Systematic Literature Review
Run a reproducible systematic literature review on arXiv with APA citations, thematic synthesis, and a dated markdown report for research-heavy builds.
Overview
Systematic Literature Review is an agent skill most often used in Idea (also Validate scope, Build docs) that searches arXiv, synthesizes papers into themed APA reports, and saves a dated SLR markdown file for solo build
Install
npx skills add https://github.com/bytedance/deer-flow --skill systematic-literature-reviewWhat is this skill?
- arXiv search via arxiv_search.py with short keyword queries, category filters (e.g. cs.CV), and relevance sort—single se
- Metadata extraction delegated to subagents via the task tool, not inline one-off scripts
- APA report from templates/apa.md with Executive Summary, themes, Convergences and Disagreements, Gaps and Open Questions
- Output saved to /mnt/user-data/outputs/ as slr-<topic-slug>-<YYYYMMDD>.md and exposed with present_files
- Eval-driven workflow: ~10 papers, thematic synthesis across at least 3 themes
- Eval fixture targets ~10 papers with at least 3 thematic synthesis buckets
- Report filename pattern slr-<topic-slug>-<YYYYMMDD>.md under default outputs
Adoption & trust: 871 installs on skills.sh; 70.7k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need credible, cited background on a technical topic but lack time to manually search arXiv, extract metadata, and write a structured synthesis.
Who is it for?
Indie builders or ML-curious solos scoping a niche (agents, CV, LLMs) who want arXiv-grounded synthesis in one agent session.
Skip if: Teams needing PRISMA-compliant clinical reviews, paywalled journal corpora only, or production RAG without human verification of claims.
When should I use this skill?
User asks for a systematic literature review on arXiv with APA format, thematic synthesis, and a saved markdown report.
What do I get? / Deliverables
You get an APA-formatted SLR report with thematic analysis and gaps saved under the default outputs path, ready to inform specs or next research skills.
- Dated SLR markdown report with APA citations and per-paper annotations
- Thematic synthesis with convergences, disagreements, and open questions
- User-visible file via present_files after save
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Literature reviews belong on the Idea shelf because builders use them to discover prior work, map themes, and justify direction before committing to a product or model choice. The `research` subphase is where arXiv search, paper shortlisting, and synthesis outputs belong—not prototyping or shipping.
Where it fits
Map diffusion-model papers in cs.CV for the last two years before picking a fine-tuning approach.
Use convergences and gaps from the SLR to decide which features are table stakes versus experiments.
Drop the Executive Summary and Gaps sections into an architecture README with APA references.
How it compares
Use instead of ad-hoc “summarize these PDFs” chat when you need one search discipline, APA structure, and a fixed SLR filename.
Common Questions / FAQ
Who is systematic-literature-review for?
Solo and indie builders, side-project researchers, and agent users who want structured arXiv literature reviews with APA citations before they design or ship.
When should I use systematic-literature-review?
During Idea research to map a field; during Validate scope to evidence feature choices; during Build docs when you need a cited background section for README or architecture notes.
Is systematic-literature-review safe to install?
It runs search scripts and may delegate network-backed subagent work—review the Security Audits panel on this page and inspect arxiv_search.py and output paths before trusting in sensitive environments.
SKILL.md
READMESKILL.md - Systematic Literature Review
{ "skill_name": "systematic-literature-review", "evals": [ { "id": 1, "prompt": "Do a systematic literature review on diffusion models in computer vision. 10 papers, last 2 years, category cs.CV, APA format. Save to default output location.", "expected_output": "A structured SLR report saved to /mnt/user-data/outputs/ with APA citations, thematic synthesis across 10 papers, and per-paper annotations.", "expectations": [ "The skill read SKILL.md for systematic-literature-review", "The arxiv_search.py script was called with a short keyword query (2-3 words), not the full topic description", "The search used --category cs.CV", "The search used --sort-by relevance, not submittedDate", "The search was executed only once without retries", "Metadata extraction was delegated via the task tool to subagents, not done inline or via python -c", "The APA template file (templates/apa.md) was read", "The final report was saved to /mnt/user-data/outputs/ with a filename matching slr-<topic-slug>-<YYYYMMDD>.md", "The present_files tool was called to make the report visible to the user", "The report contains an Executive Summary section", "The report identifies at least 3 themes with cross-paper analysis", "The report contains a Convergences and Disagreements section", "The report contains a Gaps and Open Questions section", "The report contains per-paper annotations for each of the 10 papers", "The references section uses APA 7th format with arXiv URLs" ] }, { "id": 2, "prompt": "Survey recent papers on graph neural networks for drug discovery. 5 papers, BibTeX format.", "expected_output": "A structured SLR report with BibTeX citations using @misc entries for arXiv preprints.", "expectations": [ "The skill read SKILL.md for systematic-literature-review", "The arxiv_search.py script was called with a short keyword query", "Metadata extraction was delegated via the task tool to subagents", "The BibTeX template file (templates/bibtex.md) was read, not apa.md or ieee.md", "The final report was saved to /mnt/user-data/outputs/", "The present_files tool was called", "The report contains BibTeX entries using @misc, not @article", "Each BibTeX entry includes eprint and primaryClass fields", "The report contains thematic synthesis, not just a list of papers" ] }, { "id": 3, "prompt": "Review the literature on retrieval-augmented generation — key findings, limitations, and open questions. 15 papers, IEEE format.", "expected_output": "A structured SLR report with IEEE numeric citations and 15 papers extracted in parallel batches.", "expectations": [ "The skill read SKILL.md for systematic-literature-review", "The arxiv_search.py script was called with --max-results 15 or higher", "Metadata extraction used the task tool with multiple subagent batches (15 papers requires 3 batches of 5)", "The IEEE template file (templates/ieee.md) was read", "The report uses IEEE numeric citations [1], [2], etc. in the text", "The references section uses IEEE format with numbered entries", "The report contains per-paper annotations for all papers", "The report identifies themes across the papers" ] }, { "id": 4, "prompt": "Review this paper: https://arxiv.org/abs/2310.06825", "expected_output": "The SLR skill should NOT be triggered. The request should route to academic-paper-review instead.", "expectations": [ "The systematic-literature-review skill was NOT triggered", "The agent did not call arxiv_search.py", "The agent recognized this as a single-paper review request" ] }, { "id": 5, "prompt": "What does the literature say ab