Individual skill

math-hub

Use when 高教社杯/CUMCM 数学建模项目需要竞赛级范围控制、轻量 hub 状态、当前分问交付物锁定、文献启发式解题路线、结论/证据一致性、数学核验、结果一致性审查、官方规则合规、AI 使用披露跟踪、最终提交门禁或明确任务派发。

math-hub/SKILL.md

Read pinned source

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 · 10,053 bytes
SKILL.mdcore · 10,053 bytes
SKILL.mdcore · 10,053 bytes
agents/openai.yamlasset · 300 bytes
references/a-problem-2024-casebank.mddoc · 7,808 bytes
references/a-problem-decision-tree.mddoc · 6,826 bytes
references/a-problem-pattern-library.mddoc · 8,692 bytes
references/a-problem.mddoc · 1,948 bytes
references/architect.mddoc · 3,842 bytes
references/artifacts-schema.mddoc · 37,126 bytes
references/code.mddoc · 7,248 bytes
references/figure-evidence-rules.mddoc · 8,824 bytes
references/forward-test-protocol.mddoc · 3,734 bytes
references/innovation-generator.mddoc · 7,629 bytes
references/modeler.mddoc · 4,317 bytes
references/quality-contract.mddoc · 3,523 bytes
references/review.mddoc · 5,564 bytes
references/scoring.mddoc · 6,107 bytes
references/writer.mddoc · 3,094 bytes
references/writing-templates.mddoc · 18,254 bytes

Read excerpt


# Math Contest Hub

## Purpose

Act as the contest QC governor. Lock the active problem, subquestion, deliverables, model route quality, evidence status, wording consistency, official-rule risk, and allowed next module before downstream paper-ready work proceeds.

Quality target: `national-first-candidate` means 国一候选 quality and does not promise an award. The hub protects task fit, modeling insight, evidence, reproducibility, and boundaries without forcing every request into a long workflow.

Read `math-hub/references/quality-contract.md` only when promoting paper-ready work, classifying blocked status, running a final gate, or writing a cross-module handoff. For local advice, exploratory checks, and layout/style repairs, keep the answer local and do not load the shared contract unless the result is being promoted.

## Modes

- **QC mode**: default. Answer whether the current work is off-task, unsupported, inconsistent, non-reproducible, or non-compliant if submitted now.
- **dispatch mode**: use only when the user asks to split work, delegate lanes, create a DAG, or assign modules. Start from the QC lock and route the smallest blocker.