spec-from-screenshot

spec-from-screenshot is a skill for Claude Code, Codex from sablier-labs/agent-skills. It costs 53 tokens per session (1,085 once invoked), scanned A, original, MIT.

A method for turning website screenshots or design mockups into a detailed implementation specification. It documents the visible layout, typography, colors, spacing, components, and other design details.

In plain words
What is it for?
Use it to analyze screenshots, extract a design system, inventory UI components, or create a SPEC.md file for implementation.
Why use it?
It gives developers a written reference when the original design files or implementation are unavailable. This reduces guesswork when rebuilding the interface.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to analyze screenshots, extract a design system, inventory UI components, or create a SPEC.md file for implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sablier-labs/agent-skills/spec-from-screenshot
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add sablier-labs/agent-skills --skill spec-from-screenshot
Clone the repo
git clone --depth 1 https://github.com/sablier-labs/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for spec-from-screenshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/sablier-labs/agent-skills/spec-from-screenshot/github.svg)](https://agentmods.dev/skills/sablier-labs/agent-skills/spec-from-screenshot)
Your own site
<a href="https://agentmods.dev/skills/sablier-labs/agent-skills/spec-from-screenshot"><img src="https://agentmods.dev/badge/skills/sablier-labs/agent-skills/spec-from-screenshot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-from-screenshot

Your own site · 80×15
<a href="https://agentmods.dev/skills/sablier-labs/agent-skills/spec-from-screenshot"><img src="https://agentmods.dev/badge/skills/sablier-labs/agent-skills/spec-from-screenshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,085 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.01085
Opus 5 $0.00026 $0.00543
Sonnet 5 $0.00011 $0.00217
Haiku 4.5 $0.00005 $0.00109

Measured 11d ago against content hash ab1d8a051393, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spec-from-screenshot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/spec-from-screenshot/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Screenshot Analysis & Spec Generation

Analyze website screenshots and generate detailed implementation specifications. This skill guides creation of comprehensive SPEC.md files that document design systems extracted from visual references.

When to Use

  • User provides website screenshots or design mockups
  • Request for implementation specifications from visual references
  • Need to extract design systems (colors, typography, spacing) from images
  • Creating detailed component inventories from UI screenshots

Workflow

Step 1: Validate Prerequisites

Ensure screenshots are available in the conversation. If no images are present, request them before proceeding.

Step 2: Perform Ultra-Detailed Analysis

Analyze all provided screenshots covering these aspects:

1. Layout Architecture

  • Overall page structure (header, navigation, hero, main content, sidebars, footer)
  • Grid system and column layouts
  • Container widths and max-widths
  • Section hierarchy and nesting

2. Typography System

  • Font families (identify primary, secondary, monospace)
  • Font sizes for each text level (h1-h6, body, small, etc.)
  • Font weights used (light, regular, medium, semibold, bold)
  • Line heights and letter spacing
  • Text colors and contrast ratios

3. Color Palette

  • Primary brand colors
  • Secondary/accent colors
  • Background colors (main, sections, cards)
  • Text colors (headings, body, muted, links)
  • Border colors
  • State colors (success, error, warning, info)
  • Color codes in hex/rgb (best approximation)

4. Spacing System

  • Margins between major sections
  • Padding within components
  • Gap spacing in flex/grid layouts
  • Consistent spacing scale (e.g., 4px, 8px, 16px, 24px, 32px)
  • Vertical rhythm patterns

5. Component Inventory

  • Buttons (styles, sizes, states)
  • Input fields and forms
  • Cards and containers
  • Navigation elements
  • Icons and their style
  • Badges, tags, labels
  • Modals, tooltips, dropdowns
  • List items and data tables

6. Visual Design Details

Read the full file on GitHub · 195 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 195 lines · 53 tokens per session scan A ab1d8a051393

Subscribe to this mod's changes

spec-from-screenshot is a skill published in the GitHub repository sablier-labs/agent-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,085 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens