Multi source literature brief
Skill ma-compbio-lab/SkillFoundry/skills/scientific-knowledge/multi-source-literature-brief
Use this skill to query OpenAlex, Europe PMC, Crossref, and PubMed for the same topic and build a normalized literature brief. Do not use it as a full systematic-review workflow or citation-analysis engine.From its SKILL.md
npx -y skills add ma-compbio-lab/SkillFoundry --skill multi-source-literature-briefAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.8 KB, 604 tokens by cl100k_base, as published. Nobody here has run it
Purpose
Build a compact cross-source literature brief for a query by aggregating multiple official scholarly APIs into one normalized JSON report.
When to use
- You want a quick cross-check of literature coverage across general and biomedical indexes.
- You need a reusable JSON brief before deeper paper triage or ranking.
- You want a small overlap view by DOI or title across sources.
When not to use
- You need exhaustive retrieval for a systematic review.
- You need full-text mining, citation graphs, or advanced deduplication.
- You need offline-only execution.
Inputs
- Query string
- Per-source result limit
- Optional output path
- Optional NCBI/OpenAlex etiquette fields such as
--emailor--mailto
Outputs
- JSON report with per-source counts, normalized top results, and cross-source overlap candidates
Requirements
- Python 3.10+
- Network access to OpenAlex, Europe PMC, Crossref, and NCBI E-utilities
Procedure
- Run
python3 skills/scientific-knowledge/multi-source-literature-brief/scripts/build_literature_brief.py --query "single-cell RNA-seq" --limit 2 --out skills/scientific-knowledge/multi-source-literature-brief/assets/single_cell_literature_brief.json. - Inspect the
sourcessection to compare the top normalized results from each API. - Review
overlap_summaryto see which DOI or title candidates appear in more than one source.
Validation
- The command exits successfully.
- All four source blocks are present.
- Each source returns at least one normalized result for a known query.
Failure modes and fixes
- NCBI rate limiting: rerun after a short pause or pass
--email; the wrapper already retries transient429responses. - Sparse Crossref hits: keep the query phrase concise because Crossref is title-oriented here.
- Query drift across sources: use quoted phrases or a more specific biomedical term.
Safety and limits
- This skill aggregates public bibliographic metadata only.
- It does not infer scientific truth or replace manual review.
Example
python3 skills/scientific-knowledge/multi-source-literature-brief/scripts/build_literature_brief.py --query "CRISPR screen melanoma" --limit 1
Provenance
- OpenAlex API: https://docs.openalex.org/how-to-use-the-api/api-overview
- Europe PMC RESTful Web Service: https://europepmc.org/RestfulWebService
- Crossref REST API: https://www.crossref.org/documentation/retrieve-metadata/rest-api/
- NCBI E-utilities: https://www.ncbi.nlm.nih.gov/books/NBK25501/
Related skills
openalex-literature-searcheuropepmc-method-triagecrossref-metadata-searchncbi-pubmed-search
What ships with it: 8 files
20.8 KB alongside SKILL.md, 2 of them executable
assets/
- README.md187 B
- single_cell_literature_brief.json5.0 KB
examples/
- README.md481 B
scripts/
- build_literature_brief.pyruns11.2 KB
tests/
- README.md219 B
- test_multi_source_literature_brief.pyruns2.1 KB
- metadata.yaml1.2 KB
- refs.md403 B