Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search PubMed for scientific literature. Use when the user asks to find papers, search literature, look up research, find publications, or asks about recent studies. Triggers on "pubmed", "papers", "literature", "publications", "research on", "studies about".
.claude/skills/pubmed-search/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-22 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-16 | ✗→✓ | ▲ Improved | — | — |
Search NCBI PubMed for scientific literature using BioPython's Entrez module.
pythonfrom Bio import Entrez Entrez.email = "medclaw@freedomai.com"
python# Search handle = Entrez.esearch(db="pubmed", term="CRISPR delivery methods", retmax=20, sort="date") record = Entrez.read(handle) handle.close() id_list = record["IdList"] print(f"Found {record['Count']} results, showing top {len(id_list)}")
python# Fetch details handle = Entrez.efetch(db="pubmed", id=id_list, rettype="xml") records = Entrez.read(handle) handle.close() for article in records['PubmedArticle']: medline = article['MedlineCitation'] pmid = str(medline['PMID']) title = medline['Article']['ArticleTitle'] # Get authors authors = medline['Article'].get('AuthorList', []) first_author = f"{authors[0].get('LastName', '')} {authors[0].get('Initials', '')}" if authors else "Unknown" # Get journal and year journal = medline['Article']['Journal']['Title'] pub_date = medline['Article']['Journal']['JournalIssue'].get('PubDate', {}) year = pub_date.get('Year', 'N/A') # Get abstract abstract_parts = medline['Article'].get('Abstract', {}).get('AbstractText', []) abstract = ' '.join(str(a) for a in abstract_parts)[:300] print(f"PMID: {pmid}") print(f"Title: {title}") print(f"Authors: {first_author} et al.") print(f"Journal: {journal} ({year})") print(f"Abstract: {abstract}...") print(f"Link: https://pubmed.ncbi.nlm.nih.gov/{pmid}/") print()
*PubMed Search: "CRISPR delivery methods"*
_Found 1,234 results. Top 5:_
*1.* Lipid nanoparticle-mediated CRISPR delivery...
_Smith J et al. — Nature (2026)_
PMID: 12345678
pubmed.ncbi.nlm.nih.gov/12345678
*2.* AAV-based CRISPR therapeutics: advances and challenges
_Chen L et al. — Cell (2026)_
PMID: 12345679
pubmed.ncbi.nlm.nih.gov/12345679Support these query patterns:
"CRISPR"[Title] AND "delivery"[Title] — title-specific"2026"[Date - Publication] — date filter"Nature"[Journal] — journal filterreview[Publication Type] — type filterAfter showing results, suggest:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 20 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +32 percentage points is the difference between those two pass rates over the 20 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.