msa-search-nim — Claude Code skill: what it does, how to install
This skill guides protein-sequence searches and multiple sequence alignment with ColabFold MSA-Search NIM. Use it for homolog searches or paired alignments for complexes.
no license ★ 4,106 updated 2026-10-23
npx skills add NVIDIA/skills --skill msa-search-nim -a claude-codeWhat msa-search-nim does
The skill guides an agent through ColabFold MSA-Search NIM requests. It covers choosing the hosted NVIDIA API or local Docker deployment, standard and paired MSA searches, and structural-template searches with PDB70. Alignment output can be requested as A3M or FASTA. For template searches, use local Docker: validation of the hosted template route returned HTTP 404.
Local deployment needs a GPU. The guide describes downloading databases with aria2c, mounting them in the container, setting NIM_MODEL_NAME, and checking that the service is ready. Registry access and the initial model download require NGC_API_KEY or NVIDIA_API_KEY; parallel database downloads require aria2c. Without a GPU, the local NIM cannot run.
Hosted requests use NGC_API_KEY for authorization. Once the local server is ready, inference requests need no authorization header. The skill also points to material on API details, parameters, validation, and request examples.
What it helps with
- search for homologs of a protein sequence
- create an MSA in A3M or FASTA format
- build a paired alignment for a complex
- find structural templates with PDB70
Example prompts for the agent
- Find homologs for this protein sequence with ColabFold MSA-Search NIM and return an A3M alignment.
- Create a paired MSA for these protein chains using the hosted NVIDIA API.
- Prepare a local MSA-Search NIM launch with the UniRef30 database, using
aria2candNIM_MODEL_NAME.
How to install msa-search-nim
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill msa-search-nim -a claude-code2Manually: put the files in place
~/.claude/skills/bionemo-msa-search-nim/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/bionemo-msa-search-nim/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill msa-search-nim -a codex2Manually: put the files in place
.agents/skills/bionemo-msa-search-nim/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill msa-search-nim -a cursor2Manually: put the files in place
.cursor/skills/bionemo-msa-search-nim/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills skills/bionemo-msa-search-nim2Manually: put the files in place
.github/skills/bionemo-msa-search-nim/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill msa-search-nim -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/bionemo-msa-search-nimManually: put the files in place
.devin/skills/bionemo-msa-search-nim/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about msa-search-nim
How do I install msa-search-nim in Claude Code?
Run npx skills add NVIDIA/skills --skill bionemo-msa-search-nim -a claude-code. The skill file is placed at ~/.claude/skills/bionemo-msa-search-nim/SKILL.md.
What does msa-search-nim do?
It guides requests to ColabFold MSA-Search NIM for protein multiple sequence alignments, including paired searches for complexes. It also covers template search and local Docker deployment.
What is needed to run msa-search-nim locally?
Local deployment needs a GPU and NGC_API_KEY or NVIDIA_API_KEY for registry access and the initial model download. The documented parallel database download uses aria2c.