The Agent Skills Directory

[SAFE]: The skill implements disable-model-invocation: true in its YAML frontmatter, which is a defensive configuration that prevents the agent from delegating tasks to other models during the specification generation process.
[PROMPT_INJECTION]: The skill operates on untrusted data from the conversation history and the codebase, which represents an indirect prompt injection surface.
Ingestion points: SKILL.md directs the agent to gather and analyze the current conversation context and codebase understanding.
Boundary markers: There are no specific delimiters or instructions used to separate untrusted source data from the agent's core instructions.
Capability inventory: The agent is authorized to publish the generated specification content to an external project issue tracker.
Sanitization: No sanitization or validation of the processed data is specified before it is published to the external tracker.

to-spec