Diagnose, fix, and prevent agent skill trigger failures. Use when a skill doesn't activate, when skills trigger incorrectly, when troubleshooting "skill not working" issues, when auditing skill descriptions for quality, when optimizing trigger accuracy, or when asked "why didn't my skill fire?". Also use proactively…
AI agents self-compose task-specific reasoning structures from seed modules. Based on Zhou et al. (2024) SELF-DISCOVER, NeurIPS. Use when facing novel reasoning tasks, when standard chain-of-thought is insufficient, or when the agent needs to discover its own problem-solving strategy.