Change structure without changing behaviour: identifying the seam, characterising with tests first, and stopping before the refactor becomes a rewrite.
SkillScore91Maintained
Automatic
◆Coding pack
Last verified 8/3/2026
What it changes
Passed 20 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill91%
Checks it passed that the model alone missed
Instructs identifying seams around XML parsing steps.
Instructs locating seams in the token consumption logic.
Instructs identifying seams around global state boundaries.
and 25 more in the full report
16 fixed4 passed either way1 still failing1 broke
Pass-rate lift
+68 pp
Tokens
-8%
Agent turns
0%
Response time
-1%
Model gemini-3.6-flashMeasured 8/3/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 16
Prompt
I have a bulky 500-line payment processing method in Python that has become hard to maintain. Can you help me clean up its internal structure so it's easier to read and extend, while ensuring we keep its existing behavior completely intact?
What was checked, without and with the skill
Checked
Without skill
With skill
Advises identifying seams to isolate internal dependencies before extracting code.
Missed
Passed
Recommends writing characterization tests to capture existing behavior before modifying code.
Passed
Passed
Advises stopping the restructuring process before it turns into a full system rewrite.
Missed
Passed
case-01 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md5 linessingle file
refactoring
Change structure without changing behaviour: identifying the seam,
characterising with tests first, and stopping before the refactor becomes a
rewrite.