MicrosoftKnown publishermicrosoft/experiment-catalog/.agents/skills/experiment-catalog-demo-data/SKILL.mdexperiment-catalog-demo-data
Skill8 starsChanged 5 months agoMITView on GitHub
Generate realistic demo data for the experiment catalog including projects, experiments, permutations, results with metrics, metric definitions, and tags.
In this repository5 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Keep demo-data generation separate from deployment or pipeline tasks.
- Very specific: line 26
Use this skill to populate a running Experiment Catalog instance with realistic sample projects, experiments, permutations, results, metric …
- Distinctive: line 69
Verify all of the following before handoff:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Execution Model
[!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.
Generate Demo Data
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.
This skill uses the catalog API and does not perform Azure ARM control-plane provisioning. Do not apply the ISE asset telemetry ID to demo-data API calls.
Prerequisites
- Python 3.10+
requests- a reachable catalog API, usually
http://localhost:6010
Fast Path
Run with defaults:
python scripts/generate_demo_data.pyOverride the target:
python scripts/generate_demo_data.py --base-url http://localhost:8080Key Parameters
--base-url: catalog API base URL--results: results per permutation, default300
What The Script Creates
- two demo projects
- multiple experiments per project
- multiple permutations per experiment
- metric definitions
- tags on refs
- randomized but realistic result rows
Validation Checklist
Verify all of the following before handoff:
- the target catalog is reachable
- projects and experiments exist after the run
- results were written at the expected scale
- any generated artifact or summary was saved for reuse
Local References
- Extended instructions and troubleshooting:
references/full-guide.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.