New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Academic Paper Review

by bytedance in bytedance/deer-flow

Produces a structured peer-review style critique of a research paper, covering methodology, contribution and how the work sits among related studies.

MITAuto-check passedResearch & Science

Install Academic Paper Review

skills CLI
$ npx skills add bytedance/deer-flow --skill academic-paper-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install bytedance/deer-flow academic-paper-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/bytedance/deer-flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public/academic-paper-review .claude/skills/academic-paper-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
academic-paper-review
GitHub stars
84k
Used in
2 other repos
Token cost
~3k tokens
SKILL.md length
1,028 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Produces a structured peer-review style critique of a research paper, covering methodology, contribution and how the work sits among related studies.

  • Works in 3 steps: Paper Comprehension → Critical Analysis → Review Synthesis
  • Reviewing a preprint or journal submission before writing referee comments
  • SKILL.md covers Overview, Core Capabilities, When to Use This Skill and Review Methodology, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Given a paper as an uploaded PDF or a link such as an arXiv page, the agent first records the metadata: title, authors, venue or preprint status, year, field and paper type. It then reads in a deliberate order, starting with the abstract and introduction to find the claimed contributions, followed by the related-work section to see how the authors place themselves against earlier research.

The finished review contains a summary, strengths, weaknesses, an assessment of methodology (experimental design, statistical validity, reproducibility), an evaluation of novelty and significance, literature positioning backed by targeted searches, and concrete recommendations. You can ask for a full review or a short executive summary. It works across scientific fields and is modeled on the review forms of major conferences and journals.

When your agent uses it

  • Reviewing a preprint or journal submission before writing referee comments
  • Getting an honest read on the strengths and weaknesses of a study you plan to cite
  • Summarizing a paper's contribution and limits for a reading group

Example prompts

  • “Review this arXiv paper on diffusion models and list its weaknesses.”
  • “Write a peer review of the attached PDF in the style of a conference reviewer.”
  • “Give me a one-page executive summary of this study's method and contribution.”

Requirements

  • The paper as an uploaded PDF or a reachable URL
  • Web search access for the literature positioning step

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Paper Comprehension
  2. Critical Analysis
  3. Review Synthesis

What it can do on your machine

Read from SKILL.md and the folder at commit 8a3350a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Academic Paper Review loads about 3k tokens when it runs. Until then it costs about 130 tokens; SKILL.md has 1,028 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~130
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from bytedance/deer-flow at commit 8a3350a, republished under its MIT licence (© bytedance). 1,028 words, ~3,023 tokens.

Download SKILL.mdSave it as .claude/skills/academic-paper-review/SKILL.md (or your agent's skills folder).
name
academic-paper-review
description
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer 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:

FieldDescription
TitleFull paper title
AuthorsAuthor list and affiliations
Venue / StatusPublication venue, preprint server, or submission status
YearPublication or submission year
DomainResearch field and subfield
Paper TypeEmpirical, 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

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 surveys to understand where this work fits.

Step 2.2: Methodology Assessment

Evaluate the methodology using the following framework:

CriterionQuestions to AskRating
SoundnessIs the approach technically correct? Are there logical flaws?1-5
NoveltyWhat is genuinely new vs. incremental improvement?1-5
ReproducibilityAre details sufficient to reproduce? Code/data available?1-5
Experimental DesignAre baselines fair? Are ablations adequate? Are datasets appropriate?1-5
Statistical RigorAre results statistically significant? Error bars reported? Multiple runs?1-5
ScalabilityDoes the approach scale? Are computational costs discussed?1-5
Step 2.3: Contribution Significance Assessment

Evaluate the significance level:

LevelDescriptionCriteria
LandmarkFundamentally changes the fieldNew paradigm, widely applicable breakthrough
SignificantStrong contribution advancing the state of the artClear improvement with solid evidence
ModerateUseful contribution with some limitationsIncremental but valid improvement
MarginalMinimal advance over existing workSmall gains, narrow applicability
Below thresholdDoes not meet publication standardsFundamental flaws, insufficient evidence
Step 2.4: Strengths and Weaknesses Analysis

For each strength or weakness, provide:

  • What: Specific observation
  • Where: Section/figure/table reference
  • Why it matters: Impact on the paper's claims or utility
Phase 3: Review Synthesis
Step 3.1: Assemble the Structured Review

Produce the final review using the template below.

Review Output Template

markdown
# Paper Review: [Paper Title]

## Paper Metadata
- **Authors**: [Author list]
- **Venue**: [Publication venue or preprint server]
- **Year**: [Year]
- **Domain**: [Research field]
- **Paper Type**: [Empirical / Theoretical / Survey / Systems / Position]

## Executive Summary

[2-3 paragraph summary of the paper's core contribution, approach, and main findings.
State your overall assessment upfront: what the paper does well, where it falls short,
and whether the contribution is sufficient for the claimed venue/impact level.]

## Summary of Contributions

1. [First claimed contribution — one sentence]
2. [Second claimed contribution — one sentence]
3. [Additional contributions if any]

## Strengths

### S1: [Concise strength title]
[Detailed explanation with specific references to sections, figures, or tables in the paper.
Explain WHY this is a strength and its significance.]

### S2: [Concise strength title]
[...]

### S3: [Concise strength title]
[...]

## Weaknesses

### W1: [Concise weakness title]
[Detailed explanation with specific references. Explain the impact of this weakness on
the paper's claims. Suggest how it could be addressed.]

### W2: [Concise weakness title]
[...]

### W3: [Concise weakness title]
[...]

## Methodology Assessment

| Criterion | Rating (1-5) | Assessment |
|-----------|:---:|------------|
| Soundness | X | [Brief justification] |
| Novelty | X | [Brief justification] |
| Reproducibility | X | [Brief justification] |
| Experimental Design | X | [Brief justification] |
| Statistical Rigor | X | [Brief justification] |
| Scalability | X | [Brief justification] |

## Questions for the Authors

1. [Specific question that would clarify a concern or ambiguity]
2. [Question about methodology choices or alternative approaches]
3. [Question about generalizability or practical applicability]

## Minor Issues

- [Typos, formatting issues, unclear figures, notation inconsistencies]
- [Missing references that should be cited]
- [Suggestions for improved clarity]

## Literature Positioning

[How does this work relate to the current state of the art?
Are key related works cited? Are comparisons fair and comprehensive?
What important related work is missing?]

## Recommendations

**Overall Assessment**: [Accept / Weak Accept / Borderline / Weak Reject / Reject]

**Confidence**: [High / Medium / Low] — [Justification for confidence level]

**Contribution Level**: [Landmark / Significant / Moderate / Marginal / Below threshold]

### Actionable Suggestions for Improvement
1. [Specific, constructive suggestion]
2. [Specific, constructive suggestion]
3. [Specific, constructive suggestion]

Review Principles

Constructive Criticism
  • Always suggest how to fix it — Don't just point out problems; propose solutions
  • Give credit where due — Acknowledge genuine contributions even in flawed papers
  • Be specific — Reference exact sections, equations, figures, and tables
  • Separate minor from major — Distinguish fatal flaws from fixable issues
Show full SKILL.md (402 more words)Show less
Objectivity Standards
  • ❌ "This paper is poorly written" (vague, unhelpful)
  • ✅ "Section 3.2 introduces notation X without formal definition, making the proof in Theorem 1 difficult to follow. Consider adding a notation table after the problem formulation." (specific, actionable)
Ethical Review Practices
  • Do NOT dismiss work based on author reputation or affiliation
  • Evaluate the work on its own merits
  • Flag potential ethical concerns (bias in datasets, dual-use implications) constructively
  • Maintain confidentiality of unpublished work

Adaptation by Paper Type

Paper TypeFocus Areas
EmpiricalExperimental design, baselines, statistical significance, ablations, reproducibility
TheoreticalProof correctness, assumption reasonableness, tightness of bounds, connection to practice
SurveyComprehensiveness, taxonomy quality, coverage of recent work, synthesis insights
SystemsArchitecture decisions, scalability evidence, real-world deployment, engineering contributions
PositionArgument coherence, evidence for claims, impact potential, fairness of characterizations

Common Pitfalls to Avoid

  • ❌ Reviewing the paper you wish was written instead of the paper that was submitted
  • ❌ Demanding additional experiments that are unreasonable in scope
  • ❌ Penalizing the paper for not solving a different problem
  • ❌ Being overly influenced by writing quality versus technical contribution
  • ❌ Treating absence of comparison to your own work as a weakness
  • ❌ Providing only a summary without critical analysis

Quality Checklist

Before finalizing the review, verify:

  • Paper was read completely (not just abstract and introduction)
  • All major claims are identified and evaluated against evidence
  • At least 3 strengths and 3 weaknesses are provided with specific references
  • The methodology assessment table is complete with ratings and justifications
  • Questions for authors target genuine ambiguities, not rhetorical critiques
  • Literature search was conducted to contextualize the contribution
  • Recommendations are actionable and constructive
  • The overall assessment is consistent with the identified strengths and weaknesses
  • The review tone is professional and respectful
  • Minor issues are separated from major concerns

Output Format

  • Output the complete review in Markdown format
  • Save the review to /mnt/user-data/outputs/review-{paper-topic}.md when working in sandbox
  • Present the review to the user using the present_files tool

Notes

  • This skill complements the deep-research skill — load both when the user wants the paper reviewed in the context of the broader field
  • For papers behind paywalls, work with whatever content is accessible (abstract, publicly available versions, preprint mirrors)
  • Adapt the review depth to the user's needs: a brief assessment for quick triage versus a full review for submission preparation
  • When reviewing multiple papers comparatively, maintain consistent criteria across all reviews
  • Always disclose limitations of your review (e.g., "I could not verify the proofs in Appendix B in detail")

© bytedance, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/public/academic-paper-review of bytedance/deer-flow.

Open the folder on GitHubat commit 8a3350a

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in bytedance/deer-flow, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Academic Paper Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Academic Paper Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Academic Paper Review this skillbytedance/deer-flow84k2 repos~3kAutomated safety check: PassMIT
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Academic Research PipelineImbad0202/academic-research-skills51k—~15kAutomated safety check: PassCustom licence
Academic Research Suite for CodexImbad0202/academic-research-skills-codex12k—~12kAutomated safety check: PassCustom licence
Paper Research on arXivXiaomiMiMo/MiMo-Code14k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes

  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Academic Research Pipeline

    Imbad0202/academic-research-skills

    Orchestrates a ten-stage academic workflow from research to finished manuscript, including integrity checks, two rounds of peer review and revision.

    51k GitHub stars~15k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Academic Research Suite for Codex

    Imbad0202/academic-research-skills-codex

    A router skill that sends academic work such as literature reviews, drafting, citation checks, peer review and revision to the right workflow in the ARS suite.

    12k GitHub stars~12k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed

  • Paper Research on arXiv

    XiaomiMiMo/MiMo-Code

    Searches arXiv, fetches metadata, generates BibTeX, downloads PDFs and finds citations and related papers using a bundled Python script.

    14k GitHub stars~1.5k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

  • Deep Research Agent Team

    Imbad0202/academic-research-skills

    Runs a 13-agent pipeline for rigorous academic research, from forming the question through systematic search, synthesis, bias checks and an APA 7.0 report.

    51k GitHub stars~13k tokensUpdated yesterday
    Research & ScienceAuto-check passed

More from bytedance/deer-flow

All 23 skills in this repo

  • Vercel Deploy

    bytedance/deer-flow

    Deploys a project to Vercel with one script and no login, then returns a live preview URL and a claim link for moving the deployment into your own Vercel account.

    84k GitHub starsUsed in 10 repos~797 tokens
    Auto-check passed

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check passed

  • Chart Visualization

    bytedance/deer-flow

    Picks a suitable chart type from 26 options for your data, maps the data to that chart's parameters and generates a chart image through a JavaScript script.

    84k GitHub starsUsed in 1 repo~840 tokens
    Auto-check passed

  • Excel and CSV Data Analysis

    bytedance/deer-flow

    Analyzes uploaded Excel and CSV files with SQL through DuckDB, producing schema inspections, statistical summaries and exports to CSV, JSON or Markdown.

    84k GitHub starsUsed in 4 repos~2.2k tokens
    Auto-check passed

  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    84k GitHub starsUsed in 4 repos~2.9k tokens
    Auto-check passed

  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    84k GitHub stars~2.5k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Academic Paper Review

What does Academic Paper Review do?

Produces a structured peer-review style critique of a research paper, covering methodology, contribution and how the work sits among related studies. Given a paper as an uploaded PDF or a link such as an arXiv page, the agent first records the metadata: title, authors, venue or preprint status, year, field and paper type. It then reads in a deliberate order, starting with the abstract and introduction to find the claimed contributions, followed by the related-work section to see how the authors place themselves against earlier research.

When should I use Academic Paper Review?

Academic Paper Review fits situations like: reviewing a preprint or journal submission before writing referee comments; getting an honest read on the strengths and weaknesses of a study you plan to cite; summarizing a paper's contribution and limits for a reading group.

How do I install Academic Paper Review in Claude Code?

Run `npx skills add bytedance/deer-flow --skill academic-paper-review -a claude-code`. Or copy the skill folder (skills/public/academic-paper-review in bytedance/deer-flow) into .claude/skills/academic-paper-review in your project. Claude Code loads it when a task matches its description.

How do I install Academic Paper Review in Codex?

Run `npx skills add bytedance/deer-flow --skill academic-paper-review -a codex`. Or copy the skill folder (skills/public/academic-paper-review in bytedance/deer-flow) into .agents/skills/academic-paper-review in your project. Codex loads it when a task matches its description.

Can I use Academic Paper Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bytedance/deer-flow --skill academic-paper-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/academic-paper-review, .gemini/skills/academic-paper-review, .github/skills/academic-paper-review and .opencode/skills/academic-paper-review in your project.

What does Academic Paper Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Academic Paper Review is instructions for the agent only. Our summary lists: The paper as an uploaded PDF or a reachable URL; Web search access for the literature positioning step.

Does Academic Paper Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Academic Paper Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Academic Paper Review use?

Academic Paper Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Academic Paper Review use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Academic Paper Review?

Skills that share tags, products or a category with Academic Paper Review: Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars), Academic Research Pipeline (Imbad0202/academic-research-skills, 51k stars) and Academic Research Suite for Codex (Imbad0202/academic-research-skills-codex, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Academic Paper Review?

bytedance (a GitHub organization) maintains it in bytedance/deer-flow, which has 83,674 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 11, 2026.

Source: bytedance/deer-flow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.