← Back to Skills Marketplace
carlosarturoleon

Windsor.ai Analytics

by Carlos Leon · GitHub ↗ · v1.0.3
cross-platform ✓ Security Clean
558
Downloads
2
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install windsor-ai
Description
Connect to Windsor.ai MCP for natural language access to 325+ data sources including Facebook Ads, GA4, HubSpot, Shopify, and more.
Usage Guidance
This skill is internally consistent for connecting your Windsor.ai account via mcporter, but check a few operational details before installing: 1) Verify the source/trust of this skill (no homepage and 'Source: unknown' in the registry). 2) Confirm the API key's scope in Windsor.ai and create a least-privilege key if possible. 3) Prefer storing the key in a secure secrets manager or system keychain rather than shell rc files; the instructions already warn about this. 4) Note the metadata mismatch: SKILL.md declares WINDSOR_API_KEY as the primary env, but the registry metadata showed no primary credential — confirm which is authoritative. 5) The metadata lists mcporter as a required binary but the instructions use 'npx mcporter'; ensure you understand whether a global mcporter install is required in your environment. 6) Because the skill will edit/create ~/.clawdbot/.env and a project config/mcporter.json, review and back up those files if you have existing configurations. Absence of scanner findings only means there were no regex hits — it does not replace the checks above.
Capability Analysis
Type: OpenClaw Skill Name: windsor-ai Version: 1.0.3 The skill bundle is benign. It provides instructions for connecting to the Windsor.ai API using an API key, configuring the `mcporter` tool, and querying data. The `SKILL.md` file includes clear setup steps, usage examples, and troubleshooting tips. Notably, it contains a 'Security note' advising against insecure storage of the API key, which is a positive indicator of security awareness. All commands and instructions are directly related to the stated purpose of integrating with Windsor.ai and do not exhibit any malicious intent, prompt injection attempts, or unauthorized actions.
Capability Assessment
Purpose & Capability
The name/description (Windsor.ai MCP access) matches the requested environment variable (WINDSOR_API_KEY) and the instructions (configure mcporter to point at https://mcp.windsor.ai). Requiring npx/node is reasonable for running mcporter via npx. No unrelated credentials or unrelated binaries are requested.
Instruction Scope
The SKILL.md instructs writing the API key to ~/.clawdbot/.env, exporting WINDSOR_API_KEY, and adding a windsor-ai entry to a project config/mcporter.json. Those file writes and the export are expected for this integration, but you should be aware the skill instructs modifying a project config and creating a local env file (it does not instruct reading unrelated system files).
Install Mechanism
This is an instruction-only skill with no install spec and no downloadable code, which is the lowest-risk install model.
Credentials
Only a single service credential (WINDSOR_API_KEY) is required, which is proportionate. Minor metadata mismatch: the SKILL.md metadata declares openclaw.primaryEnv as WINDSOR_API_KEY, but the registry summary listed 'Primary credential: none' — this is a metadata inconsistency to confirm before install.
Persistence & Privilege
always:false and no install that makes the skill persistent system-wide. The skill does instruct updating project config files and creating a local env file, which is normal for this type of connector and does not by itself indicate elevated privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install windsor-ai
  3. After installation, invoke the skill by name or use /windsor-ai
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Updated metadata to include openclaw compatibility and revised credentials section. - No changes to core functionality or usage instructions.
v1.0.2
- Improved security guidance for API key storage; now recommends using environment variables or secured `.env` files instead of shell rc files. - Updated environment setup instructions to emphasize security best practices and avoid exposing secrets in shell startup scripts. - Added a security note under setup with advice on restricting secret access and suggested alternatives for secret management. - Updated `metadata` to specify required binaries (`mcporter`, `npx`, `node`) and clarified primary credential (`WINDSOR_API_KEY`).
v1.0.1
windsor-ai v1.0.1 - Documentation (SKILL.md) updated with minor edits and formatting improvements. - Reference link added for Windsor.ai. - No changes to functionality or setup steps. - Removed the sample config/mcporter.json file.
v1.0.0
Initial release of the Windsor.ai skill. - Connects to Windsor.ai MCP for natural language access to data from 325+ sources, including Facebook Ads, GA4, HubSpot, and Shopify. - Provides detailed setup instructions for API key configuration and mcporter integration. - Supports queries on campaign performance, spend analysis, sales pipeline, e-commerce, trend analysis, and cross-channel attribution. - Includes templates for weekly, monthly, and client-ready performance reports. - Offers troubleshooting steps for authentication and configuration issues.
Metadata
Slug windsor-ai
Version 1.0.3
License
All-time Installs 1
Active Installs 1
Total Versions 4
Frequently Asked Questions

What is Windsor.ai Analytics?

Connect to Windsor.ai MCP for natural language access to 325+ data sources including Facebook Ads, GA4, HubSpot, Shopify, and more. It is an AI Agent Skill for Claude Code / OpenClaw, with 558 downloads so far.

How do I install Windsor.ai Analytics?

Run "/install windsor-ai" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Windsor.ai Analytics free?

Yes, Windsor.ai Analytics is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Windsor.ai Analytics support?

Windsor.ai Analytics is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Windsor.ai Analytics?

It is built and maintained by Carlos Leon (@carlosarturoleon); the current version is v1.0.3.

💬 Comments