Build small, reproducible images: layer ordering for cache hits, multi-stage builds, pinning by digest, and why running as root is still the most common finding.
SkillScore59Maintained
Automatic
◆DevOps & SRE pack
Last verified 8/3/2026
What it changes
Passed 13 of 22 test cases with the skill, and 5 of 22 without it.
Without skill23%
With skill59%
Checks it passed that the model alone missed
The Dockerfile pins base images using sha256 digests.
The Dockerfile pins the base image using a sha256 digest.
The Dockerfile pins the alpine base image using a sha256 digest.
and 4 more in the full report
8 fixed5 passed either way9 still failing0 broke
Pass-rate lift
+36 pp
Tokens
+7%
Agent turns
0%
Response time
+5%
Model gemini-3.6-flashMeasured 8/3/2026v113 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
I want to make sure my Python service builds are fully reproducible and build times are minimized across CI runs. Can you provide a guide on optimal layer ordering along with a production-ready Dockerfile example?
What was checked, without and with the skill
Checked
Without skill
With skill
The Dockerfile pins the base image using a sha256 digest.
Passed
Passed
The response explains why running containers as root is a frequent security finding.
Missed
Passed
The Dockerfile copies requirements.txt before copying application source code.
Passed
Passed
case-02 · 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
docker-images
Build small, reproducible images: layer ordering for cache hits, multi-stage
builds, pinning by digest, and why running as root is still the most common
finding.