# deeplake-dataset-stinger

deeplake-dataset-stinger is a Claude Code skill that designs and checks Deep Lake schemas for Wasp Nestmind, including ColumnDef, append-only versioning, and hybrid indexing.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 96 repo stars
- Author: Legion Code Inc.
- License: AGPL-3.0-or-later · policy=link-only · description only; the file stays with the author
- Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/data-and-ai-tools/skills/deeplake-dataset-stinger/SKILL.md
- Updated: 2026-10-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/deeplake-dataset-stinger

## What it does

This skill acts as the Deep Lake architecture guide across seven domain tables: memory, sessions, skills, rules, goals, kpis, and codebase. Schemas must live strictly inside `src/deeplake-schema.ts` as `ColumnDef[]`. Blank re-adds using `ADD COLUMN IF NOT EXISTS` trigger HTTP 500 errors in Deep Lake, so the workflow forces an explicit diff against `information_schema.columns` before altering tables.

Vector columns are formatted as 768-dimensional `FLOAT4[]` embeddings for nomic-embed-text-v1.5. Instead of issuing standard `UPDATE` queries, mutable records such as rules and goals rely on an append-only version increment to bypass Deep Lake update-coalescing bugs. Dynamic SQL fragments must strictly pass through `sqlIdent` sanitization.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add legioncodeinc/vibe-coding-tools
```
In the agent chat (not a shell):
```text
/plugin install data-and-ai-tools@wasp-nest
```
This installs the whole data-and-ai-tools plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill deeplake-dataset-stinger -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill deeplake-dataset-stinger -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill deeplake-dataset-stinger -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install legioncodeinc/vibe-coding-tools plugins/data-and-ai-tools/skills/deeplake-dataset-stinger
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill deeplake-dataset-stinger -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/legioncodeinc/vibe-coding-tools --path plugins/data-and-ai-tools/skills/deeplake-dataset-stinger
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/deeplake-dataset-stinger/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/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/data-and-ai-tools/skills/deeplake-dataset-stinger/SKILL.md

## When to use it
- Define Deep Lake tables using strict ColumnDef schema arrays
- Plan additive column migrations to avoid HTTP 500 duplicate errors
- Audit vector and BM25 hybrid indexing setups
- Configure append-only version bumps instead of row UPDATEs

## Example prompts
- Review the schema modifications inside `src/deeplake-schema.ts`
- Generate an additive column migration checklist for the `sessions` table
- Run an indexing audit on our 768-dimension vector columns

## Similar
- [doc-to-vector-dataset-generator](https://affpapa.org/en/nevibecode/skills/doc-to-vector-dataset-generator.md) — skill · 227 installs
- [deeplake-hivemind](https://affpapa.org/en/nevibecode/plugins/deeplake-hivemind.md) — plugin · ★ 1658 repo stars
- [tao-validate-dataset-format](https://affpapa.org/en/nevibecode/skills/tao-validate-dataset-format.md) — skill · 1600 installs
- [database](https://affpapa.org/en/nevibecode/rules/first-fluke-database.md) — rule · ★ 1472 repo stars
- [embedding-strategies](https://affpapa.org/en/nevibecode/skills/embedding-strategies.md) — skill · 11391 installs
- [storing-and-querying-vectors](https://affpapa.org/en/nevibecode/skills/storing-and-querying-vectors.md) — skill · 7400 installs

From the same set: [legioncodeinc/vibe-coding-tools](https://affpapa.org/en/nevibecode/by/legioncodeinc/vibe-coding-tools.md) — 172 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
