Salesforce报告助手

salesforce-reporting-copilot

by breynol01

Generate a Salesforce report blueprint from real org metadata. Use this skill when someone asks to build a report in Salesforce, understand how to query their org's data, map objects to a reporting question, or get started with SFDC CLI metadata pulls. Triggers on phrases like "build a Salesforce report", "how do I report on X in Salesforce", "pull Salesforce metadata", "what objects do I need for this report", "SFDC CLI setup", "understand my org schema", or "create a report blueprint".

4.5k数据与存储未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/breynol01/salesforce-reporting-copilot

文档

Salesforce Reporting Copilot

Generate a Report Blueprint from real Salesforce org metadata. Given an org and a reporting question, map the right objects, fields, and relationships — then produce a blueprint you can build in Salesforce Report Builder immediately.

Workflow

Step 1 — Authenticate and pull org metadata

bash
# Verify CLI auth
sf org list

# Pull object list
sf sobject list --target-org <alias>

# Describe a specific object (fields, relationships, picklists)
sf sobject describe --sobject <ObjectName> --target-org <alias>

# Pull report types available in the org
sf data query --query "SELECT Id, Name, BaseObject FROM ReportType LIMIT 200" --target-org <alias>

See references/cli-reference.md for full command patterns, flags, and troubleshooting.

Step 2 — Map the reporting question to objects

Given the user's question (e.g. "I want to see which volunteers are missing certifications"):

  1. Identify the primary object (the thing being counted or filtered)
  2. Identify related objects needed via lookup/master-detail joins
  3. Note any formula fields or rollup summaries that pre-aggregate the data
  4. Flag any missing fields or relationships that would require a new custom field

See references/object-mapping.md for common Salesforce object patterns and report type selection guidance.

Step 3 — Produce the Report Blueprint

Output a structured blueprint:

code
## Report Blueprint: [Question]

**Report Type:** [Standard or custom report type name]
**Primary Object:** [e.g. Contact]
**Related Objects:** [e.g. Account (lookup), Certification__c (child)]

### Columns
| Field Label | API Name | Object | Notes |
|---|---|---|---|
| Full Name | Name | Contact | |
| Certification Status | Certification_Status__c | Certification__c | May need custom field |

### Filters
- [Field]: [Operator] [Value]

### Grouping / Summary
- Group by: [Field]
- Summary: [Count/Sum/etc.]

### Gaps / Blockers
- [Any missing fields, permissions, or relationships]

Constraints

  • Run sf sobject describe before making field claims — never assume field API names
  • If the user's question can't be answered with existing fields, say so clearly and suggest what needs to be built
  • Do not fabricate object or field names; always pull from live org metadata
  • If the user has no SF CLI auth configured, walk them through sf org login web first (see references/cli-reference.md)

相关 Skills

技术栈评估

by alirezarezvani

Universal
热门

对比框架、数据库和云服务,结合 5 年 TCO、安全风险、生态活力与迁移复杂度做量化评估,适合技术选型、栈升级和替换路线决策。

帮你系统比较技术栈优劣,不只看功能,还把TCO、安全性和生态健康度一起量化,选型和迁移决策更稳。

数据与存储
未扫描15.8k

资深数据科学家

by alirezarezvani

Universal
热门

覆盖实验设计、特征工程、预测建模、因果推断与模型评估,适合用 Python/R/SQL 做 A/B 测试、时序分析和生产级 ML 落地,支撑数据驱动决策。

从 A/B 测试、因果分析到预测建模一条龙搞定,既有硬核统计方法也懂业务沟通,特别适合把数据结论真正落地。

数据与存储
未扫描15.8k

资深架构师

by alirezarezvani

Universal
热门

适合系统设计评审、ADR记录和扩展性规划,分析依赖与耦合,权衡单体或微服务、数据库与技术栈选型,并输出Mermaid、PlantUML、ASCII架构图。

搞系统设计、技术选型和扩展规划时,用它能更快理清架构决策与依赖关系,还能直接产出 Mermaid/PlantUML 图,方案讨论效率很高。

数据与存储
未扫描15.8k

相关 MCP 服务

SQLite 数据库

编辑精选

by Anthropic

热门

SQLite 是让 AI 直接查询本地数据库进行数据分析的 MCP 服务器。

这个服务器解决了 AI 无法直接访问 SQLite 数据库的问题,适合需要快速分析本地数据集的开发者。不过,作为参考实现,它可能缺乏生产级的安全特性,建议在受控环境中使用。

数据与存储
86.1k

by Anthropic

热门

PostgreSQL 是让 Claude 直接查询和管理你的数据库的 MCP 服务器。

这个服务器解决了开发者需要手动编写 SQL 查询的痛点,特别适合数据分析师或后端开发者快速探索数据库结构。不过,由于是参考实现,生产环境使用前务必评估安全风险,别指望它能处理复杂事务。

数据与存储
86.1k

by Firecrawl

热门

Firecrawl 是让 AI 直接抓取网页并提取结构化数据的 MCP 服务器。

它解决了手动写爬虫的麻烦,让 Claude 能直接访问动态网页内容。最适合需要实时数据的研究者或开发者,比如监控竞品价格或抓取新闻。但要注意,它依赖第三方 API,可能涉及隐私和成本问题。

数据与存储
6.4k

评论