ground-a-simulation
Skill8 starsChanged 3 months agoNo licenceView on GitHub
Use when starting a simulation, strategy game, agent-based model, backtest, training loop, or any system whose output is a number you will later have to trust. Use before the first measurement is taken — everything here is cheap now and either impossible or baseline-invalidating to retrofit. Also use when auditing a young system for whether it is measurable at all, when deciding how much rigor belongs on a pre-1.0 merge gate, when prototyping a subsystem or UI to work out what an integration test should assert, or when a team says "we can't add baselines yet, we don't know the numbers".
In this repository12 other files it gives its agents.
- agent-personasSkill
- audit-a-simulationSkill
- bootstrap-hostingSkill
- detect-driftSkill
- explain-this-projectSkill
- release-processSkill
- run-a-campaignSkill
- search-dont-argueSkill
- trust-your-instrumentsSkill
- verify-releaseSkill
- version-and-claimSkill
- wire-telemetrySkill
The file
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.