Literature Review
Run a systematic academic literature review on a topic using paper and paper-search CLI tools with triage and deep reads.
Overview
Literature-review is an agent skill for the Idea phase that conducts a systematic literature review on an academic topic using paper and paper-search CLI tools.
Install
npx skills add https://github.com/collaborative-deep-research/agent-papers-cli --skill literature-reviewWhat is this skill?
- 4-step workflow: define scope, multi-query search, triage, deep analysis
- Default scope: last 5 years and 15–20 core papers unless user overrides
- Multi-query Semantic Scholar search plus Google Scholar pass with deduplication
- Triage via details/skim; deep reads via outline and section reads on arXiv IDs
- Structured notes per paper: problem, method, key results (from SKILL procedure)
- 4-step review workflow: scope, search, triage, deep analysis
- Default 15–20 core papers and 5-year year range
- Multi-query search pattern across Semantic Scholar and Google Scholar
Adoption & trust: 562 installs on skills.sh; 44 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You need a credible map of recent research on a topic but ad-hoc Googling misses papers, duplicates hits, and skips structured comparison.
Who is it for?
Indie builders validating technical novelty or writing background sections before prototyping.
Skip if: Market sizing or competitor landing-page research with no academic sources, or reviews when paper CLI tools are unavailable.
When should I use this skill?
User asks for a literature review, survey, or systematic overview of a research area (optional topic via argument-hint).
What do I get? / Deliverables
You get a scoped, deduplicated set of highly relevant papers with structured notes from deep section reads, ready to inform specs or experiments.
- Deduped corpus with relevance tiers
- Structured per-paper notes (problem, method, results)
- Synthesized literature review document
Recommended Skills
Journey fit
Literature reviews happen when you are still exploring what is known—before you commit build scope or validation experiments. Systematic search, triage, and note-taking on papers is core Idea-phase research, not shipping or distribution work.
How it compares
Use this systematic CLI workflow instead of one-shot 'summarize papers on X' prompts without search deduplication and triage.
Common Questions / FAQ
Who is literature-review for?
Solo builders and researchers using Claude Code–class agents who want reproducible academic surveys via the agent-papers CLI stack.
When should I use literature-review?
In Idea research when you need a literature review, survey, or systematic overview—especially before Validate scoping or Build architecture choices.
Is literature-review safe to install?
Review the Security Audits panel on this Prism page; the skill runs Bash and network-backed paper searches—confirm you trust the CLI and API usage.
SKILL.md
READMESKILL.md - Literature Review
Conduct a systematic literature review on "$ARGUMENTS" using the `paper` and `paper-search` CLI tools. ## 1. Define Scope Before searching, clarify with the user: - Topic boundaries and key terms - Year range (default: last 5 years) - Target venues or communities (if any) - Desired number of papers (default: 15-20 core papers) ## 2. Multi-Query Search Search with multiple query variations to maximize coverage: ``` paper-search semanticscholar papers "<main query>" --limit 20 --year <range> paper-search semanticscholar papers "<synonym query>" --limit 20 --year <range> paper-search semanticscholar papers "<related query>" --limit 20 --year <range> paper-search google scholar "<topic>" ``` Deduplicate results by title/paper ID. ## 3. Triage For each unique paper found: ``` paper-search semanticscholar details <paper_id> paper skim <arxiv_id> --lines 2 ``` Categorize as: **highly relevant** / **somewhat relevant** / **not relevant**. ## 4. Deep Analysis For highly relevant papers: ``` paper outline <arxiv_id> paper read <arxiv_id> introduction paper read <arxiv_id> method paper read <arxiv_id> results paper read <arxiv_id> conclusion ``` Take structured notes on each paper: problem, method, key results, limitations. ## 5. Citation Graph Exploration For seminal papers, find related work: ``` paper-search semanticscholar citations <paper_id> --limit 20 paper-search semanticscholar references <paper_id> --limit 20 ``` Add any important papers discovered this way back to the triage step. ## 6. Produce Report Organize findings **by theme, not by paper**. Include: - Overview of the field and its evolution - Key methods and approaches (with comparisons) - Main results and findings - Open questions and future directions - Complete reference list with paper IDs and URLs - BibTeX entries for all cited papers (use `paper bibtex <arxiv_id>` to generate) ## Guidelines - Aim for breadth first: cover all major approaches before going deep on any one. - Note citation counts and venues to gauge paper impact. - Flag contradictory findings explicitly. - Distinguish between empirical results and theoretical claims.