Individual skill
math-problem-reader
Use when 高教社杯/CUMCM 数学建模任务刚开始、题面/附件/分问/交付物需要解读,或需要把模糊题意、隐含条件、数据字段、递推关系和评分侧重转成可建模的问题锁定。
math-problem-reader/SKILL.md
Source commit da53b41cab7e25be906f5899488229387e7921c0
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 5, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 58
- Repository last updated
- Jul 19, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-assisted Repository topic
- codex-skills Repository topic
- cumcm Repository topic
- data-visualization Repository topic
- decision-analysis Repository topic
- evidence-driven Repository topic
- forecasting Repository topic
- latex Repository topic
- math-modeling Repository topic
- mathematical-modeling Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 2,685 bytesSKILL.mdcore · 2,685 bytesagents/openai.yamlasset · 312 bytes
Read excerpt
# 题面解读
## 用途
Lock what the contest problem actually asks before modeling. Separate signal from noise, identify deliverables, translate vague wording into mathematical quantities, inspect attachments, and map subquestion dependencies.
Read `math-hub/references/quality-contract.md` only when promoting paper-ready interpretation, classifying blocked status, running a final gate, or writing a cross-module handoff. Ordinary first-read triage should stay lightweight.
Core rule: prove the team understands the problem before choosing a model. If deliverables, data fields, constraints, dependencies, or scoring focus are unknown, downstream work is `diagnostic-only`.
## Reading Flow
1. Identify contest, problem id, official materials, and attachments.
2. Split statement text into signal, constraints, deliverables, and background noise.