ai.smithery/magenie33-quality-dimension-generator
AI 与智能体by magenie33
根据任务描述生成定制化质量标准与评分指南,帮助细化目标并提升评估一致性。
什么是 ai.smithery/magenie33-quality-dimension-generator?
根据任务描述生成定制化质量标准与评分指南,帮助细化目标并提升评估一致性。
README
Quality Dimension Generator
An MCP server that generates quality evaluation standards for any task. Transform vague requirements into precise, measurable quality criteria with AI-powered analysis, ultimately improving your final work quality.
🎯 What It Does
- 📊 Analyzes your tasks - Understand what needs to be accomplished
- 🎯 Creates evaluation standards - Generate specific quality dimensions with scoring criteria
- 📈 Sets target scores - Define expected quality levels (e.g., 8/10)
- ✅ Guides execution - Help you complete tasks with clear quality standards
🚀 Quick Start
Installation
Install from the Smithery AI Model Context Protocol Registry:
🔗 Get Quality Dimension Generator on Smithery
Basic Usage
Step 1: Generate task analysis
generate_task_analysis_prompt({
userMessage: "Write a 1000-word article about AI"
})
Step 2: Generate quality standards
generate_quality_dimensions_prompt({
taskAnalysisJson: "..." // JSON from step 1
})
Result: Get comprehensive quality evaluation criteria with target scores, then complete your task following those standards.
📋 Example Output
For the task "Write a technical blog post":
{
"expectedScore": 8,
"scoreCalculation": "Average of all 5 dimension scores",
"dimensions": [
{
"name": "Technical Accuracy",
"description": "Correctness and depth of technical content",
"importance": "Ensures readers get reliable information",
"scoring": {
"10": "All technical details verified and comprehensive",
"8": "Mostly accurate with minor gaps",
"6": "Generally correct but lacks depth"
}
}
// ... 4 more dimensions
]
}
💡 Use Cases
- Software Development - Code quality, testing, documentation standards
- Content Creation - Writing quality, SEO, engagement metrics
- Project Management - Deliverable criteria, timeline adherence
- Research - Methodology, accuracy, presentation standards
🤝 Contributing
Contributions welcome! This project is open source under the MIT License.
🔗 Resources
Transform your work quality today! 🚀
常见问题
ai.smithery/magenie33-quality-dimension-generator 是什么?
根据任务描述生成定制化质量标准与评分指南,帮助细化目标并提升评估一致性。
相关 Skills
Claude接口
by anthropics
面向接入 Claude API、Anthropic SDK 或 Agent SDK 的开发场景,自动识别项目语言并给出对应示例与默认配置,快速搭建 LLM 应用。
✎ 想把Claude能力接进应用或智能体,用claude-api上手快、兼容Anthropic与Agent SDK,集成路径清晰又省心
智能体流程设计
by alirezarezvani
面向生产级多 Agent 编排,梳理顺序、并行、分层、事件驱动、共识五种工作流设计,覆盖 handoff、状态管理、容错重试、上下文预算与成本优化,适合搭建复杂 AI 协作系统。
✎ 帮你把多智能体流程设计、编排和自动化统一起来,复杂工作流也能更稳地落地,适合追求强控制力的团队。
提示工程专家
by alirezarezvani
覆盖Prompt优化、Few-shot设计、结构化输出、RAG评测与Agent工作流编排,适合分析token成本、评估LLM输出质量,并搭建可落地的AI智能体系统。
✎ 把提示优化、LLM评测到RAG与智能体设计串成一套方法,适合想系统提升AI开发效率的人。
相关 MCP Server
知识图谱记忆
编辑精选by Anthropic
Memory 是一个基于本地知识图谱的持久化记忆系统,让 AI 记住长期上下文。
✎ 帮 AI 和智能体补上“记不住”的短板,用本地知识图谱沉淀长期上下文,连续对话更聪明,数据也更可控。
顺序思维
编辑精选by Anthropic
Sequential Thinking 是让 AI 通过动态思维链解决复杂问题的参考服务器。
✎ 这个服务器展示了如何让 Claude 像人类一样逐步推理,适合开发者学习 MCP 的思维链实现。但注意它只是个参考示例,别指望直接用在生产环境里。
PraisonAI
编辑精选by mervinpraison
PraisonAI 是一个支持自反思和多 LLM 的低代码 AI 智能体框架。
✎ 如果你需要快速搭建一个能 24/7 运行的 AI 智能体团队来处理复杂任务(比如自动研究或代码生成),PraisonAI 的低代码设计和多平台集成(如 Telegram)让它上手极快。但作为非官方项目,它的生态成熟度可能不如 LangChain 等主流框架,适合愿意尝鲜的开发者。