The Agent Skills Directory

[SAFE]: The skill provides a structured framework for debugging technical issues, prioritizing root cause analysis over symptom-based fixes. All included files, such as the find-polluter.sh script and the condition-based-waiting-example.ts TypeScript file, serve legitimate development and troubleshooting purposes.
[COMMAND_EXECUTION]: The skill includes a shell script (find-polluter.sh) and several command-line examples in SKILL.md and root-cause-tracing.md. These are standard diagnostic tools (e.g., npm test, git init, env | grep, codesign) intended for local use by the agent during debugging sessions and do not pose a security risk in this context.
[PROMPT_INJECTION]: The skill uses strong instructional language, such as 'The Iron Law' and 'Violating the letter of this process is violating the spirit of debugging,' to ensure the agent follows the methodology. The inclusion of 'Pressure Tests' is a safe training mechanism to help the agent resist user pressure to take shortcuts, rather than a malicious injection attempt.

systematic-debugging