literature-review · collaborative-deep-research — Claude Code skill: systematic literature review
Runs a systematic literature review on an academic topic: searches papers, triages results, reads key works and writes a themed report.
npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a claude-codeWhat literature-review does
The skill drives a full review cycle through the paper and paper-search CLI tools. It first pins down topic boundaries, a year range and a target paper count, then searches Semantic Scholar and Google Scholar with several query variations and deduplicates by title or paper ID.
Results get sorted into three relevance buckets. For the most relevant papers the skill reads introduction, method, results and conclusion separately, keeping structured notes on problem, method, findings and limitations. From seminal papers it walks the citation graph in both directions to catch related work.
The output is a report organised by theme rather than by paper: field overview, method comparisons, open questions, a reference list with paper IDs and BibTeX entries. You need paper and paper-search installed, plus Bash, Read, Glob, Grep and Write among allowed tools. The skill defaults to the last 5 years and 15-20 papers, so set both explicitly when the topic is narrow.
What it helps with
- build a field overview from scratch
- filter irrelevant papers out of search results
- compare methods across papers
- trace related work through the citation graph
- export BibTeX for every cited paper
Example prompts for the agent
- Run a systematic literature review on graph neural networks for drug discovery
- Do a literature review on quantum computing over the last 5 years
- Put together a survey of model compression methods, 20 papers
How to install literature-review
1Skills CLI (Vercel)
npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a claude-code2Manually: put the files in place
~/.claude/skills/literature-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/literature-review/
1Skills CLI (Vercel)
npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a codex2Manually: put the files in place
.agents/skills/literature-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a cursor2Manually: put the files in place
.cursor/skills/literature-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install collaborative-deep-research/agent-papers-cli literature-review2Manually: put the files in place
.github/skills/literature-review/SKILL.md1Skills CLI (Vercel)
npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/collaborative-deep-research/agent-papers-cli --path .claude/skills/literature-reviewManually: put the files in place
.devin/skills/literature-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about literature-review
How do I install literature-review in Claude?
Run npx skills add collaborative-deep-research/agent-papers-cli --skill literature-review -a claude-code. The skill then lands in ~/.claude/skills/literature-review/SKILL.md.
What does literature-review do?
It conducts a systematic review of an academic topic: searches papers, triages them, reads the key works and produces a themed report with BibTeX.
What tools does the skill need?
The paper and paper-search CLI tools, plus access to Bash, Read, Glob, Grep and Write.
Source text
SKILL.md · Apache-2.0
--- name: literature-review description: Conduct a systematic literature review on an academic topic. Use when the user asks for a literature review, survey, or systematic overview of a research area. argument-hint: [topic] allowed-tools: Bash, Read, Glob, Grep, Write --- 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.
© collaborative-deep-research · Apache-2.0 · collaborative-deep-research/agent-papers-cli
Similar skills
Everything for Science and research →literature-review by other authors comes first.