modeling-project-structure
Standardizes directory structures and ensures reproducibility for mathematical modeling projects.
Install
mkdir -p .claude/skills/modeling-project-structure && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17455" && unzip -o skill.zip -d .claude/skills/modeling-project-structure && rm skill.zipInstalls to .claude/skills/modeling-project-structure
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
创建和治理数学建模项目目录、文件命名、产物追踪、运行日志和交付包。用于新建项目、整理混乱项目、检查目录规范。Key capabilities
- →Create and govern mathematical modeling project directories
- →Track artifacts and ensure evidence traceability
- →Generate stage products and bind conclusions to evidence
- →Run quality gates for each stage and retain failure logs
- →Provide downstream usage instructions for all outputs
How it works
This skill establishes a structured project environment for mathematical modeling, ensuring traceability of evidence and adherence to quality gates throughout the project lifecycle.
Inputs & outputs
When to use modeling-project-structure
- →Structuring a new modeling project
- →Tracking model output evidence
- →Checking project directory standards
- →Preparing project delivery packages
About this skill
项目结构
状态:Beta。该技能属于数学建模全流程系统。执行时保持证据可追溯:原题事实、模型假设、代码输出、图表和论文结论必须能互相定位。公式统一使用美元符号格式,例如 $x_i$ 和 $$\min f(x)$$。
触发场景
- 用户明确提到 modeling-project-structure 或当前任务落在“项目结构”阶段。
- 当前项目需要从上游产物推进到下游产物。
- 已有材料不完整,但需要先形成可执行的阶段交付。
- 若本 skill 存在 manifest.yaml 或 static/,先按路由加载必要片段,不要凭记忆执行专业规范。
输入要求
- 输入:项目根目录、目标名称、现有文件。
- 若输入缺失,先从项目目录中寻找同名或相邻产物。
- 查不到的事实写 unknown/待核查,不要为了完整性编造。
- 对会改变建模方向、数据取舍、论文结论的选择,必须显式列出依据和风险。
工作步骤
- 读取上游产物、原始材料和本技能 manifest/static/references 中的必要规范。
- 建立阶段契约:目标、证据、边界、输出路径和待核查项。
- 生成阶段产物,并把每个结论绑定到文件、数据、命令或日志证据。
- 运行本阶段质量门禁;失败时保留失败日志,不覆盖为成功产物。
输出产物
- 主要输出:标准目录、结构检查报告。
- 所有输出应包含:来源、时间、状态、待核查项、下游使用说明。
- 数值结果必须说明生成脚本、输入文件和输出文件位置。
- 若本阶段只完成计划而未执行,状态写 PLANNED。
质量门禁
- 变量、数据字段、公式、图表和结论必须一致。
- 不能把未经验证的文献、指标或结果写成事实。
- 数据图表必须可由 Python 代码复现。
- LaTeX 相关内容只能进入 paper/,不生成 Word。
- 公式使用 $...$ 或 $$...$$,避免混用其他公式标记。
失败/不确定时处理规则
- 环境缺失写 UNAVAILABLE: 原因,并给出可执行替代方案。
- 数据或文献无法核查写 UNKNOWN: 待核查内容。
- 若发现上游设计不可行,停止推进并返回上游阶段修订。
- 若检查失败,保留失败日志,不覆盖成成功产物。
上下游交接格式
{
"schema": "math_modeling.stage_handoff.v1",
"skill": "modeling-project-structure",
"status": "VERIFIED|PLANNED|UNKNOWN|UNAVAILABLE|FAILED",
"inputs": ["项目根目录、目标名称、现有文件"],
"outputs": ["标准目录、结构检查报告"],
"evidence": ["file paths, hashes, commands, logs"],
"open_questions": ["unknown/待核查"],
"next_skill": "由 modeling-orchestrator 根据链路选择"
}
When not to use it
- →When the task is not related to mathematical modeling project structure or governance
- →When the project does not require evidence traceability
- →When the project does not need to form executable stage deliverables
Limitations
- →Specific to mathematical modeling projects
- →Requires all formulas to use dollar sign format
- →Does not generate Word documents for LaTeX content
How it compares
This skill provides a formalized system for mathematical modeling project structure, emphasizing evidence traceability and quality gates, which is more rigorous than typical project organization.
Compared to similar skills
modeling-project-structure side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| modeling-project-structure (this skill) | 0 | 19d | Review | Advanced |
| product-strategist | 12 | 7mo | Review | Advanced |
| report-research | 1 | 5mo | Review | Intermediate |
| skills | 0 | 4mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
product-strategist
davila7
Strategic product leadership toolkit for Head of Product including OKR cascade generation, market analysis, vision setting, and team scaling. Use for strategic planning, goal alignment, competitive analysis, and organizational design.
report-research
numerai
Write a complete Numerai experiment report in experiment.md (abstract, methods, results tables, decisions, next steps) and generate/link the standard show_experiment plot(s). Use after running any Numerai research experiments, or when a user asks for a “full report”, “write up”, “experiment.md update”, or “generate the standard plot”.
skills
second-state
Transcribe speech from audio files to text.
hugging-face-evaluation
FISCFED9
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
document-pro
bighardperson
文档处理技能 - 让 AI 能够读取、解析、提取 PDF、DOCX、PPT 等文档的关键信息。当用户要求分析文档、提取内容、总结报告时触发此技能。
Create SDRF
bigbio
Create a sample-to-data-relationship format (SDRF) file (usually from another type of samplesheet)