screenshot-feature-extractor — Claude Code skill for screenshot analysis
Turns interface screenshots into a feature and task checklist. Use it to plan work from UI designs or visual references.
npx claude-code-templates@latest --skill development/screenshot-feature-extractorWhat screenshot-feature-extractor does
The skill examines screenshots and produces development tasks focused on features and user actions rather than a technology stack. When several screens are provided, it removes duplicate items. The final checklist goes to docs/plans/YYYY-MM-DD-<product>-features.md and uses - [ ] task markers.
Five subagents handle the workflow. Three inspect the UI, interactions, and business functions at the same time; a synthesizer combines their findings, then a reviewer checks the result. The process relies on all five subagents and the references/output-format.md file for its final stages, so those components need to be available.
Give Claude Code the screenshots and any relevant context. The skill can also compare screens from different products and list features and gaps found in the visual references.
What it helps with
- extract interface features from screenshots
- turn a UI design into development tasks
- merge several screens into one deduplicated checklist
- compare product features across visual references
Example prompts for the agent
- Analyze the screenshots in
design/and create a development task list. - Turn
checkout.pnginto a checklist of features and user interactions. - Compare the screens in
screens/and write one plan without duplicate tasks.
How to install screenshot-feature-extractor
1claude-code-templates
npx claude-code-templates@latest --skill development/screenshot-feature-extractor2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill screenshot-feature-extractor -a claude-code3Manually: put the files in place
~/.claude/skills/screenshot-feature-extractor/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/screenshot-feature-extractor/
Manually: put the files in place
.agents/skills/screenshot-feature-extractor/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/screenshot-feature-extractor/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates screenshot-feature-extractor2Manually: put the files in place
.github/skills/screenshot-feature-extractor/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/development/screenshot-feature-extractorManually: put the files in place
.devin/skills/screenshot-feature-extractor/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about screenshot-feature-extractor
How do I install screenshot-feature-extractor in Claude Code?
Run npx claude-code-templates@latest --skill development/screenshot-feature-extractor.
What does screenshot-feature-extractor do?
It analyzes interface screenshots and writes development tasks about product features and user interactions to a plan file.
How does it handle multiple screenshots?
Three subagents inspect each screen in parallel, then a synthesizer merges their findings. Repeated features are removed from the final list.