model-judge
Skill1 starsChanged 3 months agoNo licenceView on GitHub
Evidence-first model selection judge for mathematical modeling competitions. Use after candidate models have been proposed and before full-scale modeling. Screen candidates by task fit, dual-layer target validity, confounder diagnostics, minimum-deliverable fallback, data support, identifiability, baseline comparison, cheap proof-of-concept evidence, and competition utility. Do not prefer models because they are sophisticated, novel, or similar to official solutions. Target definition and final model approval remain human-controlled.
In this repository6 other files it gives its agents.
- article-makerSkill
- choose-modelSkill
- data-cleanerSkill
- figure-makerSkill
- modelSkill
- problem-analysisSkill
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.