Periodically self-assess output quality to catch degradation before the judge does.
Every {{assessment_interval}} iterations, self-assess:
If degrading: write assessment to _quality_log, re-read _working_notes,
change approach explicitly. If acceptable: brief note in _quality_log.
0c38749
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.