How do I install the Efetch skill?

Run npx skillmds@latest add vimalinx/efetch in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Efetch safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Efetch?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Efetch free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Efetch?

vimalinx (@vimalinx) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Efetch by vimalinx — Agent Skill

Name: Efetch
Rating: 4.2 (5 reviews)
Author: vimalinx

File contents

efetch

Quick Start

Command: efetch
Local executable: /home/vimalinx/miniforge3/envs/bio/bin/efetch
Full reference: references/help.md

When To Use This Tool

Retrieve full records or sequence data after esearch or epost.
Fetch records by ID or accession from PubMed, Nucleotide, Protein, Gene, SRA, Assembly, and related databases.
Export in FASTA, abstract, docsum, XML, JSON, or native record formats.
Pull sequence subranges when you only need a locus, not the entire accession.

Common Patterns

# 1) Fetch PubMed abstracts from a search result
esearch -db pubmed -query 'ebola virus[Title/Abstract]' | efetch -format abstract

# 2) Fetch a nucleotide record in FASTA
efetch -db nucleotide -id NM_000546.6 -format fasta

# 3) Fetch only a sequence subrange
efetch \
  -db nucleotide \
  -id NC_000001.11 \
  -format fasta \
  -seq_start 100000 \
  -seq_stop 101000

# 4) Fetch summaries in JSON-compatible mode
efetch -db assembly -id GCF_000001405.40 -format docsum -mode json

Recommended Workflow

Get stable IDs first with esearch or epost.
Choose -format deliberately, because downstream parsing depends on it.
Save raw outputs for reproducibility when the fetched record is part of an analysis result.
Pipe XML-style outputs into xtract only after verifying the record shape.

Guardrails

Always specify -db and usually specify -format; implicit defaults are easy to misread.
Large fetches should be chunked with -start and -stop, or handled through batched EDirect pipelines.
-seq_start, -seq_stop, and strand options only apply to sequence-style retrieval.
Invalid or mismatched IDs often yield empty output, so validate the upstream search first.

---name: efetchdescription: Use when you need to fetch records or data from NCBI Entrez databases (PubMed, nucleotide, protein, gene, SRA, etc.) by ID or accession---# efetch## Quick Start- **Command:** `efetch`- **Local executable:** `/home/vimalinx/miniforge3/envs/bio/bin/efetch`- **Full reference:** [references/help.md](references/help.md)## When To Use This Tool- Retrieve full records or sequence data after `esearch` or `epost`.- Fetch records by ID or accession from PubMed, Nucleotide, Protein, Gene, SRA, Assembly, and related databases.- Export in FASTA, abstract, docsum, XML, JSON, or native record formats.- Pull sequence subranges when you only need a locus, not the entire accession.## Common Patterns```bash# 1) Fetch PubMed abstracts from a search resultesearch -db pubmed -query 'ebola virus[Title/Abstract]' | efetch -format abstract``````bash# 2) Fetch a nucleotide record in FASTAefetch -db nucleotide -id NM_000546.6 -format fasta``````bash# 3) Fetch only a sequence subrangeefetch \ -db nucleotide \ -id NC_000001.11 \ -format fasta \ -seq_start 100000 \ -seq_stop 101000``````bash# 4) Fetch summaries in JSON-compatible modeefetch -db assembly -id GCF_000001405.40 -format docsum -mode json```## Recommended Workflow1. Get stable IDs first with `esearch` or `epost`.2. Choose `-format` deliberately, because downstream parsing depends on it.3. Save raw outputs for reproducibility when the fetched record is part of an analysis result.4. Pipe XML-style outputs into `xtract` only after verifying the record shape.## Guardrails- Always specify `-db` and usually specify `-format`; implicit defaults are easy to misread.- Large fetches should be chunked with `-start` and `-stop`, or handled through batched EDirect pipelines.- `-seq_start`, `-seq_stop`, and strand options only apply to sequence-style retrieval.- Invalid or mismatched IDs often yield empty output, so validate the upstream search first.

Frequently asked questions

Efetch