The Agent Skills Directory

[SAFE]: The skill operates as a purely local session observer. It tracks conversation history to generate retention and future-planning questions, storing them in a local JSON file (question-builder-log.json).
[DATA_EXPOSURE]: The skill explicitly instructs the agent to store 'public' questions and avoid writing private reasoning or sensitive content to the artifact. It also specifies that tracking should happen silently without external service calls (e.g., no curl or external APIs), which mitigates exfiltration risks.
[PROMPT_INJECTION]: No malicious prompt injection patterns were detected. The skill uses standard instructional language to define its role as a silent observer and provides clear triggers (/question-builder, /question-builder-notes, /question-builder-end).
[COMMAND_EXECUTION]: There are no shell commands, script executions, or dynamic context injections identified. The skill's primary function is text processing and JSON generation within the agent's memory environment.

question-builder