The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (capture_triage.py and capture_audit.py) and standard shell commands (mkdir) to process task logs. These operations are limited to the skill's local assets and the project's build environment.
[SAFE]: The Python scripts rely exclusively on standard libraries such as argparse, json, re, and pathlib. They perform deterministic text analysis and do not engage in network communication or access sensitive system files.
[SAFE]: All instructional content, workflows, and sample data are presented in clear text with no evidence of prompt injection, obfuscation, or persistence mechanisms.

capture