# lamindb

Keeps a LaminDB registry of biological datasets and models: artifact registration, schemas, Bionty annotation, metadata search.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1900 installs · ★ 54789
- Author: K-Dense-AI
- License: LicenseRef-Apache-2.0-license · policy=link-only · description only; the file stays with the author
- Source: https://github.com/K-Dense-AI/scientific-agent-skills/tree/HEAD/skills/lamindb/SKILL.md
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/skills/lamindb

## What it does

The skill gives your agent a working procedure for LaminDB 2.10.0 and Bionty 2.5.0. It defines typed `Feature` records, builds a `Schema` from them, runs `curator.validate()` on a table and saves the result as an artifact. Collections, branches, spaces and run lineage are covered too, so you can see which inputs and outputs a script left behind.

A good part of it is a list of traps. `Artifact.backed()`, `delete_cache()` and `is_cached()` do not exist in this release. An `open()` call on Parquet hands back a PyArrow dataset rather than a byte stream, and `curator.cat.add_ontology()` is gone — set the field's Bionty dtype and call `cat.standardize()` instead. For AnnData the path is `curator.slots["obs"].cat`.

You need Python 3.10–3.14 and `lamindb` itself; the examples were run on Python 3.12. A local SQLite instance needs no login. Public ontologies and remote storage need network access, and private instances need credentials. Registering an artifact says nothing about whether the science holds up — assay-specific checks are yours to write.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill lamindb -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill lamindb -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill lamindb -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install K-Dense-AI/scientific-agent-skills lamindb
```

2. **Manually: put the files in place**
- File: `.github/skills/lamindb/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill lamindb -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/K-Dense-AI/scientific-agent-skills --path skills/lamindb
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add K-Dense-AI/scientific-agent-skills --skill lamindb -a opencode
```

### 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/K-Dense-AI/scientific-agent-skills/tree/HEAD/skills/lamindb/SKILL.md

## When to use it
- register a dataset and keep its version straight
- validate a metadata table against a schema before publishing
- map columns onto an ontology with Bionty
- find an artifact by metadata without loading it
- trace which inputs and outputs a run produced

## Example prompts
- Define a schema for the QC metadata table and validate it with `curator.validate()`
- Standardize the `cell_type` column against a Bionty ontology and keep unresolved values as they are
- Find every artifact using that schema and list their UIDs

## Similar
- [scvi-tools](https://affpapa.org/en/nevibecode/skills/scvi-tools.md) — skill · 2400 installs
- [opentargets-database](https://affpapa.org/en/nevibecode/skills/opentargets-database.md) — skill · 2200 installs
- [ensembl-database](https://affpapa.org/en/nevibecode/skills/ensembl-database.md) — skill · 2200 installs
- [exploratory-data-analysis](https://affpapa.org/en/nevibecode/skills/exploratory-data-analysis.md) — skill · 279 installs
- [ukb-topmed-phewas-skill](https://affpapa.org/en/nevibecode/skills/ukb-topmed-phewas-skill.md) — skill · 13 installs
- [epigraphdb-skill](https://affpapa.org/en/nevibecode/skills/epigraphdb-skill.md) — skill · 13 installs

From the same set: [k-dense-ai/scientific-agent-skills](https://affpapa.org/en/nevibecode/by/k-dense-ai/scientific-agent-skills.md) — 159 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