Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce images for any purpose including UI mockups, icons, illustrations, diagrams, concept art, placeholder images, or visual representations.
.claude/skills/sanjay3290-imagen/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-19 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-16 | ✓→✗ | ▼ Worse | -71% | 0% |
| case-20 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
This skill generates images using Google Gemini's image generation model (gemini-3-pro-image-preview). It enables seamless image creation during any Claude Code session - whether you're building frontend UIs, creating documentation, or need visual representations of concepts.
Cross-Platform: Works on Windows, macOS, and Linux.
Automatically activate this skill when:
bash# Basic usage python scripts/generate_image.py "A futuristic city skyline at sunset" # With custom output path python scripts/generate_image.py "A minimalist app icon for a music player" "./assets/icons/music-icon.png" # With custom size python scripts/generate_image.py --size 2K "High resolution landscape" "./wallpaper.png"
GEMINI_API_KEY environment variable must be setGenerated images are saved as PNG files. The script returns:
User: "I need a hero image for my landing page - something abstract and tech-focused"
-> Generates and saves image, provides path for use in HTML/CSSUser: "Create a diagram showing microservices architecture"
-> Generates visual representation, ready for README or docsUser: "Generate a placeholder avatar image for the user profile component"
-> Creates image in appropriate size for component use| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→fail | 15,392 | 5,549 | -64% | 1 | 1 | 0% | 3,199 | 754 | -76% | 0 | 0 | — |
case-05 | fail→fail | 22,640 | 5,983 | -74% | 1 | 1 | 0% | 4,446 | 844 | -81% | 0 | 0 | — |
case-01 | fail→fail | 4,699 | 22,274 | +374% | 1 | 1 | 0% | 831 | 963 | +16% | 0 | 0 | — |
case-02 | fail→fail | 73,234 | 5,438 | -93% | 1 | 1 | 0% | 5,445 | 857 | -84% | 0 | 0 | — |
case-03 | fail→fail | 13,752 | 5,318 | -61% | 1 | 1 | 0% | 2,782 | 739 | -73% | 0 | 0 | — |
case-20 | pass→pass | 8,223 | 7,060 | -14% | 1 | 1 | 0% | 1,866 | 2,051 | +10% | 0 | 0 | — |
case-06 | fail→fail | 30,712 | 4,719 | -85% | 1 | 1 | 0% | 6,168 | 802 | -87% | 0 | 0 | — |
case-07 | fail→fail | 11,752 | 4,538 | -61% | 1 | 1 | 0% | 2,287 | 703 | -69% | 0 | 0 | — |
case-08 | pass→pass | 3,919 | 1,185 | -70% | 1 | 1 | 0% | 629 | 662 | +5% | 0 | 0 | — |
case-09 | fail→pass | 5,975 | 1,719 | -71% | 1 | 1 | 0% | 1,137 | 796 | -30% | 0 | 0 | — |
case-10 | fail→pass | 3,838 | 1,701 | -56% | 1 | 1 | 0% | 618 | 728 | +18% | 0 | 0 | — |
case-11 | pass→pass | 4,237 | 1,394 | -67% | 1 | 1 | 0% | 632 | 689 | +9% | 0 | 0 | — |
case-12 | fail→fail | 10,902 | 8,936 | -18% | 1 | 1 | 0% | 2,201 | 1,064 | -52% | 0 | 0 | — |
case-13 | fail→fail | 33,241 | 6,266 | -81% | 1 | 1 | 0% | 6,171 | 771 | -88% | 0 | 0 | — |
case-14 | fail→fail | 18,708 | 6,849 | -63% | 1 | 1 | 0% | 4,129 | 932 | -77% | 0 | 0 | — |
case-15 | fail→fail | 31,215 | 4,093 | -87% | 1 | 1 | 0% | 6,163 | 702 | -89% | 0 | 0 | — |
case-16 | pass→fail | 25,212 | 7,783 | -69% | 1 | 1 | 0% | 4,119 | 1,198 | -71% | 0 | 0 | — |
case-17 | fail→fail | 14,479 | 6,454 | -55% | 1 | 1 | 0% | 1,564 | 824 | -47% | 0 | 0 | — |
case-18 | fail→fail | 70,892 | 4,556 | -94% | 1 | 1 | 0% | 4,678 | 723 | -85% | 0 | 0 | — |
case-19 | fail→pass | 6,838 | 2,793 | -59% | 1 | 1 | 0% | 1,203 | 887 | -26% | 0 | 0 | — |
case-21 | pass→pass | 9,883 | 10,060 | +2% | 1 | 1 | 0% | 1,989 | 2,563 | +29% | 0 | 0 | — |
case-22 | pass→pass | 6,975 | 6,027 | -14% | 1 | 1 | 0% | 1,384 | 1,681 | +21% | 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 8 counted toward the lift figure. The other 14 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 +9 percentage points is the difference between those two pass rates over the 8 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.