Use when a large feature, story, plan, or spec idea needs to be split into small vertical slices with the Hamburger Method. This should trigger for requests such as Split this oversized story; Find the smallest useful slice; Break this feature into vertical slices; Apply the Hamburger Method; Turn this broad plan into tracked slices. Part of Plinth Toolkit
SkillScore91Maintained
Automatic
◆Product Management pack
Last verified 8/20/2026
What it changes
Passed 20 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill91%
Checks it passed that the model alone missed
Performs a self-check on the slices covering value and testability
Routes spec or task follow-ups through appropriate planning skills
Keeps specification tracking separate from general issue management
and 16 more in the full report
12 fixed8 passed either way1 still failing1 broke
Pass-rate lift
+50 pp
Tokens
+28%
Agent turns
0%
Response time
-7%
Model gemini-3.6-flashMeasured 8/20/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
We completed slicing our large Java audit logging feature using the Hamburger Method and now need detailed implementation task planning. Which routing or planning step should follow?
What was checked, without and with the skill
Checked
Without skill
With skill
Directs detailed implementation planning through the designated plan mode planning workflow
Missed
Passed
Maintains distinction between slice design and downstream execution planning
Passed
Passed
case-14 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md65 lines2 files
Hamburger Method Design
Guide Java teams through the Hamburger Method for splitting oversized work into small, valuable, end-to-end vertical slices. This is an interactive SKILL.
What is covered in this Skill?
Recognizing oversized feature, story, plan, or spec work
Identifying 3-6 functional or workflow layers that participate in delivering value
Generating 4-5 implementation or quality options per layer
Challenging scope with the smallest useful version question
Filtering options that are too costly, redundant, irreversible, or unnecessary for early learning
Composing one first vertical slice and follow-up slices
Self-checking value, size, testability, deliverability, and issue-tracking suitability
Routing plan, OpenSpec, GitHub issue, and Jira follow-up through the existing planning skills
Constraints
Split oversized work into vertical slices that deliver observable value, not isolated horizontal technical tasks.
MUST read references/052-design-hamburger-method.md before applying the method
MUST identify 3-6 functional or workflow layers before selecting a slice
MUST generate 4-5 options per layer, ordered from simplest acceptable option to richer options
MUST challenge scope with the smallest-useful-version question before recommending a first slice
MUST filter costly, redundant, irreversible, or unnecessary options before composing the first slice
MUST keep recommended work as vertical slices that deliver observable value
MUST NOT present isolated technical layers as independently shippable stories