Individual skill
import-screenshot-to-prototype
Use this plugin when the user provides a screenshot or image reference and wants it reconstructed as an editable OpenDesign prototype with sensible components, layout, and responsive behavior.
plugins/spec/examples/import-screenshot-to-prototype/SKILL.md
Source commit e7a18df64d0e5e1161903e93bb5a302229dbeb96
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 106,836
- Repository last updated
- Nov 9, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-design Repository topic
- byok Repository topic
- design-systems Repository topic
- claude-design Repository topic
- hermes-agent Repository topic
- agent-skills Repository topic
- desktop-app Repository topic
- figma-alternative Repository topic
- prototyping Repository topic
- ui-generator Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 999 bytesopen-design.jsonasset · 1,520 bytes
Read excerpt
# Import Screenshot To Prototype
## Workflow
1. Inspect the screenshot and identify layout regions, controls, typography scale, color roles, and content hierarchy.
2. Ask for the target viewport only if it cannot be inferred.
3. Rebuild the screenshot as a clean `index.html` artifact with semantic sections and reusable CSS tokens.
4. Preserve the visual intent, but replace unreadable or unavailable text with realistic editable content.
5. Add responsive behavior for at least one mobile width.
6. Self-critique visual fidelity, text fit, and editability before final.
## Output Contract
Produce `index.html` and a short `import-notes.md` that lists inferred decisions.