The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script located at ~/.claude/scripts/learning-db.py to retrieve routing and review telemetry. This script is an external dependency residing in a directory typically associated with the user's platform configuration environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which creates a potential surface for indirect prompt injection.\n
Ingestion points: The skill reads content from docs/what-didnt-work.md and queries telemetry from learning.db via an external script.\n
Boundary markers: None identified; the retrieved content is presented directly within the agent context without delimiters or warnings.\n
Capability inventory: The skill uses Bash, Read, Grep, and Glob tools to perform its reporting tasks.\n
Sanitization: No explicit sanitization or filtering of the ingested file content is mentioned before it is presented to the agent.

retro