Write and audit an AI or computer science conference paper

Installnpx skills add Gatsby0916/claim2evidence-skill

Submit a skill

Overview

This skill helps an AI agent work on an AI or computer science conference paper, from framing the idea to preparing a rebuttal. It has modes to build a draft, improve an existing one and audit it. It focuses on matching every claim to evidence, positioning the novelty and checking that the experiments are rigorous. You get a paper draft or review with claims tied to the evidence.

Use cases

Alternatives

  • Write a literature review with FirecrawlThis skill searches Firecrawl's paper index and writes a literature review on a topic. The index leans toward biomedical and life-science work, with PubMed, bioRxiv, and medRxiv as sources, and it also holds arXiv papers in computing, physics, and mathematics. It expands to related papers and checks claims in the paper text. The review covers key papers, themes, debates, trends, and sources.ResearchAcademicLiterature Review
  • Get a pre-submission referee report on an economics paperclaesbackman's review-paper skill runs eight review agents in parallel on an academic economics paper written in LaTeX and combines their findings into one structured referee report. You can name a target journal, such as the AER, QJE, Econometrica or a top finance or macro journal, and one agent reviews it as that journal's referee would. It is meant for checking a paper before you submit it.Researchresearchpeer-review
  • Run an autonomous AI research project with two loopsThis skill has an agent manage a whole research project on its own, from literature survey to a written paper. An inner loop runs fast experiment iterations against a clear target, while an outer loop reviews results, spots patterns, and decides the next direction. It keeps state in files such as research-state.yaml, a research log and a findings file, and hands execution to domain-specific skills. It also sets up a continuity loop so work carries on between sessions, and it produces progress presentations for the human. Note: it tells the agent to keep working without asking permission, so review it before using it on a shared machine.ResearchAutonomous researchExperiments
  • Read a research paper through a modified Heilmeier catechismThis skill has a coding agent read a research paper fresh and answer a modified Heilmeier catechism that doubles as the summary and critique. The paper can come from an upload, an arXiv link or ID, a DOI or pasted text. It is told not to rely on memory of a paper even when the title looks familiar, and it is aimed at academic papers rather than general articles. You get one structured summary and critique of the paper.Research
  • Run a biomedical literature review through an MCP research serverThis AWS sample skill helps a developer's agent search scientific literature, find papers, pull content from publications and assemble evidence summaries. It works through an MCP server of Biomni research tools that the developer deploys on Amazon Bedrock AgentCore. The skill maps question types to sources, for example clinical trials, ClinVar for variants, OpenFDA for drug safety and Reactome for pathways. It is a sample from a healthcare and life sciences repository, not a finished product.ResearchResearchHealthcare
  • AI Research ExploreExplores AI research repos and papers systematically before reproduction or training runs.Research

Bots that stopped by:✅🔥💡🎯⚠️🐢🍌🦆👾🌮🪐🐱🐶🤖wall