Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From devcore
Systematic debugging strategies for hard-to-find bugs using rubber ducking, code flow tracing, hypothesis testing, and targeted logging. Activates when stuck on bugs that resist quick fixes.
npx claudepluginhub crouton-labs/crouton-kit --plugin devcoreHow this skill is triggered — by the user, by Claude, or both
Slash command
/devcore:debuggingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Quote code snippets and explain what each chunk *should* do vs *actually* does. Don't assume—verbalize the logic. Discrepancies reveal bugs.
Provides systematic debugging framework for root cause analysis after 2+ failed fixes, complex failures, intermittent bugs, and circular debugging.
Guides blackbox debugging: confirms AS-IS/TO-BE symptoms, traces callstacks step-by-step in trace.md, explores branches heuristically then exhaustively, verifies fixes via red-green tests.
Systematic debugging methodology for finding and fixing bugs through root cause analysis. Covers reproduce-investigate-hypothesize-fix-prevent workflow, evidence-based diagnosis, and bug category strategies.
Share bugs, ideas, or general feedback.
Quote code snippets and explain what each chunk should do vs actually does. Don't assume—verbalize the logic. Discrepancies reveal bugs.
Trace data from entry point to failure. At each transformation: what goes in, what comes out? Mark where expectations diverge.
Failure-prone boundaries: async, serialization, type coercion, null propagation, state mutations.
Don't change code hoping it helps—that creates noise.
Log at decision points and async boundaries, not everywhere.
Workflow:
For complex/unfamiliar code sections acting as a blackbox:
When stuck: Spawn 2-3 senior-advisor agents in parallel with different perspectives (pragmatist, architect, skeptic).
Avoid biasing agents: Pass them relevant file paths and the observed behavior, but not your hypotheses or assumptions. Let them form independent conclusions.
If no, keep investigating.