# ae-dataops

A skill that tells the agent how to run DataOps work through ae-cli: tables and fields, flow releases, backfills, SQL. Handy when warehouse changes start in chat.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 862 installs · ★ 21
- Author: ThinkingAIAgenticEngine
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ThinkingAIAgenticEngine/ae-cli/tree/HEAD/skills/ae-dataops/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/ae-dataops

## What it does

The skill maps agent behaviour onto `ae-cli` across six domains: `dataops_repo`, `dataops_datatable`, `dataops_flow`, `dataops_operations`, `dataops_ide`, `dataops_integration`. It ships parameter tables, output and error handling notes, plus reference files for tables, flows and entity lifecycle. The agent opens only the section matching the task at hand.

The ground rules matter more than the command list. Table and field edits land in `DEV`, and a release to `PROD` is a separate step you ask for. Manual flow runs and backfills go to `PROD`. Which environment a SQL query hits follows from the tables it touches, so a sample query is no reason to pick one. Ordinary write commands run without `--yes`; the flag is reserved for `high-risk-write` after you confirm. `--dry-run` on field mutations and recycling checks server state, while elsewhere it only echoes the local request and validates nothing about permissions, connections or SQL.

\`ae-cli` must be on `PATH` — the skill declares it as a required binary, and nothing runs without it. One trap worth knowing: `ok:true` is not proof the job finished, because `data` can still hold `REJECTED` or `FAILED`. Async calls hand back an ID, and that same operation is what you poll; resubmitting because it is still running just duplicates work.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-dataops -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-dataops -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-dataops -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install ThinkingAIAgenticEngine/ae-cli ae-dataops
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-dataops -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/ThinkingAIAgenticEngine/ae-cli --path skills/ae-dataops
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add ThinkingAIAgenticEngine/ae-cli --skill ae-dataops -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/ThinkingAIAgenticEngine/ae-cli/tree/HEAD/skills/ae-dataops/SKILL.md

## When to use it
- create a table or view and change a field type
- build a flow in DEV and release it to PROD
- find out why a flow run failed
- run a backfill on a matching PROD flow
- run a SELECT query against the right tables

## Example prompts
- Find the space with code `sales` and list its tables
- Create a view in DEV over the orders table and show me the planned changes
- Run the backfill on that PROD flow and poll the ID for status

## Similar
- [using-dbt-state](https://affpapa.org/en/nevibecode/skills/using-dbt-state.md) — skill · 554 installs
- [warehouse-init](https://affpapa.org/en/nevibecode/skills/warehouse-init.md) — skill · 814 installs
- [cargo-orchestration](https://affpapa.org/en/nevibecode/skills/cargo-orchestration.md) — skill · 10000 installs
- [logistics-expert](https://affpapa.org/en/nevibecode/skills/logistics-expert.md) — skill · 567 installs
- [warehouse-optimization](https://affpapa.org/en/nevibecode/skills/warehouse-optimization.md) — skill · 1100 installs
- [firetiger](https://affpapa.org/en/nevibecode/skills/firetiger.md) — skill · 666 installs

From the same set: [thinkingaiagenticengine/ae-cli](https://affpapa.org/en/nevibecode/by/thinkingaiagenticengine/ae-cli.md) — 17 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