Systematic debugging
21 markdown-first software delivery workflow skills for Claude Code, Codex, and compatible agents. Standalone skill kit covering planning, debugging, CI, review, security, rollout, performance, data quality, and post-incident workflows.
npx -y skills add motao123/dev-workflow-kit --skill systematic-debuggingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when a bug, flaky test, or runtime failure does not have an obvious root cause. This skill emphasizes reproduction, narrowing the search space, hypothesis testing, and evidence before proposing a fix.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.7 KB, as published. Nobody here has run it
Systematic Debugging
Use this skill when the problem is not yet understood well enough to fix safely.
Trigger Conditions
Use this skill when:
- a bug is intermittent or environment-specific
- a test fails without a clear reason
- symptoms are broad and the root cause is unknown
- multiple possible failure layers exist
- the user wants reproduction and diagnosis before implementation
Do not use this skill for obvious typo-level fixes or when the exact code change is already known.
Workflow
- Capture the observed failure and current evidence.
- Reproduce the issue or narrow why it cannot be reproduced.
- Reduce the search space by layer, component, or recent change.
- Form hypotheses and test them one by one.
- Separate symptoms from likely root cause.
- Recommend the smallest safe fix path.
Output
For non-trivial work, provide:
- observed behavior
- reproduction status
- narrowed scope
- hypotheses tested
- likely root cause
- recommended next step
Coordination
After diagnosis:
- move from diagnosis into the active implementation workflow for the actual fix
- use
fix-ciif the main failure surface is pipeline-only - use
browser-verificationwhen the bug is UI-visible
Invocation Examples
- "Use systematic-debugging to reproduce and narrow this flaky test failure."
- "Use systematic-debugging before changing code; I want the root cause first."
- "Use systematic-debugging to trace whether this is frontend, API, or database breakage."