The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches and executes the agentrc tool from the official Microsoft repository on GitHub via npx. This is a standard operation for utilizing the tool and its ecosystem.\n- [COMMAND_EXECUTION]: Invokes shell commands to run the agentrc CLI for generating readiness reports, scaffolding new policy files, and applying existing configurations. User-provided arguments for paths or packages are interpolated into these commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests external policy configurations (JSON) which customize the readiness scoring logic and could influence the output generated by downstream reporting agents.\n
Ingestion points: Policy files located at user-defined local paths or remote packages are accessed during the apply sub-command execution.\n
Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between the policy configuration and potential embedded instructions within the JSON content.\n
Capability inventory: The skill has the ability to execute shell commands via npx and pass results to the assess skill and ai-readiness-reporter agent.\n
Sanitization: The skill relies on the agentrc tool's internal schema validation and JSON parsing to ensure the integrity of the configuration data.

acreadiness-policy