agentskills.codes
EX

experiment-runner

Use when adding, running, or debugging ML experiments, configs, baselines, metrics, or evaluation scripts.

Install

mkdir -p .claude/skills/experiment-runner && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13547" && unzip -o skill.zip -d .claude/skills/experiment-runner && rm skill.zip

Installs to .claude/skills/experiment-runner

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when adding, running, or debugging ML experiments, configs, baselines, metrics, or evaluation scripts.
106 chars✓ has a “when” trigger

About this skill

Workflow:

  1. Identify the experiment entrypoint.
  2. Identify config files and output directory.
  3. Never modify dataset files or checkpoints.
  4. Prefer adding a new config over changing default configs.
  5. Keep experiment names explicit.
  6. For new baselines, add:
    • config
    • runner hook
    • metric logging
    • README command
  7. Verification should use a tiny dry-run if available.

Search skills

Search the agent skills registry