From agentize
Provides a step-by-step debugging workflow for failing test cases, including backtracing, print debugging, and structured bug reporting via GitHub Issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentize:debug-reportThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
If you failed to pass a test case, you should:
If you failed to pass a test case, you should:
print statements to have the intermediate values printed to:
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-1 --plugin synthesys-lab-agentizeGuides active bug investigation using Code Complete's scientific debugging method: STABILIZE → LOCATE → HYPOTHESIZE → EXPERIMENT → FIX → TEST → SEARCH. Runs the failing test first, then forms testable hypotheses before editing.
Use when fixing a bug — enforces reproduce-first-then-fix discipline with a strict step-by-step protocol. Prevents wrong-approach loops by gating each step on success criteria.
Root cause analysis specialist for errors, test failures, and unexpected behavior. Captures stack traces, isolates failure locations, and provides code fixes.