Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze product screenshots to extract feature lists and generate development task checklists. Use when: (1) Analyzing competitor product screenshots for feature extraction, (2) Generating PRD/task lists from UI designs, (3) Batch analyzing multiple app screens, (4) Conducting competitive analysis from visual references.
.claude/skills/davila7-screenshot-feature-extractor/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 556% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-21 | ✗→✓ | ▲ Improved | 11% | 0% |
Extract product features from UI screenshots using a coordinated multi-agent analysis pipeline.
Core principle: Describe WHAT to build (features/interactions), NOT HOW (no tech stack).
This skill orchestrates 5 specialized agents for comprehensive analysis:
┌─────────────────┐
│ Coordinator │
│ (this skill) │
└────────┬────────┘
│
┌───────────────────┼───────────────────┐
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ UI Analyzer │ │ Interaction │ │ Business │
│ (parallel) │ │ Analyzer │ │ Analyzer │
│ │ │ (parallel) │ │ (parallel) │
└────────┬────────┘ └────────┬────────┘ └────────┬────────┘
│ │ │
└───────────────────┼───────────────────┘
▼
┌─────────────────┐
│ Synthesizer │
│ (sequential) │
└────────┬────────┘
│
▼
┌─────────────────┐
│ Reviewer │
│ (sequential) │
└─────────────────┘Gather all screenshots to analyze:
Launch THREE Task agents IN PARALLEL for each screenshot:
Agent 1: screenshot-ui-analyzer
Analyze this screenshot for UI components, layout structure, and design patterns.
Screenshot: [file path]
Return your analysis as JSON.Agent 2: screenshot-interaction-analyzer
Analyze this screenshot for user interactions, navigation flows, and state transitions.
Screenshot: [file path]
Return your analysis as JSON.Agent 3: screenshot-business-analyzer
Analyze this screenshot for business functions, data entities, and domain logic.
Screenshot: [file path]
Return your analysis as JSON.IMPORTANT: Use the Task tool with THREE parallel calls in a single message to maximize efficiency.
After all parallel analyses complete, launch the synthesizer agent:
Agent 4: screenshot-synthesizer
Synthesize these analysis results into a unified development task list.
UI Analysis:
[paste UI analyzer result]
Interaction Analysis:
[paste Interaction analyzer result]
Business Analysis:
[paste Business analyzer result]
Product Name: [product name]
Output file: docs/plans/YYYY-MM-DD-<product>-features.mdLaunch the reviewer agent to validate the output:
Agent 5: screenshot-reviewer
Review this task list for completeness and quality.
Original screenshot(s): [file paths]
Task list: [synthesized output]
If issues found, provide corrections.docs/plans/YYYY-MM-DD-<product>-features.md- [ ] checkbox format for all tasks| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 14,410 | 31,575 | +119% | 1 | 1 | 0% | 2,324 | 5,823 | +151% | 0 | 0 | — |
case-01 | fail→fail | 4,016 | 11,732 | +192% | 1 | 1 | 0% | 606 | 1,613 | +166% | 0 | 0 | — |
case-02 | fail→fail | 15,812 | 9,625 | -39% | 1 | 1 | 0% | 3,154 | 1,539 | -51% | 0 | 0 | — |
case-03 | fail→fail | 5,372 | 38,601 | +619% | 1 | 1 | 0% | 858 | 7,573 | +783% | 0 | 0 | — |
case-04 | pass→pass | 17,552 | 27,321 | +56% | 1 | 1 | 0% | 3,324 | 5,448 | +64% | 0 | 0 | — |
case-05 | fail→pass | 5,757 | 44,041 | +665% | 1 | 1 | 0% | 1,079 | 7,074 | +556% | 0 | 0 | — |
case-06 | pass→fail | 7,331 | 26,913 | +267% | 1 | 1 | 0% | 1,271 | 4,231 | +233% | 0 | 0 | — |
case-07 | pass→fail | 23,276 | 10,961 | -53% | 1 | 1 | 0% | 3,658 | 1,698 | -54% | 0 | 0 | — |
case-08 | pass→pass | 8,064 | 16,064 | +99% | 1 | 1 | 0% | 1,298 | 3,626 | +179% | 0 | 0 | — |
case-09 | fail→pass | 9,144 | 2,903 | -68% | 1 | 1 | 0% | 1,689 | 1,399 | -17% | 0 | 0 | — |
case-10 | pass→pass | 9,353 | 3,788 | -59% | 1 | 1 | 0% | 1,400 | 1,493 | +7% | 0 | 0 | — |
case-11 | fail→fail | 6,856 | 10,322 | +51% | 1 | 1 | 0% | 444 | 1,954 | +340% | 0 | 0 | — |
case-13 | fail→fail | 8,007 | 3,542 | -56% | 1 | 1 | 0% | 1,124 | 1,473 | +31% | 0 | 0 | — |
case-14 | pass→pass | 11,417 | 6,516 | -43% | 1 | 1 | 0% | 1,868 | 1,793 | -4% | 0 | 0 | — |
case-15 | fail→pass | 12,822 | 6,070 | -53% | 1 | 1 | 0% | 2,024 | 1,883 | -7% | 0 | 0 | — |
case-16 | pass→pass | 4,922 | 4,021 | -18% | 1 | 1 | 0% | 733 | 1,580 | +116% | 0 | 0 | — |
case-17 | pass→pass | 12,242 | 6,022 | -51% | 1 | 1 | 0% | 1,899 | 1,971 | +4% | 0 | 0 | — |
case-18 | pass→pass | 7,186 | 2,276 | -68% | 1 | 1 | 0% | 1,128 | 1,190 | +5% | 0 | 0 | — |
case-19 | pass→pass | 7,252 | 1,856 | -74% | 1 | 1 | 0% | 993 | 1,152 | +16% | 0 | 0 | — |
case-20 | fail→pass | 7,620 | 2,481 | -67% | 1 | 1 | 0% | 1,094 | 1,248 | +14% | 0 | 0 | — |
case-21 | fail→pass | 17,762 | 7,969 | -55% | 1 | 1 | 0% | 1,949 | 2,173 | +11% | 0 | 0 | — |
case-22 | fail→fail | 8,411 | 2,035 | -76% | 1 | 1 | 0% | 1,376 | 1,100 | -20% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 17 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +14 percentage points is the difference between those two pass rates over the 17 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.