Communitygithub.com

pubmed-database

Fluxos de trabalho diretos de busca no PubMed e nas E-utilities do NCBI para literatura biomédica, consultas MeSH, consulta de PMIDs, recuperação de citações e monitoramento de literatura com suporte de API. Use quando uma tarefa exigir literatura biomédica do PubMed em vez de pesquisa web geral.

O que é pubmed-database?

Esta skill é projetada para agentes de IA que precisam acessar e recuperar literatura biomédica de forma eficiente e precisa a partir do banco de dados MEDLINE/PubMed, utilizando as E-utilities do NCBI. Ela define quando usar consultas ao PubMed em vez de busca web geral, orienta sobre a construção de consultas booleanas com tags de campo específicas (como [tiab], [mh], [pt]), e prioriza o uso de termos MeSH para conceitos estáveis. A skill também detalha um fluxo de trabalho completo com as E-utilities (esearch, esummary, efetch, elink), incluindo exemplos de código Python com boas práticas para lidar com chaves de API e limites de taxa. Além disso, enfatiza a disciplina de resultados, sugerindo a criação de logs reprodutíveis, e fornece uma lista de verificação para garantir que as consultas sejam válidas, éticas e reproduzíveis. É compatível com agentes que podem executar código Python ou fazer chamadas HTTP diretas.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/scientific-db-pubmed-database

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

Banco de Dados PubMed

Use esta skill quando uma tarefa precisar de literatura biomédica do PubMed em vez de pesquisa web geral.

Quando Usar

  • Pesquisar na MEDLINE ou em literatura de ciências da vida.
  • Construir consultas PubMed com termos MeSH, tags de campo, datas ou tipos de artigo.
  • Consultar PMIDs, resumos, metadados de publicação ou citações relacionadas.
  • Executar passes de busca de revisão sistemática que precisem de strings de busca reproduzíveis.
  • Usar as E-utilities do NCBI diretamente do Python, shell ou outro cliente HTTP.

Construção de Consultas

Comece com a pergunta de pesquisa, divida-a em conceitos e, em seguida, combine os conceitos com operadores booleanos.

concept_1 AND concept_2 AND filter
synonym_a OR synonym_b
NOT exclusion_term

Tags de campo úteis do PubMed:

  • [ti]: título
  • [ab]: resumo
  • [tiab]: título ou resumo
  • [au]: autor
  • [ta]: abreviação do título do periódico
  • [mh]: termo MeSH
  • [majr]: principal tópico MeSH
  • [pt]: tipo de publicação
  • [dp]: data de publicação
  • [la]: idioma

Exemplos:

diabetes mellitus[mh] AND treatment[tiab] AND systematic review[pt] AND 2023:2026[dp]
(metformin[nm] OR insulin[nm]) AND diabetes mellitus, type 2[mh] AND randomized controlled trial[pt]
smith ja[au] AND cancer[tiab] AND 2026[dp] AND english[la]

MeSH e Subcabeçalhos

Prefira MeSH quando o conceito tiver um termo de vocabulário controlado estável. Combine MeSH com termos de título/resumo quando o tópico for novo ou a terminologia variar.

A sintaxe correta do subcabeçalho coloca o subcabeçalho antes da tag de campo:

diabetes mellitus, type 2/drug therapy[mh]
cardiovascular diseases/prevention & control[mh]

Use [majr] apenas quando o tópico deve ser central para o artigo. Pode melhorar a precisão, mas pode perder trabalhos relevantes.

Filtros

Tipos de publicação:

  • clinical trial[pt]
  • meta-analysis[pt]
  • randomized controlled trial[pt]
  • review[pt]
  • systematic review[pt]
  • guideline[pt]

Filtros de data:

2026[dp]
2020:2026[dp]
2026/03/15[dp]

Filtros de disponibilidade:

free full text[sb]
hasabstract[text]

Fluxo de Trabalho das E-utilities

As E-utilities do NCBI suportam fluxos de trabalho de API reproduzíveis:

  1. esearch.fcgi: pesquisar e retornar PMIDs.
  2. esummary.fcgi: retornar metadados leves do artigo.
  3. efetch.fcgi: buscar resumos ou registros completos em XML, MEDLINE ou texto.
  4. elink.fcgi: encontrar artigos relacionados e recursos vinculados.

Use um email e chave de API para scripts de produção. Armazene chaves de API em variáveis de ambiente, nunca em arquivos versionados ou histórico de comandos.

import os
import time
import requests

BASE = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"


def esearch(query: str, retmax: int = 20) -> list[str]:
    params = {
        "db": "pubmed",
        "term": query,
        "retmode": "json",
        "retmax": retmax,
        "tool": "ecc-pubmed-search",
        "email": os.environ.get("NCBI_EMAIL", ""),
    }
    api_key = os.environ.get("NCBI_API_KEY")
    if api_key:
        params["api_key"] = api_key

    response = requests.get(f"{BASE}/esearch.fcgi", params=params, timeout=30)
    response.raise_for_status()
    time.sleep(0.35)
    return response.json()["esearchresult"]["idlist"]


pmids = esearch("hypertension[mh] AND randomized controlled trial[pt] AND 2024:2026[dp]")
print(pmids)

Para lotes, prefira parâmetros do servidor de histórico do NCBI (usehistory=y, WebEnv, query_key) em vez de passar listas muito longas de PMIDs por URLs.

Disciplina de Resultados

Para cada passe de busca, registre:

  • string de busca exata
  • banco de dados pesquisado
  • data da pesquisa
  • filtros usados
  • contagem de resultados
  • formato de exportação
  • quaisquer exclusões manuais

Exemplo:

| Database | Date searched | Query | Filters | Results |
| --- | --- | --- | --- | ---: |
| PubMed | 2026-05-11 | `sickle cell disease[mh] AND CRISPR[tiab]` | 2020:2026[dp], English | 42 |

Lista de Verificação

  • As tags de campo são tags válidas do PubMed?
  • Os termos MeSH estão emparelhados com sinônimos de texto livre para tópicos mais recentes?
  • O intervalo de datas é explícito e apropriado?
  • O log da busca inclui detalhes suficientes para reproduzir a consulta?
  • As chaves de API são carregadas do ambiente?
  • O código HTTP chama raise_for_status() ou trata de outra forma respostas não-200 antes de analisar?
  • Os limites de taxa são respeitados?

Referências

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Habilidades Relacionadas