052-design-hamburger-method — Claude Code skill: setup and use
052-design-hamburger-method splits oversized user stories and specs into thin vertical slices using the Hamburger Method. Delivers end-to-end observable value instead of isolated technical tasks.
Apache-2.0 172 installs ★ 465 updated 2026-10-21
npx skills add jabrena/plinth --skill 052-design-hamburger-method -a claude-codeWhat 052-design-hamburger-method does
This interactive skill walks engineers through the Hamburger Method to break down bloated features. It maps three to six workflow layers needed for a capability, then lists four or five implementation options per layer, sorted from the plainest acceptable choice to richer variants. By testing the scope against the question of what could ship tomorrow, it trims costly or irreversible choices to form a tiny end-to-end slice.
Horizontal technical assignments are barred from becoming standalone stories. Slices must cut through the full stack and deliver visible user progress. Skipping references/052-design-hamburger-method.md prevents the workflow from running.
Once slices are verified for testability and tracking, the skill routes them directly into companion Plinth skills: 043-planning-github-issues for GitHub, 044-planning-jira for Jira, and 042-planning-openspec for formal specifications.
What it helps with
- Split an oversized feature into thin end-to-end vertical slices
- Define the smallest useful release candidate for tomorrow
- Eliminate redundant or costly architecture options early
- Format decomposed work items for Jira, GitHub issues, or Azure DevOps
Example prompts for the agent
- Apply the Hamburger Method to split this oversized story
- Find the smallest useful slice for this user profile feature
- Turn this broad spec into tracked vertical slices instead of horizontal tasks
How to install 052-design-hamburger-method
1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 052-design-hamburger-method -a claude-code2Manually: put the files in place
~/.claude/skills/052-design-hamburger-method/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/052-design-hamburger-method/
1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 052-design-hamburger-method -a codex2Manually: put the files in place
.agents/skills/052-design-hamburger-method/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 052-design-hamburger-method -a cursor2Manually: put the files in place
.cursor/skills/052-design-hamburger-method/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install jabrena/plinth skills/052-design-hamburger-method2Manually: put the files in place
.github/skills/052-design-hamburger-method/SKILL.md1Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 052-design-hamburger-method -a gemini-cli2Platform CLI
gemini skills install https://github.com/jabrena/plinth --path skills/052-design-hamburger-methodManually: put the files in place
.devin/skills/052-design-hamburger-method/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add jabrena/plinth --skill 052-design-hamburger-method -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about 052-design-hamburger-method
How to install 052-design-hamburger-method in Claude Code?
Run npx skills add jabrena/plinth --skill 052-design-hamburger-method -a claude-code in your terminal. The file is placed into ~/.claude/skills/052-design-hamburger-method/SKILL.md.
What does this skill prevent during decomposition?
It strictly forbids outputting single-tier technical chores, such as isolated database migrations or frontend-only stubs, as shippable stories.
Which planning tools does this skill connect with?
It routes parsed work items into other Plinth skills: 041-planning-plan-mode, 042-planning-openspec, 043-planning-github-issues, 044-planning-jira, and 045-planning-azure-devops.
Source text
SKILL.md · Apache-2.0
--- name: 052-design-hamburger-method description: 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 license: Apache-2.0 metadata: author: Juan Antonio Breña Moral version: 0.19.0 --- # 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 ## When to use this skill - Apply the Hamburger Method - Split this oversized story - Find the smallest useful slice - Break this feature into vertical slices - Turn this broad plan into tracked slices - This feature is too large ## Workflow 1. **Recognize Oversized Work** Read `references/052-design-hamburger-method.md`, then restate the large feature, story, plan, or spec idea and why ordinary implementation task decomposition would be too broad, risky, or horizontal. 2. **Map Layers and Options** Identify 3-6 functional or workflow layers needed for observable value. For each layer, generate 4-5 implementation or quality options ordered from the simplest acceptable choice to richer choices. 3. **Challenge Scope** Ask: "If this had to ship tomorrow, what would be the smallest useful version?" Use the answer to remove options that are too costly, redundant, irreversible, or unnecessary for early learning. 4. **Compose the First Slice** Select one option from each relevant layer to create the smallest useful end-to-end vertical slice. Explain the user-visible value, validation signal, and why rejected layer options wait for later slices. 5. **Plan Follow-Up Slices** Propose follow-up vertical slices that incrementally improve quality, automation, robustness, reach, observability, operational behavior, or supported workflows without turning them into isolated technical layers. 6. **Self-Check and Route Follow-Up** Check every slice for value, size, testability, deliverability, and issue-tracking suitability. Route implementation planning through `041-planning-plan-mode`, spec-level changes through `042-planning-openspec`, GitHub issue work through `043-planning-github-issues`, Jira work through `044-planning-jira`, and Azure DevOps work through `045-planning-azure-devops`. ## Reference For detailed guidance, examples, and constraints, see [references/052-design-hamburger-method.md](references/052-design-hamburger-method.md).
© Juan Antonio Breña Moral · Apache-2.0 · jabrena/plinth