Academic Paper Review
Get a structured, venue-style peer review of a paper from a PDF, URL, or arXiv link when you need rigor before citing or building on the work.
Overview
Academic Paper Review is an agent skill most often used in Idea (also Validate, Build) that produces structured peer-review-quality analyses of academic papers from PDFs or URLs.
Install
npx skills add https://github.com/bytedance/deer-flow --skill academic-paper-reviewWhat is this skill?
- Structured reviews: summary, strengths, weaknesses, methodology, contribution, literature positioning
- Methodology rigor checks: experimental design, statistics, reproducibility
- Supports uploaded PDFs, paper URLs, and arXiv links
- Targets standards aligned with top venues (NeurIPS, ICML, ACL, Nature, IEEE)
- Actionable recommendations and constructive peer-review tone
- Review sections include summary, strengths, weaknesses, methodology, contribution, literature positioning, and recommend
Adoption & trust: 1k installs on skills.sh; 70.7k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You found a dense PDF or arXiv link and need a rigorous, structured read before you trust its claims for your product or model roadmap.
Who is it for?
Indie AI builders evaluating papers for RAG, agents, or ML features who want reproducibility and novelty called out explicitly.
Skip if: Substituting formal peer review for journal submission, medical/legal advice, or homework grading policies at your institution.
When should I use this skill?
User requests review, analyze, critique, or summarize academic papers, preprints, or scientific publications via PDF, URL, or arXiv.
What do I get? / Deliverables
You receive a venue-style review with methodology and contribution verdicts plus concrete recommendations you can cite in notes or specs.
- Structured academic review document
- Methodology and contribution assessment with recommendations
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Idea/research is the first shelf for deep literature comprehension before you commit product or model choices. Research subphase covers synthesizing external publications—not shipping code review.
Where it fits
Review two competing agent-architecture papers and compare novelty before picking a stack.
Decide whether a cited benchmark paper is strong enough to justify a scoped MVP feature.
Draft an internal design note with contribution and limitation language mirrored from a structured review.
How it compares
Research critique skill package, not a reference manager or automated citation graph MCP.
Common Questions / FAQ
Who is academic-paper-review for?
Solo technical founders and agent builders who ingest research PDFs and need fast, structured critical analysis.
When should I use academic-paper-review?
In Idea when surveying literature; in Validate when a paper must support a go/no-go; in Build when writing internal docs that justify a method choice.
Is academic-paper-review safe to install?
Check the Security Audits panel on this page; fetching external URLs sends network traffic and you should not upload confidential manuscripts to untrusted environments.
SKILL.md
READMESKILL.md - Academic Paper Review
# Academic Paper Review Skill ## Overview This skill produces structured, peer-review-quality analyses of academic papers and research publications. It follows established academic review standards used by top-tier venues (NeurIPS, ICML, ACL, Nature, IEEE) to provide rigorous, constructive, and balanced assessments. The review covers **summary, strengths, weaknesses, methodology assessment, contribution evaluation, literature positioning, and actionable recommendations** — all grounded in evidence from the paper itself. ## Core Capabilities - Parse and comprehend academic papers from uploaded PDFs or fetched URLs - Generate structured reviews following top-venue review templates - Assess methodology rigor (experimental design, statistical validity, reproducibility) - Evaluate novelty and significance of contributions - Position the work within the broader research landscape via targeted literature search - Identify limitations, gaps, and potential improvements - Produce both detailed review and concise executive summary formats - Support papers in any scientific domain (CS, biology, physics, social sciences, etc.) ## When to Use This Skill **Always load this skill when:** - User provides a paper URL (arXiv, DOI, conference proceedings, journal link) - User uploads a PDF of a research paper or preprint - User asks to "review", "analyze", "critique", "assess", or "summarize" a research paper - User wants to understand the strengths and weaknesses of a study - User requests a peer-review-style evaluation of academic work - User asks for help preparing a review for a conference or journal submission ## Review Methodology ### Phase 1: Paper Comprehension Thoroughly read and understand the paper before forming any judgments. #### Step 1.1: Identify Paper Metadata Extract and record: | Field | Description | |-------|-------------| | **Title** | Full paper title | | **Authors** | Author list and affiliations | | **Venue / Status** | Publication venue, preprint server, or submission status | | **Year** | Publication or submission year | | **Domain** | Research field and subfield | | **Paper Type** | Empirical, theoretical, survey, position paper, systems paper, etc. | #### Step 1.2: Deep Reading Pass Read the paper systematically: 1. **Abstract & Introduction** — Identify the claimed contributions and motivation 2. **Related Work** — Note how authors position their work relative to prior art 3. **Methodology** — Understand the proposed approach, model, or framework in detail 4. **Experiments / Results** — Examine datasets, baselines, metrics, and reported outcomes 5. **Discussion & Limitations** — Note any self-identified limitations 6. **Conclusion** — Compare concluded claims against actual evidence presented #### Step 1.3: Key Claims Extraction List the paper's main claims explicitly: ``` Claim 1: [Specific claim about contribution or finding] Evidence: [What evidence supports this claim in the paper] Strength: [Strong / Moderate / Weak] Claim 2: [...] ... ``` ### Phase 2: Critical Analysis #### Step 2.1: Literature Context Search Use web search to understand the research landscape: ``` Search queries: - "[paper topic] state of the art [current year]" - "[key method name] comparison benchmark" - "[authors] previous work [topic]" - "[specific technique] limitations criticism" - "survey [research area] recent advances" ``` Use `web_fetch` on key related papers or survey