agent-bom discover snowflake
Discover Snowflake AI assets and generate standardized inventory JSON
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: agent-bom discover snowflake. It is used for: Discover Snowflake AI assets and generate standardized inventory JSON Full Skill content: https://321skill.com/skills/agent-bom-discover-snowflake-x-8/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the challenge of fragmented and difficult-to-manage Snowflake AI assets. In practice, when enterprises utilize AI features like Snowflake Cortex, Snowpark, Notebook, Streamlit, and MCP, assets are scattered across different accounts and warehouses, lacking a standardized inventory. This leads to difficulties in auditing, opaque cost tracking, and increased compliance risks. By automatically discovering and generating a standardized agent-bom inventory, you can quickly gain a comprehensive view of your AI infrastructure.
Usage is straightforward. You simply need to install agent-bom and configure Snowflake read-only credentials (SSO, OAuth, or key pair authentication is recommended). You can then trigger the discovery process using natural language instructions, such as "Inventory the Cortex AI assets in my Snowflake account." It will automatically connect to Snowflake, execute read-only queries, scan assets related to Cortex, Snowpark, Notebook, Streamlit, MCP, and AI observability, and finally output a JSON inventory file compliant with the agent-bom specification to a specified path.
It is ideal for data analysts, operations engineers, and agent development teams who need to manage Snowflake AI infrastructure, especially organizations that have deployed services like Snowflake Cortex or Snowpark but lack a unified asset view. Whether for compliance audits, cost accounting, or providing foundational data for AI governance, this Skill significantly improves efficiency.
Before first use, ensure you have a Python 3.11+ environment and that the agent-bom Snowflake extension is installed. Prioritize using SSO or key pair authentication during setup to avoid passing passwords in conversations. Note that it performs read-only discovery operations only and will not modify any Snowflake resources. The output path is user-specified to ensure data security.
Key Features
Unlike Snowflake's native INFORMATION_SCHEMA, it specifically focuses on AI and Cortex assets (such as Cortex Search, Snowpark Container Services) and outputs a standardized agent-bom inventory JSON, facilitating subsequent scanning, integration into CI/CD, or import into governance platforms.
Limitations
Requires Python 3.11+, depends on the agent-bom library (with the snowflake extension installed), supports read-only discovery only (cannot modify or delete Snowflake resources), and requires the operator to have read-only access to the Snowflake account.
FAQ
How do I configure Snowflake authentication?
SSO, OAuth, or key pair authentication is recommended. Set environment variables like SNOWFLAKE_PRIVATE_KEY_PATH or SNOWFLAKE_AUTHENTICATOR to avoid using passwords. Please refer to the agent-bom documentation for specifics.
Which Snowflake assets are supported for discovery?
It supports Cortex AI (e.g., Cortex Search, Cortex Analyst), Snowpark, Notebook, Streamlit, MCP services, and AI observability-related assets.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agent-bom-discover-snowflake-x-8/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover snowflake, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-snowflake-x-8/raw/index.md