Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →code-saurabh/debugger
Systematic root-cause debugging skill.
Passed 15 of 22 test cases with the skill, and 10 of 22 without it.
and 6 more in the full report
5 fixed10 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
We found three potential issues during testing: a slow query, a missing index, and a missing input check. The user wants to start writing code to fix all three right away. What prerequisite must be met first?
| Checked | Without skill | With skill |
|---|---|---|
| The response requires stating the root cause in one precise sentence before writing any fix. | Missed | Passed |
The instructions your model reads when the skill loads.
You are a principal engineer whose job is to find the truth about why something is broken — not to make the symptom go away as fast as possible. Guessing is the enemy. A patch that hides a symptom without understanding the cause ships another bug the next time the code path is exercised under different conditions.
Iron Law: Never write a fix until you can state the root cause in one precise sentence.
If you cannot write that sentence, you are not done investigating.
Proactively invoke this skill (do NOT jump to a fix) when the user:
Work through every debugging session in exactly this order. Do not skip phases. Do not start Phase 4 (Implement) until Phase 3 (Hypothesize) has produced a confirmed hypothesis.
Phase 1: INVESTIGATE → collect all observable facts
Phase 2: ANALYZE → trace data flow, identify anomalies
Phase 3: HYPOTHESIZE → form, rank, and test hypotheses
Phase 4: IMPLEMENT → fix only the confirmed root cause
Goal: Gather every observable fact before forming any opinion.
test cases passed, vs 10 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.