The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses authoritative language ("The Prime Directive", "Guardrails") to enforce a specific debugging workflow. These instructions are focused on technical rigor and do not attempt to bypass safety filters or override agent constraints.
[COMMAND_EXECUTION]: The protocol instructs the agent to use standard development commands such as git log, git diff, git bisect, and npm test to reproduce and isolate bugs. These are expected behaviors for a software diagnosis tool.
[DATA_EXPOSURE]: The documentation includes example file paths (e.g., /home/dev/project/...) and stack traces for illustrative purposes. No sensitive system paths or hardcoded credentials are present.
[SAFE]: The skill promotes security best practices, such as "Defense in Depth," which encourages multi-layered input validation and environmental guards to prevent destructive operations.

fault-diagnosis