Back to directory

Image to Spec

Agent skill
1 skill

Generate a design-system spec from a raw image file (a screenshot, mockup, or captured app screen) when there is no Figma source. Reads the image with vision and emits a COMPONENTSPEC.md-shaped doc (--component) or a SCREENSPEC.md-shaped doc (--screen), auto-detecting the mode when no flag is given. A gated --gameplay mode (ADR-0084, off by default) instead derives a MECHANICSSPEC.md behavior contract for a 2D game from screenshots, extracted video frames, and playtest notes, with every rule in EARS form tagged observed, assumed, or open. Every observation is marked proposed because an image is an inference source, not a source of truth. Use when you have only an image and want a structured spec the design cluster can consume. Do not use when a Figma node exists (use component-spec or screen-spec), when you want code rather than a spec, or to push the image into Figma (that is generatefigmadesign, a separate capability).

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategoryProduct & designStars0

About this skill

Generate a design-system spec from a raw image file (a screenshot, mockup, or captured app screen) when there is no Figma source. Reads the image with vision and emits a COMPONENTSPEC.md-shaped doc (--component) or a SCREENSPEC.md-shaped doc (--screen), auto-detecting the mode when no flag is given. A gated --gameplay mode (ADR-0084, off by default) instead derives a MECHANICSSPEC.md behavior contract for a 2D game from screenshots, extracted video frames, and playtest notes, with every rule in EARS form tagged observed, assumed, or open. Every observation is marked proposed because an image is an inference source, not a source of truth. Use when you have only an image and want a structured spec the design cluster can consume. Do not use when a Figma node exists (use component-spec or screen-spec), when you want code rather than a spec, or to push the image into Figma (that is generatefigmadesign, a separate capability).

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 4aac4f643ad017db81b4265bfeea8e3c4732c03655b983da10cf94017a3df7dc

About scan coverage and limitations

About this listing

Category
Product & design
Reported license
MIT
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Image to Spec | Agent Skills Atlas