agentleFS
Evan-Kim2028Evan-Kim2028/agent-skills/skills/frontend/mockup-implement/SKILL.md

mockup-implement

Skill1 starsChanged 3 months agoMITView on GitHub

Port a signed-off mockup (HTML picker winner, Figma, screenshot) into production with fidelity — no freestyle redesign. Use only when a design is already chosen and the task is "match this." Prefer product-design when craft/explore path is unclear; frontend-design for full FE feature implementation. Not for open-ended exploration (ui-explore first) or inventing new visual systems (design-system / craft).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    If not signed off → ui-explore (or Figma) first.

    line 38
  2. Distinctive:

    Never paste mock CSS wholesale if it bypasses tokens.

    line 65
  3. Distinctive:

    Prefer smallest PR that matches the signed surface

    line 69
  4. Distinctive:

    Use browser-verify (and mobile-product-ux if applicable).

    line 91

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mockup → production implementation

Job: Ship the agreed design in production primitives — not a reinterpretation.

Sources (attribution)

  • Design-to-code fidelity practice from OpenAI/Figma “implement design” skill lineage: multi-state components, respect existing system, verify visually.
  • Repo design/ workflows: HTML pickers, ?design= variants, selection JSON, DESIGN-DIRECTION locks (SilphCo-style and similar).
  • ui-explore skill: exploration stays in throwaway HTML; this skill starts after a winner is chosen.

When to load

  • “Port Trade Floor v7 mockup” / “implement design B”
  • Figma frame → React
  • Screenshot parity tickets
  • Agents redesign while “implementing”

Preconditions

  1. Signed-off source named (path, frame, or URL)
  2. design-system constraints known (tokens, kit)
  3. Out of scope listed (don’t “while we’re here” redesign nav)

If not signed off → ui-explore (or Figma) first; do not implement fog.

Workflow

1. Inventory the mockup

Extract a checklist:

ConcernNotes
Layout regionsheader / body / sticky / HUD
Typographywhich roles (title, meta, mono price)
Componentsmap to kit (Button, Sheet, Panel…)
Statesempty, loading, error, selected, disabled
Motionnone / subtle / explicit
Breakpointsmobile vs desktop differences
Datareal fields vs placeholder

2. Map mock → code

Mock elementProduction target
Pretty div buttonKit Button variant
Hard-coded colorToken class / CSS var
Fake dataReal query + empty/error
Absolute artboardResponsive layout + sticky rules

Never paste mock CSS wholesale if it bypasses tokens.

3. Implement minimal delta

  • Prefer smallest PR that matches the signed surface
  • Reuse routes/features; don’t new-page without need
  • Preserve existing analytics/a11y hooks

4. Fidelity gate

Side-by-side:

  1. Mockup (or HTML ?design=winner)
  2. Local prod build

Check:

  • Structure/order of regions
  • Spacing rhythm within ~token step
  • Sticky/HUD behavior on mobile
  • Primary CTA placement
  • No extra chrome the mock lacks
  • No missing states the mock shows

5. Verify

Use browser-verify (and mobile-product-ux if applicable). Update snapshots only when intentional.

Anti-patterns

  • “Improved” colors/fonts during port
  • Shipping desktop mock only when mock specifies mobile
  • Leaving mock placeholder copy in production
  • New dependencies for something the kit already does
  • Scope creep into adjacent pages

Relation to ui-explore

ui-explore → pick winner → mockup-implement → product-ui-craft polish → browser-verify

Hand off

NeedNext skill
Tokens/primitivesdesign-system
Post-port polishproduct-ui-craft
Mobile stickymobile-product-ux
Browser proofbrowser-verify

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.