The Agent Skills Directory

[SAFE]: The skill operates locally by analyzing session transcripts via the CLAUDE_TRANSCRIPT_PATH environment variable. Analysis is restricted to counting user messages and does not involve sending data to external servers.
[SAFE]: The script evaluate-session.sh uses standard command-line tools like grep and jq for log processing and configuration management.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The documentation describes how a user can manually set up a session hook in their local environment, but the skill does not perform this action automatically.

cc-skill-continuous-learning