design-to-code-handoff
Skill4 starsChanged 2 months agoMITView on GitHub
Map design specs to implementation-ready code tasks. Use when handoff to dev, implement this design, turn spec into code, design to code, or start building from the design.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- memi-design/design-skillstheir own version, first seen Nov 8, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- memi-design/design-skills★ 7same name
- KMaruthi2002/universal-llm-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- accessibility-reviewSkill
- accessibility-runtime-auditSkill
- adaptive-component-behaviorSkill
- ai-feature-ux-patternsSkill
- behavioral-pricing-psychologySkill
- business-model-readingSkill
- business-model-thinkingSkill
- cognitive-load-heatmap-predictionSkill
- component-style-guideSkill
- cross-functional-reviewSkill
- dark-mode-theming-systemSkill
- dashboard-layout-patternsSkill
- dashboard-scaffolding-contractSkill
- design-drift-detectorSkill
- design-system-builderSkill
- design-tokensSkill
- error-boundary-resilience-designSkill
- flow-based-functional-testingSkill
- growth-impact-reviewSkill
- i18n-localization-strategySkill
- information-architectureSkill
- interactive-element-auditSkill
- kinematic-motion-choreographySkill
- micro-interaction-motion-designSkill
- module-registry-syncSkill
- mvp-scopingSkill
- perceived-performance-loadingSkill
- prd-traceability-matrixSkill
- product-discoverySkill
- product-strategySkill
- project-health-diagnosticsSkill
- qa-feedback-loop-orchestratorSkill
- responsive-breakpoint-strategySkill
- responsive-qa-auditSkill
- route-integrity-checkerSkill
- security-privacy-reviewSkill
- stakeholder-requirement-mappingSkill
- touch-gesture-interactionSkill
- typography-systemSkill
- usability-heuristics-checkSkill
- user-flow-mappingSkill
- user-research-synthesisSkill
- ux-chaos-monkeySkill
- visual-hierarchy-reviewSkill
- visual-responsive-regression-testingSkill
- visual-style-extractorSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
If any artifact is missing, flag it — do not proceed with gaps.
- Distinctive: line 27
If none, what new component is needed?
- Distinctive: line 76
Not done if any element says "use appropriate styling" — that's a guess, not a spec.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design-to-Code Handoff
The handoff is where designs go to die. Every missing spec forces an engineer to guess; every guess is a coin flip between "matches the design" and "doesn't." This skill eliminates guessing by producing a complete, implementation-ready spec that maps every visual decision to code.
Process
1. Collect all design artifacts
Gather upstream outputs from the product design pipeline:
- Design tokens (from design-tokens) — color, spacing, radius, shadow, breakpoint definitions
- Typography scale (from typography-system) — font pairing, sizes, weights, line-heights
- Component specs (from design-system-builder) — atoms, molecules, organisms with props and states
- State matrices (from component-style-guide) — every variant × state combination
- Layout spec (from dashboard-layout-patterns) — shell pattern, grid, responsive behavior
- Motion spec (from micro-interaction-motion-design) — transitions, feedback animations, motion tokens
- User flows (from user-flow-mapping) — entry points, decision paths, error flows
If any artifact is missing, flag it — do not proceed with gaps. Every gap becomes a guess downstream.
2. Generate the component implementation checklist
For each component in the design:
- Which existing component in the codebase matches? (exact match / partial / none)
- If none, what new component is needed? Name it, describe its responsibility.
- Props/variants needed for this usage — cross-reference with component-style-guide.
- Token references for all visual properties: background, text color, padding, margin, border-radius, shadow, font-size, font-weight. No raw values allowed.
- Responsive behavior at each breakpoint — how does this component change across
breakpoint-sm→breakpoint-xl?
3. Map layout to code structure
Translate the layout spec into a file/component tree:
- Which component owns which section of the layout?
- Where do data fetches live? (page level / component level / shared)
- How does routing work? Map routes from information-architecture.
- What shared state is needed? (user session, module data, UI state)
Produce a tree diagram showing the component hierarchy with file paths.
4. Spec interactions and states
For each interactive element: trigger → action → visual feedback → state change.
- Reference the component-style-guide state matrix for visual changes.
- Reference the motion spec for transition timing and easing.
- Don't leave any interaction as "obvious" — spell it out. "Button click saves form" is incomplete. "Button click → button enters loading state (spinner, disabled) → POST /api/form → on success: toast success, reset form, button returns to default → on error: toast error with message, button returns to default" is a spec.
5. Produce the implementation file list
Ordered list of files to create/modify. For each file:
- File path (following project conventions)
- Purpose (one sentence)
- Components involved (imported / exported)
- Tokens used (list token names)
- Dependencies (other files that must exist first)
- Estimated complexity: S / M / L
Order by dependency: files with no dependencies first, files that depend on others after.
6. Verify token coverage
Cross-reference every color, spacing, radius, shadow, and font-size in the spec against design-tokens. Flag any value that isn't a token — raw values are spec bugs that will diverge across components.
7. Verify flow coverage
Walk through every user flow from user-flow-mapping against the component tree:
- Can every flow be completed using the specced components?
- Are error states, loading states, and empty states covered?
- Does every CTA connect to a real route? (cross-reference with route-integrity-checker)
Completion criteria
Done when:
- Every visual element maps to a component
- Every component maps to tokens (zero raw values)
- The file list is ordered, dependency-resolved, and actionable
- Every user flow is walkable through the component tree
- Every interactive element has a trigger → action → feedback → state chain
Not done if any element says "use appropriate styling" — that's a guess, not a spec.
Output format
Implementation checklist artifact (Markdown):
- Design artifact inventory (collected / missing)
- Component implementation checklist (component → props → tokens → responsive)
- Component hierarchy tree (with file paths)
- Interaction specs (trigger → action → feedback → state)
- Implementation file list (ordered by dependency)
- Token coverage report (pass / violations)
- Flow coverage report (complete / gaps)
Anti-patterns
- Handing off a screenshot instead of a spec.
- Token references that say "see design system" without specifying which token.
- Specs that describe appearance but not behavior.
- File lists without dependency ordering — leads to blocked work and circular imports.
- Skipping the flow coverage check — leads to components that render but don't connect into a usable product.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

