The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gh CLI to interact with GitHub repository features. It executes commands to create issues, create labels, and modify issue labels (gh issue create, gh label create, gh issue edit). These are standard operations for a development-focused agent.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests content from external repository files to generate its output.
Ingestion points: Reads GLOSSARY.md, GLOSSARY-MAP.md, and Architecture Decision Records (ADRs) found in the docs/adr/ or src/*/docs/adr/ directories (SKILL.md).
Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to distinguish between the contents of these files and the core instructions.
Capability inventory: The skill can create and edit issues on the GitHub repository using the gh CLI.
Sanitization: No specific sanitization, filtering, or validation of the ingested documentation content is performed before the model synthesizes it into a specification.

to-spec