Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate logos using Replicate AI and make them transparent with background removal.
.claude/skills/aiskillstore-logo-generator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -48% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 151% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 166% | 0% |
You are the Logo Designer. You generate professional logos using AI and process them to have transparent backgrounds.
public/assets/logo.png.⚠️ IMPORTANT: Before using this skill, ensure REPLICATE_API_TOKEN is set in your environment variables (.env, .env.local, or .env.production).
and Dev Requirement: pnpm add sharp -D
Script: .claude/skills/logo-generator/scripts/generate-logo.ts
Usage:
bashpnpm run script .claude/skills/logo-generator/scripts/generate-logo.ts "<prompt>" "[company-name]"
Parameters:
prompt: Description of the logo design (e.g., "Minimalistic Logo Design for Tech Startup").company-name: Optional company/brand name to include in the prompt (default: uses prompt as-is).Example:
bashpnpm run script .claude/skills/logo-generator/scripts/generate-logo.ts "Minimalistic Logo Design for BrayanCodes" "BrayanCodes"
When asked to "Generate a logo" or "Create a logo for X":
REPLICATE_API_TOKEN is set. If not, inform the user.public/assets/logo.pngmejiabrayan/logoai:67ed00e8999fecd32035074fa0f2e9a31ee03b57a8415e6a5e2f93a242ddd8d2bria/remove-backgroundpublic/assets/logo.pngFor advanced configuration and model details, see reference.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 26,742 | 3,168 | -88% | 1 | 1 | 0% | 5,818 | 916 | -84% | 0 | 0 | — |
case-02 | fail→fail | 16,493 | 5,909 | -64% | 1 | 1 | 0% | 2,630 | 899 | -66% | 0 | 0 | — |
case-03 | fail→fail | 14,079 | 3,112 | -78% | 1 | 1 | 0% | 2,775 | 938 | -66% | 0 | 0 | — |
case-04 | fail→pass | 6,499 | 4,841 | -26% | 1 | 1 | 0% | 1,117 | 1,373 | +23% | 0 | 0 | — |
case-05 | fail→pass | 5,702 | 2,296 | -60% | 1 | 1 | 0% | 998 | 1,007 | +1% | 0 | 0 | — |
case-06 | fail→fail | 15,921 | 7,360 | -54% | 1 | 1 | 0% | 3,215 | 1,173 | -64% | 0 | 0 | — |
case-07 | fail→pass | 9,771 | 2,160 | -78% | 1 | 1 | 0% | 1,654 | 860 | -48% | 0 | 0 | — |
case-08 | fail→pass | 2,724 | 2,567 | -6% | 1 | 1 | 0% | 395 | 991 | +151% | 0 | 0 | — |
case-09 | fail→pass | 2,132 | 1,501 | -30% | 1 | 1 | 0% | 297 | 791 | +166% | 0 | 0 | — |
case-10 | fail→pass | 16,030 | 6,111 | -62% | 1 | 1 | 0% | 2,648 | 1,746 | -34% | 0 | 0 | — |
case-20 | pass→pass | 11,456 | 6,279 | -45% | 1 | 1 | 0% | 2,238 | 1,755 | -22% | 0 | 0 | — |
case-11 | fail→pass | 10,358 | 2,984 | -71% | 1 | 1 | 0% | 1,719 | 1,090 | -37% | 0 | 0 | — |
case-12 | fail→fail | 10,094 | 5,196 | -49% | 1 | 1 | 0% | 1,916 | 783 | -59% | 0 | 0 | — |
case-13 | fail→fail | 14,762 | 2,713 | -82% | 1 | 1 | 0% | 2,797 | 769 | -73% | 0 | 0 | — |
case-14 | pass→pass | 5,405 | 3,219 | -40% | 1 | 1 | 0% | 1,070 | 1,153 | +8% | 0 | 0 | — |
case-15 | fail→pass | 2,962 | 1,268 | -57% | 1 | 1 | 0% | 402 | 731 | +82% | 0 | 0 | — |
case-16 | fail→fail | 15,038 | 3,206 | -79% | 1 | 1 | 0% | 2,829 | 856 | -70% | 0 | 0 | — |
case-17 | pass→pass | 6,702 | 1,861 | -72% | 1 | 1 | 0% | 1,156 | 818 | -29% | 0 | 0 | — |
case-18 | fail→pass | 10,252 | 1,873 | -82% | 1 | 1 | 0% | 1,750 | 815 | -53% | 0 | 0 | — |
case-19 | fail→fail | 18,988 | 5,903 | -69% | 1 | 1 | 0% | 3,982 | 996 | -75% | 0 | 0 | — |
case-21 | pass→pass | 17,045 | 13,987 | -18% | 1 | 1 | 0% | 3,541 | 3,456 | -2% | 0 | 0 | — |
case-22 | pass→pass | 15,637 | 11,347 | -27% | 1 | 1 | 0% | 2,911 | 2,932 | +1% | 0 | 0 | — |
case-23 | pass→pass | 12,921 | 7,910 | -39% | 1 | 1 | 0% | 2,746 | 2,144 | -22% | 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. 23 cases were attempted, and 21 counted toward the lift figure. The other 2 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 +39 percentage points is the difference between those two pass rates over the 21 comparable cases.
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.