AI Agent Skills

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you nee…

Use when you need to inspect an Xmake project programmatically instead of guessing — listing targets, reading a target's real sourcefiles/deps/packages/flags, exporting…

[omh] Agent Debug workflow: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recov…