# msa-search-nim

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.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 4106 repo stars
- Author: NVIDIA
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NVIDIA/skills/tree/HEAD/skills/bionemo-msa-search-nim/SKILL.md
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/msa-search-nim

## What it 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.

## Requirements
- Works with: Docker

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill msa-search-nim -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/bionemo-msa-search-nim/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/bionemo-msa-search-nim/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill msa-search-nim -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/bionemo-msa-search-nim/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill msa-search-nim -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/bionemo-msa-search-nim/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NVIDIA/skills skills/bionemo-msa-search-nim
```

2. **Manually: put the files in place**
- File: `.github/skills/bionemo-msa-search-nim/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NVIDIA/skills --skill msa-search-nim -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NVIDIA/skills --path skills/bionemo-msa-search-nim
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/bionemo-msa-search-nim/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/NVIDIA/skills/tree/HEAD/skills/bionemo-msa-search-nim/SKILL.md

## When to use it
- 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
- 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 `aria2c` and `NIM_MODEL_NAME`.

## Similar
- [protein-sequence-msa](https://affpapa.org/en/nevibecode/skills/protein-sequence-msa.md) — skill · 2400 installs
- [debug-openshell-cluster](https://affpapa.org/en/nevibecode/skills/debug-openshell-cluster.md) — skill · 739 installs
- [protein-sequence-similarity-search](https://affpapa.org/en/nevibecode/skills/protein-sequence-similarity-search.md) — skill · 2400 installs
- [nvidia-speech-nim](https://affpapa.org/en/nevibecode/skills/nvidia-speech-nim.md) — skill · 132 installs
- [searxng-search](https://affpapa.org/en/nevibecode/skills/searxng-search.md) — skill · 838 installs
- [brightdata-local-search](https://affpapa.org/en/nevibecode/skills/brightdata-local-search.md) — skill · 625 installs

From the same set: [nvidia/skills](https://affpapa.org/en/nevibecode/by/nvidia/skills.md) — 312 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
