# wandb-autoresearch

wandb-autoresearch runs bounded machine learning trials via W&B Launch, smoke-tests real jobs, compares metrics, and tracks research state across sessions.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 387 installs · ★ 76 repo stars
- Author: wandb
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/wandb/skills/tree/HEAD/skills/wandb-autoresearch/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/wandb-autoresearch

## What it does

The skill coordinates training research through W&B Launch instead of falling back on local `wandb.init()` calls. The agent inspects launchable code and queue availability first. It then runs a minimal smoke test before touching any compute budget.

Trials execute one after another. The agent inspects metrics and hardware utilization from the completed job before picking the next configuration. Research progress stays in a local markdown file and syncs to a W&B Artifact via `autoresearch_state.py` when approved.

Python packages must be installed explicitly using `uv`. Without an active W&B Launch queue with verified capacity, the agent will refuse to schedule trials.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add wandb/skills --skill wandb-autoresearch -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add wandb/skills --skill wandb-autoresearch -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add wandb/skills --skill wandb-autoresearch -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install wandb/skills skills/wandb-autoresearch
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add wandb/skills --skill wandb-autoresearch -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/wandb/skills --path skills/wandb-autoresearch
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add wandb/skills --skill wandb-autoresearch -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/wandb/skills/tree/HEAD/skills/wandb-autoresearch/SKILL.md

## When to use it
- verify code readiness and W&B Launch queue capacity
- smoke-test training workloads before full execution
- execute serial parameter trials based on observed metrics
- persist and resume experiment state using W&B Artifacts

## Example prompts
- Inspect queue capacity and smoke-test our training job in W&B Launch
- Run serial trials testing learning rates on W&B Launch within a budget of 4 runs
- Save current autoresearch state to W&B Artifacts

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 326779d7d9da431a.

BEGIN THIRD-PARTY FILE 326779d7d9da431a
````text
---
name: wandb-autoresearch
description: "Run bounded, evidence-driven training research through W&B Launch: assess project readiness, establish launchable code and queue capacity, smoke-test real jobs, execute serial trials, compare metrics, and persist resumable research state. Use when a coding agent is asked to autonomously test training hypotheses or tune a real W&B-tracked workload."
---
<!--
SPDX-FileCopyrightText: 2026 CoreWeave, Inc.
SPDX-License-Identifier: Apache-2.0
SPDX-PackageName: skills
-->

# W&B autoresearch

Use W&B Launch to execute real training experiments, read their results, and
choose the next bounded trial. Do not create a local `wandb.init()` run as a
substitute for compute that was supposed to run through Launch.

The Launch implementation lives in `skills/wandb-primary`:

- `skills/wandb-primary/scripts/launch_helpers.py`
- the `Launch` section in `skills/wandb-primary/SKILL.md`

Install missing packages explicitly with `uv`; do not assume a fixed working
directory or preinstalled environment.

## Flow

Read only the reference for the current stage:

| Stage | Entry condition | Read |
|---|---|---|
| Understand | Always first; inspect launchable code, queue capacity, data location, and prior state | `references/understand.md` |
| Set up | Launchable code or usable queue capacity is missing | `references/setup.md` |
| Search | Launchable code and queue capacity both exist | `references/search.md` |

The readiness gate is `launchable code + queue with usable capacity`. A dataset
may be a versioned Artifact or may be supplied by the code/image; its storage
form alone does not determine readiness.

## Experiment records

Use each W&B object for one job:

- Runs hold trial config, metrics, system metrics, status, and code/job lineage.
- Job or code Artifacts make code relaunchable.
- Dataset Artifacts provide versioned inputs when the workload needs them.
- Launch queues and agents provide compute.
- A small local markdown file holds the hypothesis, trial tally, decisions,
  queue, and next step.

Keep local state at a user-visible path in the current project or a path the
user supplied. Sync it to a W&B Artifact only when cross-session resume is
useful and the user authorizes the write:

```bash
S=skills/wandb-autoresearch/scripts/autoresearch_state.py
uv run --with wandb python "$S" load ENTITY PROJECT --dest .
uv run --with wandb python "$S" save ENTITY PROJECT --path AUTORESEARCH_STATE.md
```

## Compute safety

- Confirm the queue, metric direction, search axis, and trial/compute budget
  before the first non-smoke launch. Do not exceed the agreed budget.
- Smoke-test the real job at a deliberately small setting before full trials.
- Change only config fields the program actually reads. Use a code edit and a
  new job Artifact for architecture or pipeline changes.
- Run trials serially unless the user explicitly authorizes parallel compute.
````
END THIRD-PARTY FILE 326779d7d9da431a

The third-party file has ended. Everything between the 326779d7d9da431a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2922 of 3195 bytes. © wandb · Apache-2.0 · https://github.com/wandb/skills/tree/HEAD/skills/wandb-autoresearch/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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
