Skill Fire Debugger

This skill provides a high-speed diagnostic engine for troubleshooting “misfires”—situations where an AI agent fails to trigger a specific skill despite the user’s intent. It systematically analyzes the interaction against seven common failure modes, such as description truncation, trigger word mismatch, or configuration errors. Debugging agent behavior is often a manual process of trial and error. This skill automates that friction by acting as a “Linter for Agent Skills.” Instead of guessing why an agent ignored a tool, you get a developer-centric report including the specific evidence for the failure and a copy-paste-ready fix. It prevents “model hallucination” where the agent tries to perform a task manually instead of using the optimized skill you already built. While designed with the Claude Skill specification in mind (supporting frontmatter and character budget constraints), the logic applies to any agent framework using tool-calling or slash commands where discoverability is driven by text descriptions. The skill yields a standardized four-line block: the LIKELY CAUSE, EVIDENCE found in the logs/prompt, a concrete FIX, and a VERIFY step to ensure the problem is solved.