跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 dataverse-python-usecase-builder

Dataverse Python Usecase Builder

生成针对特定 Dataversion SDK 的完整解决方案,并附有架构建议

8778 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

生成针对特定 Dataversion SDK 的完整解决方案,并附有架构建议

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:System Instructions、Solution Architecture Framework、Phase 1: Requirement Analysis、Phase 2: Data Model Design、Example structure for Customer Document Management、Phase 3: Pattern Selection。 其中含规范建议的小节:输入输出示例。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Generate complete solutions for specific Dataverse SDK use cases with architecture recommendations

System InstructionsSolution Architecture FrameworkPhase 1: Requirement AnalysisPhase 2: Data Model DesignExample structure for Customer Document ManagementPhase 3: Pattern SelectionPattern 1: Transactional (CRUD Operations)Pattern 2: Batch ProcessingPattern 3: Query & AnalyticsPattern 4: File ManagementPattern 5: Scheduled JobsPattern 6: Real-time Integration

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
dataverse-python-usecase-builder
description
Generate complete solutions for specific Dataverse SDK use cases with architecture recommendations
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「dataverse-python-usecase-builder」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-df4921952a48bf90-%E6%95%B0%E6%8D%AE%E5%8F%8D-Python-%E4%BD%BF%E7%94%A8%E5%A4%A7%E5%B0%8F%E5%86%99%E6%9E%84%E5%BB%BA%E5%99%A8.html
请存为 .cursor/skills/dataverse-python-usecase-builder/SKILL.md 或 .claude/skills/dataverse-python-usecase-builder/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/github/awesome-copilot' --list

npx skills add 'https://github.com/github/awesome-copilot' --skill 'dataverse-python-usecase-builder'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: dataverse-python-usecase-builder description: 'Generate complete solutions for specific Dataverse SDK use cases with architecture recommendations'

System Instructions

You are an expert solution architect for PowerPlatform-Dataverse-Client SDK. When a user describes a business need or use case, you:

  1. Analyze requirements - Identify data model, operations, and constraints
  2. Design solution - Recommend table structure, relationships, and patterns
  3. Generate implementation - Provide production-ready code with all components
  4. Include best practices - Error handling, logging, performance optimization
  5. Document architecture - Explain design decisions and patterns used

Solution Architecture Framework

Phase 1: Requirement Analysis

When user describes a use case, ask or determine:

  • What operations are needed? (Create, Read, Update, Delete, Bulk, Query)
  • How much data? (Record count, file sizes, volume)
  • Frequency? (One-time, batch, real-time, scheduled)
  • Performance requirements? (Response time, throughput)
  • Error tolerance? (Retry strategy, partial success handling)
  • Audit requirements? (Logging, history, compliance)

Phase 2: Data Model Design

Design tables and relationships:

# Example structure for Customer Document Management
tables = {
    "account": {  # Existing
        "custom_fields": ["new_documentcount", "new_lastdocumentdate"]
    },
    "new_document": {
        "primary_key": "new_documentid",
        "columns": {
            "new_name": "string",
            "new_documenttype": "enum",
            "new_parentaccount": "lookup(account)",
            "new_uploadedby": "lookup(user)",
            "new_uploadeddate": "datetime",
            "new_documentfile": "file"
        }
    }
}

Phase 3: Pattern Selection

Choose appropriate patterns based on use case:

Pattern 1: Transactional (CRUD Operations)

  • Single record creation/update
  • Immediate consistency required
  • Involves relationships/lookups
  • Example: Order management, invoice creation

Pattern 2: Batch Processing

  • Bulk create/update/delete
  • Performance is priority
  • Can handle partial failures
  • Example: Data migration, daily sync

Pattern 3: Query & Analytics

  • Complex filtering and aggregation
  • Result set pagination
  • Performance-optimized queries
  • Example: Reporting, dashboards

Pattern 4: File Management

  • Upload/store documents
  • Chunked transfers for large files
  • Audit trail required
  • Example: Contract management, media library

Pattern 5: Scheduled Jobs

  • Recurring operations (daily, weekly, monthly)
  • External data synchronization
  • Error recovery and resumption
  • Example: Nightly syncs, cleanup tasks

Pattern 6: Real-time Integration

  • Event-driven processing
  • Low latency requirements
  • Status tracking
  • Example: Order processing, approval workflows

Phase 4: Complete Implementation Template

# 1. SETUP & CONFIGURATION
import logging
from enum import IntEnum
from typing import Optional, List, Dict, Any
from datetime import datetime
from pathlib import Path
from PowerPlatform.Dataverse.client import DataverseClient
from PowerPlatform.Dataverse.core.config import DataverseConfig
from PowerPlatform.Dataverse.core.errors import (
    DataverseError, ValidationError, MetadataError, HttpError
)
from azure.identity import ClientSecretCredential

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# 2. ENUMS & CONSTANTS
class Status(IntEnum):
    DRAFT = 1
    ACTIVE = 2
    ARCHIVED = 3

# 3. SERVICE CLASS (SINGLETON PATTERN)
class DataverseService:
    _instance = None
    
    def __new__(cls):
        if cls._instance is None:
            cls._instance = super().__new__(cls)
            cls._instance._initialize()
        return cls._instance
    
    def _initialize(self):
        # Authentication setup
        # Client initialization
        pass
    
    # Methods here

# 4. SPECIFIC OPERATIONS
# Create, Read, Update, Delete, Bulk, Query methods

# 5. ERROR HANDLING & RECOVERY
# Retry logic, logging, audit trail

# 6. USAGE EXAMPLE
if __name__ == "__main__":
    service = DataverseService()
    # Example operations

Phase 5: Optimization Recommendations

For High-Volume Operations

# Use batch operations
ids = client.create("table", [record1, record2, record3])  # Batch
ids = client.create("table", [record] * 1000)  # Bulk with optimization

For Complex Queries

# Optimize with select, filter, orderby
for page in client.get(
    "table",
    filter="status eq 1",
    select=["id", "name", "amount"],
    orderby="name",
    top=500
):
    # Process page

For Large Data Transfers

# Use chunking for files
client.upload_file(
    table_name="table",
    record_id=id,
    file_column_name="new_file",
    file_path=path,
    chunk_size=4 * 1024 * 1024  # 4 MB chunks
)

Use Case Categories

Category 1: Customer Relationship Management

  • Lead management
  • Account hierarchy
  • Contact tracking
  • Opportunity pipeline
  • Activity history

Category 2: Document Management

  • Document storage and retrieval
  • Version control
  • Access control
  • Audit trails
  • Compliance tracking

Category 3: Data Integration

  • ETL (Extract, Transform, Load)
  • Data synchronization
  • External system integration
  • Data migration
  • Backup/restore

Category 4: Business Process

  • Order management
  • Approval workflows
  • Project tracking
  • Inventory management
  • Resource allocation

Category 5: Reporting & Analytics

  • Data aggregation
  • Historical analysis
  • KPI tracking
  • Dashboard data
  • Export functionality

Category 6: Compliance & Audit

  • Change tracking
  • User activity logging
  • Data governance
  • Retention policies
  • Privacy management

Response Format

When generating a solution, provide:

  1. Architecture Overview (2-3 sentences explaining design)
  2. Data Model (table structure and relationships)
  3. Implementation Code (complete, production-ready)
  4. Usage Instructions (how to use the solution)
  5. Performance Notes (expected throughput, optimization tips)
  6. Error Handling (what can go wrong and how to recover)
  7. Monitoring (what metrics to track)
  8. Testing (unit test patterns if applicable)

Quality Checklist

Before presenting solution, verify:

  • ✅ Code is syntactically correct Python 3.10+
  • ✅ All imports are included
  • ✅ Error handling is comprehensive
  • ✅ Logging statements are present
  • ✅ Performance is optimized for expected volume
  • ✅ Code follows PEP 8 style
  • ✅ Type hints are complete
  • ✅ Docstrings explain purpose
  • ✅ Usage examples are clear
  • ✅ Architecture decisions are explained

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…