agentleFS
Sign inStart free
ManojDevHub1ManojDevHub1/visual-engineering-suite/skills/visual-reconstruction/SKILL.md

visual-reconstruction

Skill1 starsChanged 26 days agoMITView on GitHub

Inspect supplied screenshots, mockups, or web pages, extract visual hierarchy, layout structure, typography, and visible components, and produce a structured UI specification separating facts from assumptions.

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
  1. Distinctive:

    Use this skill when presented with a screenshot, UI reference image, mockup, or web page that needs to be reconstructed into frontend code.

    line 9
  2. Distinctive:

    Always determine image width and height to establish the target device context:

    line 23
  3. Distinctive:

    Follow the comprehensive Visual Analysis Guide:

    line 32

≈ “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

Visual Reconstruction Skill

Use this skill when presented with a screenshot, UI reference image, mockup, or web page that needs to be reconstructed into frontend code.

Core Responsibilities

  1. Empirical Grounding: Distinguish verified visual facts from assumptions.
  2. Dimension Awareness: Inspect reference image dimensions using check-dimensions.js.
  3. Structured Specification: Produce an implementation-ready UI specification matching reconstruction-schema.json before generating code.
  4. Uncertainty Logging: Explicitly log any unverified typography, spacing, or responsive behaviors.

Step-by-Step Procedure

1. Inspect Reference Image Dimensions

Always determine image width and height to establish the target device context:

node skills/visual-reconstruction/scripts/check-dimensions.js <path-to-reference-image>
  • < 500px: Mobile viewport context.
  • 500px - 1024px: Tablet viewport context.
  • > 1024px: Desktop viewport context.

2. Perform Visual Deconstruction

Follow the comprehensive Visual Analysis Guide:

  • Layout & Structure: Identify root containers, flex rows/columns, CSS grid layouts, and padding gutters.
  • Hierarchy & Typography: Identify display headings, section titles, body paragraphs, and microcopy.
  • Component Atoms: Identify buttons, inputs, pills, avatar circles, cards, and dividers.
  • Color Zones: Note surface colors, text contrast, borders, and accent highlights.

3. Log Observed Facts vs. Uncertainties

Format your analysis with strict separation:

### Observed Facts (Empirical)
- The header contains a logo on the left and 4 navigation items on the right.
- The hero section contains an H1 headline, a short subtitle, and a primary action button.
- The background color of the hero is dark slate (#0F172A).

### Uncertainties & Hypotheses
- Font Family: Hypothesized as Inter or system sans-serif. Requires project font check.
- Button Hover State: Not visible in static image. Will implement subtle brightness reduction.
- Mobile Layout: Reference is desktop only. Will adapt 3-column grid to 1-column stack below 768px.

4. Output the Reconstruction Specification

Synthesize the analysis into a structured specification or JSON conforming to reconstruction-schema.json. Proceed to design-system-extraction or frontend-implementation.

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.

Check your setup, free