The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes bash to run ast-grep, a tool for structural code searching, to analyze repository architecture and conventions. This is standard functionality for a development-focused agent.
[COMMAND_EXECUTION]: The instructions include examples of curl commands (e.g., curl -X POST /login) provided to the agent as suggested methods for verifying that defined acceptance criteria are met.
[PROMPT_INJECTION]: The skill ingests untrusted user input via the feature_description field to drive classification and discovery logic, creating a surface for indirect prompt injection.
Ingestion points: The feature_description variable defined in the Input YAML block.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the user input.
Capability inventory: The agent has access to shell execution (bash), file reading (ARCHITECTURE.md, etc.), and the ability to trigger other vendor skills (majestic-devops:devops-plan).
Sanitization: No specific validation or sanitization of the user-provided text is performed before it is used for logic branching.

blueprint-discovery