The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructional logic for using shell utilities jq and sed to programmatically extract specific lines from documentation files based on a JSON index.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from local documentation files, which creates an attack surface for indirect prompt injection. Ingestion points: Reads content from /.claude/docs/workflow.md and /.claude/docs/testing.md (as specified in the Guideline Index). Boundary markers: None identified; the skill fetches and presents raw lines from the documentation files without explicit delimiters. Capability inventory: The skill utilizes Read and Grep tools and provides specific shell-based logic (sed, jq) for data retrieval. Sanitization: No explicit sanitization or validation of the retrieved file content is performed before it is integrated into the agent's context.

tdd-reference