EZ Math Model
Seven-stage pipeline for CUMCM/MCM/ICM math-modeling contests: intake to packaged paper.
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 14, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · f9e0810
Its own algorithm-selection table flags this dataset (n=10, <15) for GM(1,1) grey prediction over linear regression, but a real held-out test showed plain linear regression beat GM(1,1) (0.42% vs 1.78% MAPE) — the skill's process/packaging scaffolding is the real value-add, not the auto-picked model.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 6/10
- Docs & honesty 4/5
What EZ Math Model does
Orchestrates a full math-modeling-contest workflow — problem intake, model selection from a built-in algorithm library, Python solving, chart quality gates, paper writing, quality audit, and zip packaging. Triggers on CUMCM/MCM/ICM/国赛/美赛 mentions or uploaded contest problem statements with multi-part questions and datasets.
How to install EZ Math Model
git clone https://github.com/woodfishhhh/EZ_math_model
cd EZ_math_model
mkdir -p ~/.claude/skills
cp -r skills/ez-math-model ~/.claude/skills/ez-math-model
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger EZ Math Model
-
/ez-math-modelSeven-stage pipeline for CUMCM/MCM/ICM math-modeling contests: intake to packaged paper.
It also activates on plain-language prompts like these:
-
Here's our CUMCM contest problem, help us build the full model -
Predict town population for 2025-2027 from this ten-year series -
Package our math-modeling paper for submission with all the charts
Frequently asked questions
- Is the EZ Math Model skill free?
- Yes. The skill itself is free from woodfishhhh/EZ_math_model. SkillProof publishes the install command and an independent test verdict at no cost.
- Does EZ Math Model work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Its own algorithm-selection table flags this dataset (n=10, <15) for GM(1,1) grey prediction over linear regression, but a real held-out test showed plain linear regression beat GM(1,1) (0.42% vs 1.78% MAPE) — the skill's process/packaging scaffolding is the real value-add, not the auto-picked model.
- What is the EZ Math Model SkillProof Score?
- 8.0/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
- How do I install EZ Math Model?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use EZ Math Model with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.