Not in the top 1,000 by GitHub stars
BZDmathclub/bzd-math-modeling-skills
数学建模竞赛论文智能评审 Skill,支持 Codex 与 Claude Code,使用近五年国赛评阅细则、评分要点、评分概述等文件以及对应赛题进行蒸馏,并将真正在主观评审中涉及到的各种因素考虑在内,较为完备的复刻完整的评审流程,以便大家能够对自己的论文有较好的定位。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/总控类/bzd-modeling-workflow/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/生成类/bzd-ai-usage-disclosure/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/生成类/bzd-modeling-ideas/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/生成类/bzd-problem-restatement/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/生成类/bzd-problem-translator/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/综合评审与自我定位类/bzd-cumcm-school-awards/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/综合评审与自我定位类/bzd-review-paper/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-abstract-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-ai-usage-disclosure/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-model-assumption-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-model-dictionary/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-model-solution-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-paper-aigc-auditor/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-paper-format-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-problem-analysis-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-problem-restatement/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-reference-appendix-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-reference-appendix-checker/bzd-reference-appendix-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-review-paper/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
skills/论文自查类/bzd-symbol-notation-checker/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
5395fb591a47 → 5395fb591a47
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Heat
4.8- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- bzd-modeling-workflow
skills/总控类/bzd-modeling-workflow - bzd-ai-usage-disclosure
skills/生成类/bzd-ai-usage-disclosure - bzd-modeling-ideas
skills/生成类/bzd-modeling-ideas - bzd-problem-restatement
skills/生成类/bzd-problem-restatement - bzd-problem-translator
skills/生成类/bzd-problem-translator - bzd-cumcm-school-awards
skills/综合评审与自我定位类/bzd-cumcm-school-awards - bzd-review-paper
skills/综合评审与自我定位类/bzd-review-paper - bzd-abstract-checker
skills/论文自查类/bzd-abstract-checker - bzd-ai-usage-disclosure
skills/论文自查类/bzd-ai-usage-disclosure - bzd-model-assumption-checker
skills/论文自查类/bzd-model-assumption-checker - bzd-model-dictionary
skills/论文自查类/bzd-model-dictionary - bzd-model-solution-checker
skills/论文自查类/bzd-model-solution-checker - bzd-paper-aigc-auditor
skills/论文自查类/bzd-paper-aigc-auditor - bzd-paper-format-checker
skills/论文自查类/bzd-paper-format-checker - bzd-problem-analysis-checker
skills/论文自查类/bzd-problem-analysis-checker - bzd-problem-restatement
skills/论文自查类/bzd-problem-restatement - bzd-reference-appendix-checker
skills/论文自查类/bzd-reference-appendix-checker - bzd-reference-appendix-checker
skills/论文自查类/bzd-reference-appendix-checker/bzd-reference-appendix-checker - bzd-review-paper
skills/论文自查类/bzd-review-paper - bzd-symbol-notation-checker
skills/论文自查类/bzd-symbol-notation-checker
How it works
bzd-modeling-workflow
When your agent uses it
Orchestrate the BZD mathematical-modeling Skills across problem reading, idea generation, model selection, paper drafting, section checks, final format/AIGC audits and judge-style scoring. Use when a user wants one entry point, an end-to-end competition workflow, the next appropriate Skill, or coordinated processing of a problem and paper.
What it loads into context
Frontmatter
78 tokensAlways available to the agent
SKILL.md
1,397 tokensWhen the skill is activated
Reference documents
1,007 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required reference
- Initial intake
- Routing rules
- State and handoff
- Required controller output
- Guardrails
Files
SKILL.mdcore6,781 bytesreferences/end-to-end-workflow.mddoc3,601 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-ai-usage-disclosure
When your agent uses it
Generate or review mathematical-modeling competition AI tool usage statements and the anonymous AI工具使用详情.pdf. Use when users provide real AI usage records, or when checking a paper, statement, details PDF, code, and AI records for completeness, anonymity, and consistency.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,566 tokensWhen the skill is activated
Reference documents
3,014 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 模式选择
- 共同输入原则
- 信息充分性门槛
- 模式一:正文声明生成
- 模式二:详情材料生成
- 模式三:联合自查
- 禁止行为
- 最终提醒
Files
SKILL.mdcore6,502 bytesagents/openai.yamlasset352 bytesreferences/compliance-checklist.mddoc3,501 bytesreferences/details-template.mddoc3,945 bytesreferences/statement-rules.mddoc1,751 bytesreferences/usage-categories.mddoc1,715 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-modeling-ideas
When your agent uses it
Generate a coherent, whole-paper mathematical modeling solution framework from a complete contest problem. Use after the user supplies a CUMCM or other modeling problem and asks for modeling ideas, an overall solution plan, question-by-question analysis, candidate-model comparison, model-selection reasons, innovations, validation, or cross-question linkage. For every question, explain the task and mathematical essence, compare multiple feasible models in tables, recommend a route with explicit reasons, and keep all questions connected through shared data, variables, parameters, constraints, and validation.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
1,814 tokensWhen the skill is activated
Reference documents
2,154 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Input
- Required references
- Core workflow
- Required output
- Quality rules
Files
SKILL.mdcore9,290 bytesagents/openai.yamlasset366 bytesreferences/cumcm-abcde-modeling-patterns.mddoc3,589 bytesreferences/integrated-modeling-patterns.mddoc3,682 bytesreferences/strategy-output-standard.mddoc2,792 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-problem-restatement
When your agent uses it
Generate a compliant Chinese mathematical-modeling problem-restatement chapter from a complete problem statement, or review a user's restatement against the original problem. Covers research background, problem review, and research overview; does not perform the separate problem-analysis chapter.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
874 tokensWhen the skill is activated
Reference documents
855 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Generation mode
- Review mode
- Shared safeguards
Files
SKILL.mdcore4,103 bytesagents/openai.yamlasset350 bytesreferences/restatement-rules.mddoc2,038 bytesreferences/review-checklist.mddoc1,253 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-problem-translator
When your agent uses it
Translate a complete mathematical modeling contest problem sentence by sentence into precise modeling language, preserve every substantive condition and definition, expose hidden constraints, draw a mandatory Mermaid cross-question flowchart, audit omissions, and deliver one easy-to-open Markdown report. For Huawei Cup (CPGMCM) graduate-contest problems, additionally prepend a plain-language layer that rewrites the background and questions as a primary-school word problem with a mandatory term-mapping table. Optionally render the finished report as one standalone HTML page on request. Use whenever a user supplies a CUMCM, CPGMCM, or other modeling problem and asks to interpret, translate, unpack, read closely, identify requirements, or avoid missing details before modeling.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
3,205 tokensWhen the skill is activated
Reference documents
8,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required references
- Contest identification
- Required input
- Workflow
- Optional HTML rendering
- Required Markdown content
- Guardrails
Scripts executed separately
scripts/render_html.py
Files
SKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesSKILL.mdcore15,581 bytesagents/openai.yamlasset1,052 bytesreferences/cpgmcm-plain-language-translation.mddoc10,157 bytesreferences/cpgmcm-translation-signals.mddoc5,608 bytesreferences/cumcm-abcde-translation-signals.mddoc3,308 bytesreferences/historical-review-signals.mddoc3,434 bytesreferences/md-output-standard.mddoc7,620 bytesreferences/sentence-interpretation-rules.mddoc3,043 bytesscripts/render_html.pyruns20,094 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-cumcm-school-awards
When your agent uses it
Query 2021-2025 CUMCM school awards and 2026 forecasts, or assess a student's preparation distance from provincial and national awards using school history and prior modeling experience.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
658 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 查询
- 备赛评估
- Safeguards
Scripts executed separately
scripts/query_school.py
Files
SKILL.mdcore2,932 bytesSKILL.mdcore2,932 bytesagents/openai.yamlasset255 bytesassets/高教社杯国赛学校综合统计与2026预测.xlsxasset153,954 bytesscripts/query_school.pyruns2,168 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-review-paper
When your agent uses it
Review mathematical modeling competition papers from a complete problem and paper, with an optional strict bzd-paper-format-checker audit, itemized problem-specific scoring, a bottom-up low-score safeguard, and CUMCM award calibration by problem type, division, region, school and advisor. Generate a Chinese HTML judge report.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
2,967 tokensWhen the skill is activated
Reference documents
27,960 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Knowledge basis and contest gateway
- Workflow
- Required output order
- Guardrails
Scripts executed separately
scripts/award_position.pyscripts/competition_context.pyscripts/score_percentile.py
Files
SKILL.mdcore13,766 bytesSKILL.mdcore13,766 bytesagents/openai.yamlasset691 bytesassets/report-template.htmlasset7,497 bytesreferences/atomic-deduction-scoring.mddoc7,415 bytesreferences/award-ranking-output.mddoc6,060 bytesreferences/calibration-record-template.mddoc1,472 bytesreferences/calibrations/cpgmcm-2024-c-core-loss.mddoc4,596 bytesreferences/calibrations/cpgmcm-2024-f-xray-pulsar.mddoc3,899 bytesreferences/calibrations/cumcm-2022-a-wave-energy.mddoc2,988 bytesreferences/calibrations/cumcm-2022-b-bearing-only-uav.mddoc2,696 bytesreferences/calibrations/cumcm-2022-c-ancient-glass.mddoc3,430 bytesreferences/calibrations/cumcm-2023-a-heliostat-field.mddoc3,129 bytesreferences/calibrations/cumcm-2023-b-multibeam-survey.mddoc3,151 bytesreferences/calibrations/cumcm-2023-c-vegetable-pricing.mddoc8,702 bytesreferences/calibrations/cumcm-2024-a-bench-dragon.mddoc2,544 bytesreferences/calibrations/cumcm-2024-b-production-decisions.mddoc2,943 bytesreferences/calibrations/cumcm-2024-c-crop-strategy.mddoc3,125 bytesreferences/calibrations/cumcm-2025-a-smoke-screen.mddoc3,048 bytesreferences/calibrations/cumcm-2025-b-epitaxial-thickness.mddoc3,100 bytesreferences/calibrations/cumcm-2025-c-nipt.mddoc4,076 bytesreferences/competition-context-adjustment.mddoc6,514 bytesreferences/cross-case-patterns.mddoc8,263 bytesreferences/cumcm-problem-type-review.mddoc3,056 bytesreferences/data/region_difficulty_scores.csvasset2,214 bytesreferences/data/region_public_statistics.csvasset2,491 bytesreferences/data/school_awards_2021_2026.csvasset129,110 bytesreferences/evidence-centered-scoring.mddoc12,282 bytesreferences/formatting-standard.mddoc9,240 bytesreferences/html-output.mddoc2,228 bytesreferences/learning-protocol.mddoc3,551 bytesreferences/low-score-safeguard.mddoc3,242 bytesreferences/rubric-construction.mddoc7,125 bytesreferences/rubric.mddoc4,525 bytesreferences/title-abstract-keywords.mddoc5,916 bytesscripts/award_position.pyruns3,047 bytesscripts/competition_context.pyruns9,116 bytesscripts/score_percentile.pyruns1,863 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-abstract-checker
When your agent uses it
Review a user-provided Chinese mathematical-modeling abstract without requiring the problem statement or full paper, identify concrete writing defects, and prioritize revisions. Use when the user asks to check, diagnose, or improve a modeling-paper abstract; do not claim coverage or factual consistency that cannot be verified without the problem or paper.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
842 tokensWhen the skill is activated
Reference documents
1,201 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- First gate: independent readability
- Evidence discipline
- Required output
- Revision boundary
Files
SKILL.mdcore4,091 bytesagents/openai.yamlasset337 bytesreferences/rubric.mddoc4,671 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-ai-usage-disclosure
When your agent uses it
Generate or review mathematical-modeling competition AI tool usage statements and the anonymous AI工具使用详情.pdf. Use when users provide real AI usage records, or when checking a paper, statement, details PDF, code, and AI records for completeness, anonymity, and consistency.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,566 tokensWhen the skill is activated
Reference documents
3,014 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 模式选择
- 共同输入原则
- 信息充分性门槛
- 模式一:正文声明生成
- 模式二:详情材料生成
- 模式三:联合自查
- 禁止行为
- 最终提醒
Files
SKILL.mdcore6,502 bytesagents/openai.yamlasset352 bytesreferences/compliance-checklist.mddoc3,501 bytesreferences/details-template.mddoc3,945 bytesreferences/statement-rules.mddoc1,751 bytesreferences/usage-categories.mddoc1,715 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-model-assumption-checker
When your agent uses it
Review a mathematical-modeling paper's model-assumption section against the complete problem statement. Diagnose whether each assumption is necessary, evidence-based, compatible with the task, appropriately simplified, and usable by the later model. Use for assumption review, not automatic full-paper review or unsupported assumption generation.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,165 tokensWhen the skill is activated
Reference documents
1,179 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 审查目标
- 审查流程
- 必须输出
- 行为边界
Files
SKILL.mdcore4,536 bytesagents/openai.yamlasset319 bytesreferences/assumption-review-rules.mddoc4,391 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-model-dictionary
When your agent uses it
Query the bundled BZD mathematical-modeling dictionary for a user-selected model, explain its assumptions, inputs, outputs, limitations and validation, then judge whether it fits the current competition problem and data. Use when a user asks whether a proposed model is appropriate, requests model feasibility review, or wants dictionary-based alternatives for a modeling task.
What it loads into context
Frontmatter
76 tokensAlways available to the agent
SKILL.md
958 tokensWhen the skill is activated
Reference documents
864 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Required inputs
- Current-task isolation
- Workflow
- Output structure
- Copyright and data guardrails
Scripts executed separately
scripts/query_dictionary.py
Files
SKILL.mdcore4,956 bytesagents/openai.yamlasset380 bytesassets/model-dictionary.jsonasset8,677,144 bytesreferences/fit-assessment.mddoc3,643 bytesscripts/query_dictionary.pyruns2,778 bytes处理报告.mddoc633 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-model-solution-checker
When your agent uses it
Review the model establishment, numerical solution, result analysis, model validation, and sensitivity or robustness sections of a mathematical-modeling paper against the complete problem. Use for core-model-section diagnosis, not automatic full-paper scoring or unsupported recomputation.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,581 tokensWhen the skill is activated
Reference documents
3,360 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 审查目标
- 审查流程
- 必须输出
- 行为边界
Files
SKILL.mdcore6,164 bytesagents/openai.yamlasset332 bytesreferences/cumcm-abcde-solution-redflags.mddoc4,224 bytesreferences/model-establishment-and-solution.mddoc4,635 bytesreferences/validation-and-sensitivity.mddoc3,693 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-paper-aigc-auditor
When your agent uses it
对数学建模竞赛论文进行两层AI痕迹审计——第一层9维检测(语言层面60%:连接词/排比/拔高词/被动句/段落规律/文本复杂度;事实层面40%:引文验证/数值一致性/术语一致性),第二层模型合理性深度审查。严格判分+一票否决+问题标红。输出分层HTML报告。
What it loads into context
Frontmatter
114 tokensAlways available to the agent
SKILL.md
6,883 tokensWhen the skill is activated
Reference documents
44,049 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 融合nature-AIGC检测方法 · 严格判分版
- 核心原理
- 使用场景
- 输入要求
- 执行流程(9步)
- 报告标红规范(v2.2强制)
- 关键输出物
- 特殊说明
- 文件清单
- 快速开始
- 版本信息
- 重要声明
Files
BZD数模论文AI痕迹审计完整Prompt.mddoc39,509 bytesINTEGRATION_SUMMARY.mddoc10,598 bytesQUICK_CHECK_CARD.mddoc5,266 bytesREADME.mddoc11,900 bytesSKILL.mdcore21,325 bytesreferences/audit-framework.mddoc21,319 bytesreferences/humanizer-keywords.txtdoc2,289 bytesreferences/layer1-enhanced-detection.mddoc19,097 bytesreferences/models-zh.mddoc7,076 bytesreferences/nature-detector-integration.mddoc13,658 bytesreferences/patterns-zh.mddoc9,483 bytestemplates/BZD数模论文AI痕迹审计报告模板.htmlasset37,167 bytestemplates/BZD数模论文AI痕迹自查指南.htmlasset25,618 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-paper-format-checker
When your agent uses it
Review a complete mathematical-modeling competition paper with an atomic checklist covering abstract readability, page structure, typography, headings, pagination, figures, tables, equations, anonymity, metadata, visual balance, and page allocation. Return the review in chat or Markdown by default, and provide the bundled single-sheet checklist when the user requests a reusable form. Use when the user provides a PDF or Word paper and asks for a full-paper format and writing-compliance audit; do not replace technical model correctness review.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
4,393 tokensWhen the skill is activated
Reference documents
17,101 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 平台兼容性
- 规则优先级
- AI 使用材料边界
- 检查流程
- 高教社杯全国大学生数学建模竞赛特别规则
- 中国研究生数学建模竞赛(华为杯)特别规则
- 输入与核验边界
- 原子检查点与评分
- 必须输出
- 行为边界
Files
SKILL.mdcore16,719 bytesagents/openai.yamlasset989 bytesassets/~$数学建模论文各板块自查表.xlsxasset165 bytesassets/数学建模论文各板块自查表.xlsxasset28,444 bytesassets/数学建模论文自查表.xlsxasset29,243 bytesreferences/format-review-rules.mddoc22,987 bytesreferences/paper-section-self-check-table.mddoc31,548 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-problem-analysis-checker
When your agent uses it
Review a Chinese mathematical-modeling problem-analysis section against the original problem, checking task classification, data reasoning, cross-problem linkage, model-choice rationale, validation planning, chapter boundaries, and the overall solution framework. Use for diagnosis, not automatic full rewriting.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
912 tokensWhen the skill is activated
Reference documents
1,767 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core distinction
- Review procedure
- Required output
- Evidence and behavior boundaries
Files
SKILL.mdcore4,568 bytesagents/openai.yamlasset354 bytesreferences/analysis-checklist.mddoc3,062 bytesreferences/cumcm-abcde-analysis-checks.mddoc3,505 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-problem-restatement
When your agent uses it
Generate a compliant Chinese mathematical-modeling problem-restatement chapter from a complete problem statement, or review a user's restatement against the original problem. Covers research background, problem review, and research overview; does not perform the separate problem-analysis chapter.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
874 tokensWhen the skill is activated
Reference documents
855 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Generation mode
- Review mode
- Shared safeguards
Files
SKILL.mdcore4,103 bytesagents/openai.yamlasset350 bytesreferences/restatement-rules.mddoc2,038 bytesreferences/review-checklist.mddoc1,253 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-reference-appendix-checker
When your agent uses it
Check a mathematical-modeling paper's in-text citations, bibliography, appendix length and content, code, supporting files, reproducibility, consistency, and anonymity. Use when the user provides a paper or related materials and wants one consolidated P0-P3 audit; do not generate or invent missing sources or programs.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,568 tokensWhen the skill is activated
Reference documents
2,229 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 检查原则
- 材料边界
- 执行流程
- 风险等级
- 输出
Files
SKILL.mdcore5,948 bytesagents/openai.yamlasset343 bytesreferences/appendix-rules.mddoc2,270 bytesreferences/checklist.mddoc3,620 bytesreferences/reference-rules.mddoc2,247 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-reference-appendix-checker
When your agent uses it
Check a mathematical-modeling paper's in-text citations, bibliography, appendix length and content, code, supporting files, reproducibility, consistency, and anonymity. Use when the user provides a paper or related materials and wants one consolidated P0-P3 audit; do not generate or invent missing sources or programs.
What it loads into context
Frontmatter
74 tokensAlways available to the agent
SKILL.md
1,568 tokensWhen the skill is activated
Reference documents
2,229 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 检查原则
- 材料边界
- 执行流程
- 风险等级
- 输出
Files
SKILL.mdcore5,948 bytesagents/openai.yamlasset343 bytesreferences/appendix-rules.mddoc2,270 bytesreferences/checklist.mddoc3,620 bytesreferences/reference-rules.mddoc2,247 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-review-paper
When your agent uses it
Review mathematical modeling competition papers from a complete problem and paper, with an optional strict bzd-paper-format-checker audit, itemized problem-specific scoring, a bottom-up low-score safeguard, and CUMCM award calibration by problem type, division, region, school and advisor. Generate a Chinese HTML judge report.
What it loads into context
Frontmatter
71 tokensAlways available to the agent
SKILL.md
2,967 tokensWhen the skill is activated
Reference documents
27,480 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Knowledge basis and contest gateway
- Workflow
- Required output order
- Guardrails
Scripts executed separately
scripts/award_position.pyscripts/competition_context.pyscripts/score_percentile.py
Files
SKILL.mdcore13,766 bytesSKILL.mdcore13,766 bytesagents/openai.yamlasset691 bytesassets/report-template.htmlasset7,497 bytesreferences/atomic-deduction-scoring.mddoc7,415 bytesreferences/award-ranking-output.mddoc6,060 bytesreferences/calibration-record-template.mddoc1,472 bytesreferences/calibrations/cpgmcm-2024-c-core-loss.mddoc4,596 bytesreferences/calibrations/cpgmcm-2024-f-xray-pulsar.mddoc3,899 bytesreferences/calibrations/cumcm-2022-a-wave-energy.mddoc2,988 bytesreferences/calibrations/cumcm-2022-b-bearing-only-uav.mddoc2,696 bytesreferences/calibrations/cumcm-2022-c-ancient-glass.mddoc3,430 bytesreferences/calibrations/cumcm-2023-a-heliostat-field.mddoc3,129 bytesreferences/calibrations/cumcm-2023-b-multibeam-survey.mddoc3,151 bytesreferences/calibrations/cumcm-2023-c-vegetable-pricing.mddoc8,702 bytesreferences/calibrations/cumcm-2024-a-bench-dragon.mddoc2,544 bytesreferences/calibrations/cumcm-2024-b-production-decisions.mddoc2,943 bytesreferences/calibrations/cumcm-2024-c-crop-strategy.mddoc3,125 bytesreferences/calibrations/cumcm-2025-a-smoke-screen.mddoc3,048 bytesreferences/calibrations/cumcm-2025-b-epitaxial-thickness.mddoc3,100 bytesreferences/calibrations/cumcm-2025-c-nipt.mddoc4,076 bytesreferences/competition-context-adjustment.mddoc6,514 bytesreferences/cross-case-patterns.mddoc8,263 bytesreferences/cumcm-problem-type-review.mddoc1,970 bytesreferences/data/region_difficulty_scores.csvasset2,214 bytesreferences/data/region_public_statistics.csvasset2,491 bytesreferences/data/school_awards_2021_2026.csvasset129,110 bytesreferences/evidence-centered-scoring.mddoc12,282 bytesreferences/formatting-standard.mddoc9,240 bytesreferences/html-output.mddoc2,228 bytesreferences/learning-protocol.mddoc3,551 bytesreferences/low-score-safeguard.mddoc1,687 bytesreferences/rubric-construction.mddoc7,125 bytesreferences/rubric.mddoc4,525 bytesreferences/title-abstract-keywords.mddoc5,916 bytesscripts/award_position.pyruns3,047 bytesscripts/competition_context.pyruns9,116 bytesscripts/score_percentile.pyruns1,863 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbzd-symbol-notation-checker
When your agent uses it
Review the symbol-notation section of a mathematical-modeling paper against the full paper. Check table coverage, symbol meanings, units, overloading, case and subscript consistency, first-use definitions, formula usage, and visible table formatting. Use for symbol-table diagnosis, not general paper review.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
1,252 tokensWhen the skill is activated
Reference documents
1,236 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 审查范围
- 审查流程
- 必须输出
- 行为边界
Files
SKILL.mdcore4,715 bytesagents/openai.yamlasset351 bytesreferences/symbol-review-rules.mddoc4,535 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- bzd-modeling-workflow
- bzd-ai-usage-disclosure
- bzd-modeling-ideas
- bzd-problem-restatement
- bzd-problem-translator
- bzd-cumcm-school-awards
- bzd-review-paper
- bzd-abstract-checker
- bzd-ai-usage-disclosure
- bzd-model-assumption-checker
- bzd-model-dictionary
- bzd-model-solution-checker
- bzd-paper-aigc-auditor
- bzd-paper-format-checker
- bzd-problem-analysis-checker
- bzd-problem-restatement
- bzd-reference-appendix-checker
- bzd-reference-appendix-checker
- bzd-review-paper
- bzd-symbol-notation-checker
Repository facts
- License
- No license detected
- Created
- Aug 13, 2026
- Last pushed
- Sep 18, 2026
- Forks
- 19
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 15 notes
skills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/生成类/bzd-problem-translator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/综合评审与自我定位类/bzd-cumcm-school-awards/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/综合评审与自我定位类/bzd-review-paper/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/论文自查类/bzd-model-dictionary/assets/model-dictionary.json:1Analysis incomplete: Blob exceeds size or total-read limit; file skippedskills/论文自查类/bzd-review-paper/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 17 network referencesin 8 files: bzd-problem-translator/scripts/render_html.py:402 bzd-review-paper/assets/report-template.html:28 bzd-review-paper/assets/report-template.html:28 and 5 more
- No hidden or obfuscated text
- No instruction overrides
- 9 executable scriptsin 9 files: bzd-problem-translator/scripts/render_html.py:1 bzd-cumcm-school-awards/scripts/query_school.py:1 bzd-review-paper/scripts/award_position.py:1 and 6 more
- No access to secrets
- No requests to vote in Hot
Show all 26 signals by file
skills/生成类/bzd-problem-translator/scripts/render_html.py
- Executable scriptline 1
Executable file - Network accessline 402
</main> </div> <script src="https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.min.js"></script> - Network accessline 403
</div> <script src="https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.min.js"></script> <script>{js}</script> - Network accessline 404
<script src="https://cdn.jsdelivr.net/npm/mermaid@10/dist/mermaid.min.js"></script>
skills/综合评审与自我定位类/bzd-cumcm-school-awards/scripts/query_school.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/综合评审与自我定位类/bzd-review-paper/SKILL.md
skills/综合评审与自我定位类/bzd-review-paper/assets/report-template.html
- Network accessline 28
<section class="card section"><h2><span>04</span>评委式评价</h2><ul class="clean-list">{{JUDGE_ITEMS}}</ul></section> <section class="card section"><h2><span>05</span>优先修改建议</h2><ol class="clean-list numbered">{{REVISION_ITEMS}}</ol><p class - Network accessline 29
<section class="card section"><h2><span>05</span>优先修改建议</h2><ol class="clean-list numbered">{{REVISION_ITEMS}}</ol><p class="footer">BZD-review-paper · 本报告为模型化评审意见,不代表竞赛官方结果</p></section> <aside class="card service" aria-label="BZD数模社联系 - Network accessline 30
<aside class="card service" aria-label="BZD数模社联系方式"><p>✨ 如需进一步详细的论文检查、赛中资料等服务<br>可关注 <strong>BZD数模社</strong> 官网:<a href="https://bzdshumo.com/">https://bzdshumo.com/</a></p><p><strong>QQ数模交流群(主群1):</strong>689964173<br><strong>QQ数模交流2群(主群2)
skills/综合评审与自我定位类/bzd-review-paper/references/award-ranking-output.md
- Network accessline 105
> 如需进一步详细的论文检查、赛中资料等服务,可关注 **BZD数模社**:https://bzdshumo.com/
skills/综合评审与自我定位类/bzd-review-paper/scripts/award_position.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/综合评审与自我定位类/bzd-review-paper/scripts/competition_context.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/综合评审与自我定位类/bzd-review-paper/scripts/score_percentile.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/论文自查类/bzd-model-dictionary/scripts/query_dictionary.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/论文自查类/bzd-paper-aigc-auditor/README.md
skills/论文自查类/bzd-review-paper/SKILL.md
skills/论文自查类/bzd-review-paper/assets/report-template.html
- Network accessline 28
<section class="card section"><h2><span>04</span>评委式评价</h2><ul class="clean-list">{{JUDGE_ITEMS}}</ul></section> <section class="card section"><h2><span>05</span>优先修改建议</h2><ol class="clean-list numbered">{{REVISION_ITEMS}}</ol><p class - Network accessline 29
<section class="card section"><h2><span>05</span>优先修改建议</h2><ol class="clean-list numbered">{{REVISION_ITEMS}}</ol><p class="footer">BZD-review-paper · 本报告为模型化评审意见,不代表竞赛官方结果</p></section> <aside class="card service" aria-label="BZD数模社联系 - Network accessline 30
<aside class="card service" aria-label="BZD数模社联系方式"><p>✨ 如需进一步详细的论文检查、赛中资料等服务<br>可关注 <strong>BZD数模社</strong> 官网:<a href="https://bzdshumo.com/">https://bzdshumo.com/</a></p><p><strong>QQ数模交流群(主群1):</strong>689964173<br><strong>QQ数模交流2群(主群2)
skills/论文自查类/bzd-review-paper/references/award-ranking-output.md
- Network accessline 105
> 如需进一步详细的论文检查、赛中资料等服务,可关注 **BZD数模社**:https://bzdshumo.com/
skills/论文自查类/bzd-review-paper/scripts/award_position.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/论文自查类/bzd-review-paper/scripts/competition_context.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/论文自查类/bzd-review-paper/scripts/score_percentile.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Declared and executed: 1 fact
- Contacts cdn.jsdelivr.net, which SKILL.md, the README and the plugin manifest do not mentionbzd-problem-translator/scripts/render_html.py:404High confidence
Signal confidence: 20 facts
- Executable script in a comment of a file that runsbzd-problem-translator/scripts/render_html.py:1Low confidence
- Network access in code of a file that runsbzd-problem-translator/scripts/render_html.py:402High confidence
- Network access in code of a file that runsbzd-problem-translator/scripts/render_html.py:403High confidence
- Network access in code of a file that runsbzd-problem-translator/scripts/render_html.py:404High confidence
- Executable script in code of a file that runsbzd-cumcm-school-awards/scripts/query_school.py:1High confidence
- Network access in prose of the SKILL.mdbzd-review-paper/SKILL.md:98Low confidence
- Network access in prose of the SKILL.mdbzd-review-paper/SKILL.md:99Low confidence
- Network access in prose of documentationbzd-review-paper/references/award-ranking-output.md:105Low confidence
- Executable script in code of a file that runsbzd-review-paper/scripts/award_position.py:1High confidence
- Executable script in code of a file that runsbzd-review-paper/scripts/competition_context.py:1High confidence
- Executable script in code of a file that runsbzd-review-paper/scripts/score_percentile.py:1High confidence
- Executable script in code of a file that runsbzd-model-dictionary/scripts/query_dictionary.py:1High confidence
- Network access in code of documentationbzd-paper-aigc-auditor/README.md:355Low confidence
- Network access in code of documentationbzd-paper-aigc-auditor/README.md:356Low confidence
- Network access in prose of the SKILL.mdbzd-review-paper/SKILL.md:98Low confidence
- Network access in prose of the SKILL.mdbzd-review-paper/SKILL.md:99Low confidence
- Network access in prose of documentationbzd-review-paper/references/award-ranking-output.md:105Low confidence
- Executable script in code of a file that runsbzd-review-paper/scripts/award_position.py:1High confidence
- Executable script in code of a file that runsbzd-review-paper/scripts/competition_context.py:1High confidence
- Executable script in code of a file that runsbzd-review-paper/scripts/score_percentile.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/总控类/bzd-modeling-workflow/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/总控类/bzd-modeling-workflow/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/总控类/bzd-modeling-workflow/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/总控类/bzd-modeling-workflow/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/总控类/bzd-modeling-workflow/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/总控类/bzd-modeling-workflow/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.