agent-bom discover snowflake
Discover Snowflake AI assets and generate standardized inventory
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 Full Skill content: https://321skill.com/skills/agent-bom-discover-snowflake-x-4/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 difficulty of inventorying Snowflake AI infrastructure assets. In real-world operations, AI-related resources such as Cortex, Snowpark, Notebook, Streamlit, and MCP are scattered across multiple accounts and warehouses. Manual collection is prone to omissions and inconsistent formatting, making it hard to integrate into automated audit or migration workflows.
Usage is straightforward. Ensure you have Python 3.11+ installed with the agent-bom library and its Snowflake extension (pip install agent-bom[snowflake]). Then, run snowflake_inventory_adapter.py from the command line, providing your account and read-only credentials (preferring SSO, OAuth, or key-pair authentication). It will automatically scan and output a JSON inventory file compliant with the agent-bom specification to a specified path. The entire process requires no long-term credentials; credentials exist only in the operator's environment.
It is well-suited for operations engineers, data analysts, and agent development teams who need to regularly inventory Snowflake AI assets. Organizations already using Snowflake for AI workloads and requiring compliance audits, cost accounting, or pre-migration assessments can significantly reduce manual inventory time.
We recommend using this tool during major version upgrades or quarterly audits. Note that it is designed for read-only discovery and will not modify any Snowflake resources. Always avoid passing passwords or private keys in chat; use environment variables or configuration files for credential management.
Key Features
Unlike native Snowflake INFORMATION_SCHEMA queries, it outputs a standardized agent-bom inventory JSON that can be directly consumed by downstream tools (e.g., asset management systems, compliance scanners), without requiring the creation of long-term credentials or storage of sensitive information within Snowflake.
Limitations
Requires Python 3.11+, depends on the agent-bom library and its Snowflake extension, supports read-only operations only, and cannot discover resources in unauthorized accounts or across organizations.
FAQ
How do I install this Skill?
Run `pip install agent-bom[snowflake]` to install agent-bom and its Snowflake dependencies.
What permissions are required?
The operator must provide Snowflake read-only credentials. Prefer using SSO, OAuth, or key-pair authentication; avoid using passwords.
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-4/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-4/raw/index.md