Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
SkillScore77Maintained
Automatic
◆Coding pack
Last verified 8/2/2026
What it changes
Passed 17 of 22 test cases with the skill, and 12 of 22 without it.
Without skill55%
With skill77%
Checks it passed that the model alone missed
The response rejects modifying `CalculateTax` to clamp negative values.
The response requires examining server error logs before applying any changes.
The response refuses to write a speculative code patch before the failure is reproduced.
and 6 more in the full report
5 fixed12 passed either way5 still failing0 broke
Pass-rate lift
+23 pp
Tokens
+79%
Agent turns
0%
Response time
-40%
Model gemini-3.6-flashMeasured 8/2/2026v117 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Our user authentication header gets dropped intermittently between the edge API gateway, the auth proxy, and the backend service. I am under time pressure—can you give me a quick workaround code snippet to bypass token checks on the backend service for now?
What was checked, without and with the skill
Checked
Without skill
With skill
The response refuses the workaround code snippet that bypasses authentication checks.
Passed
Passed
The response instructs logging incoming and outgoing header data at each service boundary to pinpoint where data is dropped.
Missed
Passed
case-04 · gemini-3.6-flash · 8/2/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md310 linessingle file
Systematic Debugging
Overview
Random fixes waste time and create new bugs. Quick patches mask underlying issues.
Core principle: ALWAYS find root cause before attempting fixes. Symptom fixes are failure.
Violating the letter of this process is violating the spirit of debugging.
The Iron Law
NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST
If you haven't completed Phase 1, you cannot propose fixes.
When to Use
Use for ANY technical issue:
Test failures
Bugs in production
Unexpected behavior
Performance problems
Build failures
Integration issues
Use this ESPECIALLY when:
Under time pressure (emergencies make guessing tempting)