Debugging

This is a structured workflow for turning concrete failures into root-cause diagnoses. It guides you through reproduce, isolate, verify loops when you already have a failing command, test, or request and need to narrow down what broke. The skill includes mode-specific packets for regressions, flaky tests, and environment mismatches, plus clear handoff boundaries so you know when to route to log analysis, testing strategy, or performance work instead. It's designed for the middle phase of debugging where reproduction is possible but the cause is still unclear, and it pushes you to run one discriminating check per hypothesis rather than patching five things at once. Works best when the failure is concrete enough to retest.

skills.sh installs: 167
GitHub stars: 22
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add akillness/oh-my-skills --skill debugging --agent claude-code

Installs into .claude/skills of the current project.

Files

Debugging

Use this skill when the job is to turn a concrete failure into a bounded diagnosis loop.

The center of the skill is small and repeatable:

define the failing behavior in testable terms,
build or confirm the cheapest reliable reproducer,
isolate the narrowest failing boundary,
run one discriminating check per hypothesis,
verify the fix under the same conditions.

Read references/handoff-boundaries.md before taking work that may belong to log-analysis, testing-strategies, code-review, or performance-optimization. Read references/debug-loop.md for the full experiment-loop scaffolding. Read references/mode-selection-and-fast-checks.md when the case is clearly a regression, flake, env/config mismatch, or artifact-led investigation.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly