AI-research-feedback
Referee-style reviews for papers, grants, and research code
All Skills in This Repository (4)
Pure Emerald Level Indicatorsreview-paper
Review LaTeX academic papers with eight specialized agents for pre-submission quality.
review-paper-code
Review research code for reproducibility and alignment with LaTeX papers.
review-paper-light
Review academic papers for contribution and overclaiming via two-agent analysis.
review-pap
Reviews pre-analysis plans via 6 specialized agents for consistency and compliance.
Frequently Asked Questions
FAQPage SchemaHow to install AI-research-feedback?▼
Run `npx skills add claesbackman/AI-research-feedback --all -g -y` in your terminal to install all review skills globally.
How to get feedback on a research paper before submission?▼
Run /review-paper for a full 8-agent referee report targeting journals like AER or QJE, or /review-paper-light for a fast 2-agent check on contribution and identification.
Can it check if my code matches my paper?▼
Yes. The review-paper-code skill maps your paper's main empirical claims to your Stata, R, or Python code and flags reproducibility gaps, while audit-analysis hunts for errors in changed analysis code.
Does it work with Claude Code?▼
Yes. All skills follow the standard SKILL.md format and run as slash commands inside Claude Code, with reviews saved to a dated reviews/ folder.
Can it review grant proposals and pre-analysis plans?▼
Yes. The review-grant skill runs a 6-agent panel review for funders like NSF, NIH, or ERC, and review-pap checks pre-analysis plans against registry standards like AEA or OSF.
Related Repositories in Education & Research
View All in Education & Research→learn-claude-code
Learn to build AI agent harnesses from scratch
ai-agents-for-beginners
Learn to build, deploy, and secure AI agents step by step
33-js-concepts
Master 33 essential JavaScript concepts with tested, verified guides