agent-bom discover snowflake
Inventory Snowflake AI Assets and Generate Standardized BOM
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: Inventory Snowflake AI Assets and Generate Standardized BOM Full Skill content: https://321skill.com/skills/agent-bom-discover-snowflake-x-6/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 uniformly inventorying AI assets within Snowflake environments. In practice, operations and data analytics teams often need visibility into the usage of AI-related resources such as Cortex, Snowpark, Notebooks, Streamlit, and MCP, but manual queries are inefficient and prone to omissions. This tool automatically discovers these assets and outputs a JSON inventory compliant with the agent-bom standard, providing a reliable foundation for subsequent audits and governance.
Usage is straightforward: simply invoke it via the command line or through an AI agent in an environment where agent-bom (with the snowflake extension) is installed. It leverages the operator's existing read-only credentials (prioritizing SSO, OAuth, or key pair authentication) to connect to Snowflake, executes a series of discovery queries, and finally writes the inventory to a JSON file you specify. The entire process requires no long-term credential exposure and makes no modifications to any Snowflake resources.
It is well-suited for teams or individuals who need to regularly inventory AI infrastructure, especially organizations already using services like Snowflake Cortex and Snowpark. Data analysts can quickly understand the current distribution of AI assets, operations engineers can use it for compliance audits and resource planning, and agent developers can integrate the standardized inventory into automated workflows.
It is recommended to ensure a Python 3.11+ environment before first use and install dependencies via pip install agent-bom[snowflake]. Note that this tool supports read-only operations only and will not modify any Snowflake resources. Also, prioritize using SSO or key pair authentication to avoid passing passwords or tokens in conversations.
Key Features
Unlike manually querying Snowflake system tables or using third-party BI tools, it automatically generates a standardized JSON inventory compliant with the agent-bom specification, without requiring long-term credentials—all authentication reuses the operator's existing SSO/OAuth/key pair context, and credentials never leave the local environment.
Limitations
Requires Python 3.11+, depends on the agent-bom library with the snowflake extension installed, supports read-only queries only, and cannot modify or create Snowflake resources.
FAQ
What permissions are required to use it?
The operator must provide Snowflake credentials with read-only permissions. Prioritize using SSO, OAuth, or key pair authentication, and avoid using passwords. It is recommended to use the SNOWFLAKE_PRIVATE_KEY_PATH or SNOWFLAKE_AUTHENTICATOR environment variables.
Which Snowflake objects does it support discovering?
It supports discovering Cortex, Snowpark, Notebooks, Streamlit, MCP, and AI observability-related assets, including query history, Cortex functions, Snowpark stored procedures, Streamlit applications, and more.
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-6/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-6/raw/index.md