model-card-generator

Model documentation skill for generating model cards following Google's model card framework.

不碰外部（只输出文字）无严重或高危命中a5c-ai/babysitter

它会碰到什么

扫了多少2 个文本文件，6 KB

它会碰到什么不碰外部（只输出文字）

命中总数0 处

命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实，不是结论。命中多不等于有毒（安全工具、规则库、示例脚本本来就会包含危险写法），命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系，需要你自己看。

技能内容

model-card-generator

Overview

Model documentation skill for generating comprehensive model cards following Google's model card framework for ML model documentation.

Capabilities

Model details documentation (architecture, training, etc.)
Intended use specification
Performance metrics documentation
Ethical considerations section
Caveats and limitations
Quantitative analysis sections
Version history tracking
Multiple output formats (HTML, Markdown, JSON)

Target Processes

Model Interpretability and Explainability Analysis
Model Evaluation and Validation Framework
ML Model Retraining Pipeline

Tools and Libraries

Model Card Toolkit
TensorFlow Model Analysis (optional)
Jinja2 (templating)

Input Schema

{
  "type": "object",
  "required": ["modelDetails", "intendedUse"],
  "properties": {
    "modelDetails": {
      "type": "object",
      "properties": {
        "name": { "type": "string" },
        "version": { "type": "string" },
        "type": { "type": "string" },
        "architecture": { "type": "string" },
        "trainingDate": { "type": "string" },
        "framework": { "type": "string" },
        "citations": { "type": "array", "items": { "type": "string" } },
        "license": { "type": "string" }
      }
    },
    "intendedUse": {
      "type": "object",
      "properties": {
        "primaryUses": { "type": "array", "items": { "type": "string" } },
        "primaryUsers": { "type": "array", "items": { "type": "string" } },
        "outOfScopeUses": { "type": "array", "items": { "type": "string" } }
      }
    },
    "factors": {
      "type": "object",
      "properties": {
        "relevantFactors": { "type": "array", "items": { "type": "string" } },
        "evaluationFactors": { "type": "array", "items": { "type": "string" } }
      }
    },
    "metrics": {
      "type": "object",
      "properties": {
        "performanceMetrics": { "type": "array" },
        "decisionThresholds": { "type": "object" },
        "variationApproaches": { "type": "array" }
      }
    },
    "evaluationData": {
      "type": "object",
      "properties": {
        "datasets": { "type": "array" },
        "motivation": { "type": "string" },
        "preprocessing": { "type": "string" }
      }
    },
    "trainingData": {
      "type": "object",
      "properties": {
        "datasets": { "type": "array" },
        "motivation": { "type": "string" },
        "preprocessing": { "type": "string" }
      }
    },
    "ethicalConsiderations": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": { "type": "string" },
          "mitigationStrategy": { "type": "string" }
        }
      }
    },
    "caveatsAndRecommendations": {
      "type": "array",
      "items": { "type": "string" }
    },
    "outputConfig": {
      "type": "object",
      "properties": {
        "format": { "type": "string", "enum": ["html", "markdown", "json"] },
        "outputPath": { "type": "string" }
      }
    }
  }
}

Output Schema

{
  "type": "object",
  "required": ["status", "modelCardPath"],
  "properties": {
    "status": {
      "type": "string",
      "enum": ["success", "error"]
    },
    "modelCardPath": {
      "type": "string"
    },
    "format": {
      "type": "string"
    },
    "sections": {
      "type": "array",
      "items": { "type": "string" }
    },
    "warnings": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Warnings about missing recommended sections"
    }
  }
}

Usage Example

{
  kind: 'skill',
  title: 'Generate model card',
  skill: {
    name: 'model-card-generator',
    context: {
      modelDetails: {
        name: 'Fraud Detection Model',
        version: '2.0.0',
        type: 'Binary Classification',
        architecture: 'XGBoost',
        trainingDate: '2024-01-15',
        framework: 'scikit-learn',
        license: 'Proprietary'
      },
      intendedUse: {
        primaryUses: ['Transaction fraud detection'],
        primaryUsers: ['Risk management team'],
        outOfScopeUses: ['Credit scoring', 'Identity verification']
      },
      metrics: {
        performanceMetrics: [
          { name: 'AUC-ROC', value: 0.95 },
          { name: 'Precision@0.5', value: 0.87 }
        ]
      },
      ethicalConsiderations: [
        { name: 'Demographic bias', mitigationStrategy: 'Regular fairness audits' }
      ],
      outputConfig: {
        format: 'markdown',
        outputPath: 'docs/model_card.md'
      }
    }
  }
}

想直接用这个技能？

本站把开放许可（MIT / Apache 等）的技能按仓库打包整理到网盘，点一下转存到你自己的网盘，不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接，不打包。

去原始仓库

它属于哪个仓库

仓库a5c-ai/babysitter

星标★ 1,796

本站分层T1

该仓技能数2115

原文件路径library/specializations/data-science-ml/skills/model-card-generator/SKILL.md

同一个仓库里的其他技能

看这个仓库的全部 2115 个技能