agent-bom ingest
Validate and import cloud resource 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 ingest. It is used for: Validate and import cloud resource inventory JSON Full Skill content: https://321skill.com/skills/agent-bom-ingest-x-10/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 challenges of fragmented and unreliable cloud resource inventory data. In real-world development, operations teams or agents often need to obtain inventory lists in JSON format from sources like AWS, Azure, GCP, Snowflake, or CMDB. However, manual validation is time-consuming and error-prone, often missing issues caused by schema inconsistencies or missing critical fields (e.g., discovery_provenance).
Usage is straightforward: simply provide the inventory JSON file to the AI. It will automatically invoke the agent-bom mcp validate command to check the schema, then execute agent-bom scan --inventory for a local scan, outputting findings in JSON, SARIF, HTML, or Markdown formats. You can then use natural language instructions to view audit reports, export compliance lists, or generate visual charts.
It is ideal for teams or individuals who need to manage multi-cloud assets uniformly, generate audit reports, or perform security and compliance checks. This is especially useful for developers or operations personnel who already have the agent-bom toolchain but need to quickly validate and import inventory data into their local AI workflows.
It is recommended to use this tool uniformly when receiving inventory JSON pushed from third parties. Note that it primarily relies on the local agent-bom environment (Python 3.11+ and agent-bom 0.84.4+) and will not automatically push data to the control plane unless the user explicitly provides a push URL and API Token.
Key Features
Unlike manually validating with the agent-bom command line, this Skill automates schema validation, scanning, and exporting through AI-powered natural language interaction, eliminating the need to remember complex parameters. It also includes built-in security reviews (such as requiring the `discovery_provenance` field) and a redaction mechanism to prevent accidental credential exposure.
Limitations
Requires Python 3.11+ and agent-bom 0.84.4+. The JSON must strictly adhere to the packaged `inventory.schema.json` contract; non-standard inventory file formats are not supported.
FAQ
Does this Skill require cloud platform access credentials?
No. It only validates and imports the JSON file provided by the user and does not require any cloud platform credentials. The optional push feature requires the user to provide their own agent-bom API Token, but it is not displayed in the conversation.
Which cloud platforms or data sources' inventory JSON are supported?
It supports JSON formats generated by AWS, Azure, GCP, Snowflake, CMDB, and endpoint collectors, as long as they conform to the agent-bom schema.
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-ingest-x-10/raw/index.md to read the original Skill definition (Markdown format) for agent-bom ingest, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-ingest-x-10/raw/index.md