paper-review
Performs comprehensive ML paper reviews based on NeurIPS/ICML/ICLR criteria.
Install
mkdir -p .claude/skills/paper-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13042" && unzip -o skill.zip -d .claude/skills/paper-review && rm skill.zipInstalls to .claude/skills/paper-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Comprehensive ML Paper Review. Use when user needs a rigorous peer review of ML papers following NeurIPS/ICML/ICLR standards with structured feedback and ratings.Key capabilities
- →Extract contributions, hypotheses, and evidence into a claims ledger
- →Identify closest prior work for novelty and positioning assessment
- →Audit theory, methods, and systems for technical correctness
- →Check baselines, ablations, metrics, and splits for experimental rigor
- →List missing details that block reproduction
- →Flag dual-use, privacy, bias, and misuse risks
How it works
The skill acts as an elite ML researcher, extracting claims, assessing novelty, auditing technical correctness and experimental rigor, and identifying reproducibility issues. It then generates a structured review report.
Inputs & outputs
When to use paper-review
- →Review ML manuscript
- →Check paper experimental rigor
- →Assess paper reproducibility
About paper-review
Evaluates ML manuscripts for soundness, novelty, and experimental rigor. Audits system claims, code verification, and potential safety/ethics concerns.
Comprehensive ML Paper Review. Use when user needs a rigorous peer review of ML papers following NeurIPS/ICML/ICLR standards with structured feedback and ratings.
When not to use it
- →When claiming to have run code without verification
- →When fabricating citations
- →When revealing confidential content if the manuscript is under review
Limitations
- →Does not claim to have run code unless verified
- →Does not fabricate citations
- →Does not reveal confidential content if manuscript is under review
How it compares
This workflow provides a rigorous, structured peer review of ML papers following top-tier venue standards, focusing on soundness, reproducibility, and ethical considerations, unlike a casual reading.
Compared to similar skills
paper-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| paper-review (this skill) | 0 | 7mo | No flags | Advanced |
| esm | 3 | 9mo | Review | Advanced |
| hugging-face-paper-publisher | 6 | 8mo | Review | Intermediate |
| torchdrug | 3 | 9mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by ihmorol
View all by ihmorol →You might also like
esm
davila7
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.
hugging-face-paper-publisher
patchy631
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
torchdrug
davila7
Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.
string-database
davila7
Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.
transformer-lens-interpretability
davila7
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
denario
davila7
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.