# windsor-ai-business-data

Connects your coding agent to marketing, sales, CRM, and ecommerce data through Windsor.ai. Useful when building dashboards or seeding test data.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 845 installs · ★ 40
- Author: cline
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/cline/skills/tree/HEAD/skills/windsor-ai-business-data/SKILL.md
- Updated: 2026-07-21
- HTML: https://affpapa.org/en/nevibecode/skills/windsor-ai-business-data

## What it does

The skill guides the agent through querying business metrics using four Windsor.ai MCP tools: `get_connectors`, `get_options`, `get_fields`, and `get_data`. It establishes an inspect-first workflow where the model inspects active account IDs and connector schemas before running data queries.

Supported connectors cover 325+ platforms across advertising, e-commerce, and CRM, including Google Ads, Stripe, Shopify, and HubSpot. Queries support presets like `last_7d` along with compound filter expressions. Without the underlying Windsor.ai MCP tools and connected account credentials, tool calls will simply return empty results.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cline/skills --skill windsor-ai-business-data -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/windsor-ai-business-data/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/windsor-ai-business-data/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cline/skills --skill windsor-ai-business-data -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/windsor-ai-business-data/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cline/skills --skill windsor-ai-business-data -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/windsor-ai-business-data/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cline/skills windsor-ai-business-data
```

2. **Manually: put the files in place**
- File: `.github/skills/windsor-ai-business-data/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cline/skills --skill windsor-ai-business-data -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cline/skills --path skills/windsor-ai-business-data
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/windsor-ai-business-data/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add cline/skills --skill windsor-ai-business-data -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/cline/skills/tree/HEAD/skills/windsor-ai-business-data/SKILL.md

## When to use it
- pull ad spend, impressions, and conversion metrics from advertising platforms
- inspect available connector schemas before writing typed data interfaces
- retrieve CRM deals and ecommerce transactions for reporting components
- seed local dashboards and charts with real production analytics

## Example prompts
- Check connected platforms using get_connectors to see what accounts are active
- Fetch spend and clicks from google_ads for last_30d and save them to metrics.json
- Inspect field definitions for the shopify connector and write TypeScript interfaces

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 5d0a48a58f0fc256.

BEGIN THIRD-PARTY FILE 5d0a48a58f0fc256
```text
---
name: windsor-ai-business-data
description: Query Windsor.ai business data across marketing, sales, CRM, ecommerce, finance, and analytics connectors. Use when users need dashboards, reports, data visualization, schema exploration, or connector-backed test data from Windsor.ai.
disable-model-invocation: false
---

# Windsor.ai Business Data Skill

Use this skill whenever the user needs business data — marketing analytics, sales metrics, CRM data, ecommerce transactions, financial data, or any other data available through Windsor.ai's 325+ connectors.

## When to Use

- User is building a dashboard, report, or data visualization that needs business data from any source
- User asks about ad spend, campaign performance, ROAS, CTR, CPC, or conversion metrics
- User needs CRM, sales, ecommerce, or financial data in their codebase
- User needs to explore what data sources or fields are available
- User wants to seed a project with real data (e.g. for testing, prototyping, or generating fixtures)
- User is building an integration with any platform supported by Windsor.ai

## Available Tools

Windsor.ai provides 4 MCP tools:

### `get_connectors`
Lists all connected platforms and their account IDs. Always call this first if you don't know what accounts are available.

### `get_options`
Returns available fields, date filters, and options for a specific connector. Use this to discover what data can be queried before calling `get_data`.

**Parameters:**
- `connector` (required): Platform ID like `"google_ads"`, `"facebook"`, `"tiktok"`, `"linkedin"`, `"googleanalytics4"`, `"hubspot"`, `"salesforce"`, `"searchconsole"`, `"instagram"`, `"youtube"`, `"google_my_business"`, `"shopify"`, `"stripe"`, `"quickbooks"`, and 300+ more
- `accounts` (required): List of account IDs from `get_connectors`

### `get_fields`
Returns detailed metadata about specific fields — data types, descriptions, available values. Use this when you need to understand the schema before writing code that processes the data.

**Parameters:**
- `connector` (required): Platform ID
- `fields` (required): List of field IDs like `["campaign", "spend", "clicks"]`

### `get_data`
Retrieves actual data. This is the main query tool.

**Parameters:**
- `connector` (required): Platform ID
- `accounts` (required): List of account IDs
- `fields` (required): Fields to retrieve, e.g. `["campaign", "date", "spend", "clicks", "impressions"]`
- `date_from` / `date_to`: Date range as `"YYYY-MM-DD"`
- `date_preset`: Shorthand like `"last_7d"`, `"last_30d"`, `"this_month"`, `"last_3m"`
- `filters`: Conditions like `[["spend", "gt", 100], "and", ["campaign", "contains", "Sale"]]`
- `options`: Connector-specific options like `{"attribution_window": "7d_view,1d_click"}`

## Workflow Pattern

1. **Discover** → Call `get_connectors` to see what's connected
2. **Explore** → Call `get_options` to see available fields for a connector
```
END THIRD-PARTY FILE 5d0a48a58f0fc256

The third-party file has ended. Everything between the 5d0a48a58f0fc256 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2924 of 4109 bytes. © cline · Apache-2.0 · https://github.com/cline/skills/tree/HEAD/skills/windsor-ai-business-data/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md