SkillsAdd

wandb/skills

wandb-autoresearch

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.

First seen Aug 6, 2026

Installation

$ npx skills add wandb/skills --skill wandb-autoresearch
View on skills.sh ↗ GitHub repository ↗

Summary

  • 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.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

agent-browser Shared topics
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
azure-aigateway Shared topics
microsoft/azure-skills

Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: sem…

566.3K installs
azure-compute Shared topics
microsoft/azure-skills

Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compar…

510K installs
supabase-postgres-best-practices Shared topics
supabase/agent-skills

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill …

391.6K installs
prisma-cli Shared topics
prisma/skills

Prisma ORM CLI commands reference covering init, generate, migrate, db, dev, complete, studio, …

267K installs
supabase Shared topics
supabase/agent-skills

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge F…

263K installs

Also in this package

Other skills from wandb/skills.

npx skills add wandb/skills
wandb-primary 1.5K wandb-eval-tables 121

Browse all from wandb/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 67
License LICENSE
Default branch main
Open issues 1
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,195 B
  • docs SUMMARY.md 375 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 120 installs

SKILL.md

<!-- 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:

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.

Inspect each completed result before selecting the next trial.

  • Report failures, hardware utilization, and uncertainty. Re-run a likely

winner with another seed when the apparent gap could be noise.

  • Never fabricate a run, metric, queue result, or completion state.