The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a shell script (evaluate-session.sh) designed to run at the conclusion of a session via a configured hook. This script performs metadata analysis on session transcripts, specifically counting messages to determine if extraction thresholds are met.
[SAFE]: The skill operates locally within the user's directory structure (~/.claude/skills/learned/). It does not perform any network operations or external data transmissions.
[SAFE]: No evidence of prompt injection, obfuscation, or credential harvesting was found. The skill's behavior aligns with its stated purpose of continuous learning and pattern extraction.

continuous-learning