The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/check.py uses subprocess.run() to execute internal validation scripts and the trace reporting tool. It specifically runs validate_skill.py, validate_evals.py, and trace_report.py using the current Python interpreter.
[SAFE]: The skill accesses configuration files such as SKILL.md and evals/evals.json of peer skills within the repository. This cross-skill file reading is necessary for its stated purpose of identifying coverage gaps across the fleet and does not involve sensitive user data or external exfiltration.
[SAFE]: No network operations, credential harvesting, or obfuscation techniques were detected. All operations are restricted to the local file system and execution of known internal scripts.

skill-trace-debugger