Generate realistic demo data for the experiment catalog including projects, experiments, permutations, results with metrics, metric definitions, and tags.
[!IMPORTANT] Do not execute this skill directly in the main thread. Delegate the data generation task to its own sub-agent and pass this skill path to that sub-agent.
Keep demo-data generation separate from deployment or pipeline tasks. Store the created dataset summary in session artifacts instead of replaying bulk logs.
Use this skill to populate a running Experiment Catalog instance with realistic
sample projects, experiments, permutations, results, metric definitions, and
tags. Open references/full-guide.md for the long-form walkthrough.
requestshttp://localhost:6010Run with defaults:
python scripts/generate_demo_data.py
Override the target:
python scripts/generate_demo_data.py --base-url http://localhost:8080
--base-url: catalog API base URL--results: results per permutation, default 300Verify all of the following before handoff:
references/full-guide.md