pubmed-search-agent: Skill for Claude Code

.claude/skills/pubmed-search/SKILL.md

pubmed-search is a skill for Claude Code from Dariolex/pubmed-search-agent. It costs 92 tokens per session (2,538 once invoked), scanned A, original, MIT.

A guide for searching PubMed, a database of medical and scientific research, from a request written in everyday language.

In plain words
What is it for?
Use it to search for studies, clinical trials, articles, or other medical literature on PubMed.
Why use it?
It translates the request into a structured search and filters results so relevant studies are easier to find.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Dariolex/pubmed-search-agent's own configuration. It tells Claude Code how to work on pubmed-search-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pubmed-search-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Dariolex/pubmed-search-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Dariolex/pubmed-search-agent/master/.claude/skills/pubmed-search/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Dariolex/pubmed-search-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pubmed-search

README.md
[![agentmods](https://agentmods.dev/badge/skills/dariolex/pubmed-search-agent/pubmed-search/github.svg)](https://agentmods.dev/skills/dariolex/pubmed-search-agent/pubmed-search)
Your own site
<a href="https://agentmods.dev/skills/dariolex/pubmed-search-agent/pubmed-search"><img src="https://agentmods.dev/badge/skills/dariolex/pubmed-search-agent/pubmed-search/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pubmed-search

Your own site · 80×15
<a href="https://agentmods.dev/skills/dariolex/pubmed-search-agent/pubmed-search"><img src="https://agentmods.dev/badge/skills/dariolex/pubmed-search-agent/pubmed-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.02538
Opus 5.5 $0.00037 $0.01015
Sonnet 5.5 $0.00018 $0.00508
Haiku 4.5 $0.00009 $0.00254

Measured 2mo ago against content hash c061246b48bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pubmed-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pubmed-search/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trasforma una richiesta in linguaggio naturale in una ricerca PubMed reale, poi filtra i risultati per pertinenza rispetto all'intento dell'utente.

Eseguire i comandi Python dalla radice del progetto (dove c'è pytest.ini), con src sul PYTHONPATH — es. PYTHONPATH=src python -m nl_query_translator .... Serve un file .env valido con NCBI_API_KEY, NCBI_TOOL_NAME, NCBI_EMAIL.

Flusso

1. Estrai il JSON intermedio dalla richiesta

Analizza la richiesta NL e costruisci questo JSON (schema esteso con provenienza):

{
  "intento_originale": "<la richiesta dell'utente, verbatim>",
  "concetti": [
    {"termine": "<concetto>", "sinonimi": ["<variante>"], "mesh": "<termine MeSH o null>", "provenienza": "<perché estratto>"}
  ],
  "operatore_tra_concetti": "AND",
  "esclusioni": [{"termine": "<da escludere>", "campo": "pt", "provenienza": "<perché>"}],
  "filtri": {
    "date": {"da": "<anno>", "a": "<anno>", "tipo": "dp"},
    "tipi_studio": ["<publication type>"],
    "lingua": "<lingua o null>",
    "brevetto": true
  }
}

Linee guida per l'estrazione:

  • Concetti: i nuclei clinici/scientifici della richiesta. Aggiungi sinonimi utili (varianti terminologiche, non traduzioni). Per il campo mesh, se hai un candidato plausibile (es. melanoma), non limitarti al tuo giudizio: verificalo con il resolver (vedi sotto) prima di popolarlo nel JSON finale.
  • operatore_tra_concetti: AND di norma (l'utente vuole tutti i concetti insieme). Usa OR solo se la richiesta è esplicitamente alternativa ("melanoma o carcinoma").
  • Esclusioni: frasi come "escludendo X", "senza X", "non case report" → NOT. Per i tipi di pubblicazione usa campo: "pt"; per termini liberi ometti campo.
  • Filtri date: "ultimi 3 anni" → calcola dalla data odierna (da = anno corrente − 3, a = anno corrente). tipo: dp (data di pubblicazione) di default.
  • Tipi di studio: "trial randomizzati" → randomized controlled trial; "meta-analisi" → meta-analysis; "review" → review. Più tipi vengono uniti in OR automaticamente.
  • Lingua: solo se la richiesta la specifica ("in inglese" → english).
  • Brevetto: imposta brevetto: true quando la richiesta chiede articoli i cui autori dichiarano un brevetto ("che dichiarano un brevetto", "con brevetto registrato", "autori con brevetti"); ometti il campo (non impostarlo a false) quando non richiesto. Aggiunge AND "patent*"[cois] alla query. Attenzione: PubMed non indicizza i brevetti — il filtro cerca nel Conflict of Interest Statement, che è testo libero. Cattura quindi anche le dichiarazioni negative ("gli autori non detengono brevetti"): vanno scartate leggendo coi_statement nella fase 5.

Read the full file on GitHub · 180 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 180 lines · 92 tokens per session scan A c061246b48bc

Subscribe to this mod's changes

pubmed-search is a skill published in the GitHub repository Dariolex/pubmed-search-agent (2 stars, last pushed 3mo ago), licensed MIT. It adds 92 tokens to every session and 2,538 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

pubmed-search compared with skills from other repositories

pubmed-search next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pubmed-searchDariolex/pubmed-search-agentSkill23mo agoMITA92Claude Code
noodle-biomedical-literature-discoveryhelena-bioinformatics/noodle-mcpSkill02mo agoApache-2.0A105Codex
noodle-biomedical-literature-discovery-mcphelena-bioinformatics/noodle-mcpSkill02mo agoApache-2.0A62Claude Code
drug-discoveryNousResearch/hermes-agentSkill261kyesterdayMITA19Claude Code, Codex
detecting-pv-signalsmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A218Claude Code
structuring-radiology-reportsmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A195Claude Code
coding-icd10maziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A209Claude Code