ncbi-datasets-skill — Codex skill: what it does, how to install
Queries NCBI Datasets v2 for genome, assembly, and taxonomy metadata. It produces compact summaries directly in Codex without large raw dumps.
npx skills add openai/plugins --skill ncbi-datasets-skill -a codexWhat ncbi-datasets-skill does
The skill pipes a JSON payload via stdin into scripts/ncbi_datasets.py. This script calls NCBI Datasets v2 endpoints for genome records, assembly reports, or taxonomy trees. By default, the tool outputs a brief markdown summary. It keeps conversation context light.
Execution requires Python in your environment. You must provide a relative path key, while fields like params or max_items filter the result. If machine-readable output is required, passing save_raw=true writes the full response to raw_output_path.
Install this skill if your workflow involves frequent lookups of NCBI metadata. Skip it if you need bulk sequence downloads.
What it helps with
- pull concise genome assembly summaries from NCBI Datasets v2
- query taxonomy metadata by taxon identifier
- save complete raw JSON responses to disk via file path
- look up dataset reports by assembly accession code
Example prompts for the agent
- Look up taxonomy metadata for taxon 9606 using ncbi-datasets-skill
- Get the dataset report for assembly GCF_000001405.40 and show a brief summary
- Fetch genome reports for taxon 9606 and save the raw JSON to disk
How to install ncbi-datasets-skill
1Skills CLI (Vercel)
npx skills add openai/plugins --skill ncbi-datasets-skill -a codex2Manually: put the files in place
.agents/skills/ncbi-datasets-skill/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add openai/plugins --skill ncbi-datasets-skill -a claude-code2Manually: put the files in place
~/.claude/skills/ncbi-datasets-skill/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ncbi-datasets-skill/
Manually: put the files in place
.cursor/skills/ncbi-datasets-skill/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install openai/plugins ncbi-datasets-skill2Manually: put the files in place
.github/skills/ncbi-datasets-skill/SKILL.mdPlatform CLI
gemini skills install https://github.com/openai/plugins --path plugins/life-science-research/skills/ncbi-datasets-skillManually: put the files in place
.devin/skills/ncbi-datasets-skill/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set201
The whole set →Similar
Questions about ncbi-datasets-skill
How to install ncbi-datasets-skill in Codex?
Run npx skills add openai/plugins --skill ncbi-datasets-skill in your terminal. Codex will detect the skill configuration in your workspace.
What does ncbi-datasets-skill do?
It queries NCBI Datasets v2 REST endpoints via a bundled Python script. The skill returns compact summaries for assemblies, genomes, and taxonomy into chat.
How to get raw JSON instead of a short summary?
Ask Codex to save the raw payload by enabling save_raw=true. The script writes the full response to raw_output_path.
