Mathematical Modeling Review skill
A skill that reviews a CUMCM competition paper against the problem, scores five dimensions and gives an unofficial award forecast.
- 104 ★ on the repository
- Last commit
Minimal access
Why this level
- The skill only reads submitted materials and writes a report; the award forecast is approximate.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/mathematical-modeling-reviewDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill only reads submitted materials and writes a report; the award forecast is approximate.
This is third-party code. Review the repository files before installing.
What it does
Mathematical Modeling Review assesses papers for the China Undergraduate Mathematical Contest in Modeling (CUMCM). The agent receives the full problem statement and the paper, breaks the statement into questions, locates the matching models and results and writes a report usable for revision. The report has five scores of 20 points each, an unofficial total from a public deterministic script, an expected award (national first or second, provincial first, second or third, or "not yet estimated"), a forecast range, confidence and reasons the result may cross levels. Findings separate confirmed errors, major doubts and local flaws, each with a location in the paper, a basis in the problem and a fix criterion. Without the full problem statement the skill performs only an internal preliminary review.
Who it is for. CUMCM student participants and their advisors who want a review of the paper before submission or after the contest.
Good fit when
- Before submission a check is needed on whether every question of the problem is answered.
- The places where the model violates problem constraints must be found.
- An estimate of the realistic award and the first thing to fix is wanted.
- After the contest a review of the paper version for the next attempt is needed.
Not a fit when
- The paper is for another contest such as MCM/ICM or a field-specific one.
- An official assessment from the organizers is required.
- The full problem and data are missing but an award forecast is mandatory.
Example request
Review this CUMCM paper against the attached problem: break down each question, give five scores, an award forecast and the three most urgent fixes.Limitations
The skill is built only for CUMCM, so the scale and award mapping do not fit other contests. The forecast is unofficial and approximate: a check on 18 public papers showed errors in both directions, so there is no reliable basis to treat it as a guarantee. The license is limited to personal non-commercial use, and redistribution or commercial use needs the author's consent. During the contest follow the organizers' rules on AI tools. Copy the whole skill directory with the references and scoring scripts.
How to disable. Delete the skill folder from the agent's skills directory entirely, with the references and scoring scripts.
FAQ
What input is required?
The full paper and the full problem with appendices and data for the given year, group and number. Code, data and results help too.
What happens without the full problem?
The skill does only an internal preliminary review with no total score or award forecast.
How do I install it?
Copy the whole skill directory following `部署指南.md`; copying only `SKILL.md` loses the references and scoring script.
How accurate is the forecast?
It is unofficial. A check on 18 public papers showed both overestimates and underestimates.
Can it be used for other contests?
No, the scale is tied to CUMCM.
Discussion
No questions or reviews yet.
Related
SkillsA skill for writing a mathematical modeling contest paper: LaTeX template, writing rules and five analyzed winning papers
Meta-model-agent takes a mathematical modeling task through seven stages: data, model, computation, figures and paper.
Skill with 30 prompt templates for research papers in English and Chinese, from literature review to grant proposals
A family of 17 skills for a research paper: idea, literature, experiments, writing, review, rebuttal and a pre-submission check
A set of three research skills: paper writing, academic Word and PowerPoint documents, scientific computing and figures
Twelve skills for research work: idea evaluation, literature review, paper text, reviewer rebuttals and figures
README in short
The skill breaks a paper down by the problem's questions, computes five scores with a script and gives an unofficial forecast. CUMCM only.