Run systematic literature reviews from a research question
Web page · https://agentusecases.ai/use-case/run-systematic-literature-reviews-from-a-research-question
Done with Claude Code. A physician-researcher built Claude Code skills that search databases, screen articles, chase citations, fetch PDFs and write the synthesis.
First seen by Oriel on .
AI summary
A physician-researcher’s Claude Code workflow automates systematic literature reviews from PICO formulation through database searching, screening, citation chasing, PDF collection, quality appraisal, and synthesis.
- The Python-backed skills query PubMed, OpenAlex, and Semantic Scholar, deduplicate results, screen abstracts twice, follow citations, and download open-access PDFs.
- The agent pauses at six checkpoints for user approval, while users must manually obtain paywalled PDFs; the manual PDF step assumes macOS.
- A worked congestive heart failure care-transitions review includes the complete output package, but the source reports no timing or accuracy measurements.
- Reviews typically require about 4–6 sessions, and users are advised to obtain a free Semantic Scholar key because shared access is often rate-limited.
- The workflow includes instructions for producing included-study lists, findings summaries, and exclusion logs, with a disclaimer to verify all outputs.
#claude code #systematic reviews #literature search #research automation
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Agent Use Cases | https://agentusecases.ai/use-case/run-systematic-literature-reviews-from-a-research-question | https://agentusecases.ai/use-case/run-systematic-literature-reviews-from-a-research-question Read discussion |