 34 tokens original MIT

review-grant

05

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Run a 6-agent pre-submission panel review for a grant proposal targeting a specified funder or program.

474 4d ago A 25 tokens original MIT

review-pap

06

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Run a 6-agent pre-submission review of a pre-analysis plan (PAP) for a specified registration target or journal.

474 4d ago A 29 tokens original MIT

review-paper-checks

07

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Run a fast 3-agent mechanical check of an economics paper — spelling and grammar, internal consistency and cross-references, and unsupported claims. Reports fixable errors, not editorial judgment.

474 4d ago A 42 tokens original MIT

review-paper-code

08

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Review research code for reproducibility and quality, extract the paper's main empirical claims, compare paper to code, and write a constructive markdown report. Designed for social science / economics projects with LaTeX papers and Stata, R, or Python code.

474 4d ago A 55 tokens original MIT

review-paper-light

09

claesbackman/AI-research-feedback

Skill Claude CodeCodex

Run a fast 2-agent pre-submission check for an economics paper — focuses on contribution, identification, and causal overclaiming. Completes in 1 minute.

474 4d ago A 38 tokens original MIT