Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand storytelling through design. Specializes in transforming complex information into engaging visual stories that connect with audiences and drive emotional engagement.
.claude/skills/30eggis-design-design-visual-storyteller/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 105% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 29% | 0% |
| case-11 | ✓→✗ | ▼ Worse | 86% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 94% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 80% | 0% |
<!-- Imported from agency-agents: design/design-visual-storyteller.md Original frontmatter: name: Visual Storyteller description: Expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand storytelling through design. Specializes in transforming complex information into engaging visual stories that connect with audiences and drive emotional engagement. color: purple emoji: 🎬 vibe: Transforms complex information into visual narratives that move people. -->
You are a Visual Storyteller, an expert visual communication specialist focused on creating compelling visual narratives, multimedia content, and brand storytelling through design. You specialize in transforming complex information into engaging visual stories that connect with audiences and drive emotional engagement.
bash# Analyze brand narrative and communication goals cat ai/memory-bank/brand-guidelines.md cat ai/memory-bank/audience-research.md # Review existing visual assets and brand story ls public/images/brand/ grep -i "story\|narrative\|message" ai/memory-bank/*.md
You're successful when:
Instructions Reference: Your detailed visual storytelling methodology is in this agent definition - refer to these patterns for consistent visual narrative creation, multimedia design excellence, and cross-platform adaptation strategies.
/hiring and /resource-manager wiring..harness/documents/{mission_name}/workers/{name}.md unless the requester specifies another mission document.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 24,197 | 27,022 | +12% | 1 | 1 | 0% | 3,774 | 5,177 | +37% | 0 | 0 | — |
case-02 | fail→fail | 26,684 | 27,612 | +3% | 1 | 1 | 0% | 4,237 | 5,832 | +38% | 0 | 0 | — |
case-03 | fail→pass | 16,505 | 22,452 | +36% | 1 | 1 | 0% | 2,546 | 5,230 | +105% | 0 | 0 | — |
case-04 | fail→pass | 21,224 | 18,204 | -14% | 1 | 1 | 0% | 3,282 | 4,246 | +29% | 0 | 0 | — |
case-05 | pass→pass | 16,790 | 22,638 | +35% | 1 | 1 | 0% | 2,676 | 5,195 | +94% | 0 | 0 | — |
case-06 | pass→pass | 14,408 | 17,240 | +20% | 1 | 1 | 0% | 2,338 | 4,203 | +80% | 0 | 0 | — |
case-07 | fail→fail | 14,880 | 19,755 | +33% | 1 | 1 | 0% | 2,244 | 4,301 | +92% | 0 | 0 | — |
case-08 | pass→pass | 37,007 | 26,074 | -30% | 1 | 1 | 0% | 3,786 | 5,720 | +51% | 0 | 0 | — |
case-09 | pass→pass | 19,264 | 43,958 | +128% | 1 | 1 | 0% | 2,420 | 5,319 | +120% | 0 | 0 | — |
case-10 | pass→pass | 17,742 | 22,434 | +26% | 1 | 1 | 0% | 2,636 | 4,685 | +78% | 0 | 0 | — |
case-11 | pass→fail | 17,591 | 27,466 | +56% | 1 | 1 | 0% | 3,470 | 6,442 | +86% | 0 | 0 | — |
case-12 | fail→fail | 10,718 | 9,106 | -15% | 1 | 1 | 0% | 2,176 | 3,384 | +56% | 0 | 0 | — |
case-13 | fail→fail | 15,787 | 15,642 | -1% | 1 | 1 | 0% | 2,352 | 4,044 | +72% | 0 | 0 | — |
case-14 | pass→pass | 17,507 | 19,345 | +10% | 1 | 1 | 0% | 2,754 | 4,221 | +53% | 0 | 0 | — |
case-15 | pass→pass | 18,093 | 26,694 | +48% | 1 | 1 | 0% | 2,913 | 5,595 | +92% | 0 | 0 | — |
case-16 | pass→pass | 29,925 | 20,015 | -33% | 1 | 1 | 0% | 2,898 | 4,526 | +56% | 0 | 0 | — |
case-17 | pass→pass | 16,967 | 19,478 | +15% | 1 | 1 | 0% | 2,789 | 4,521 | +62% | 0 | 0 | — |
case-18 | pass→pass | 16,725 | 16,006 | -4% | 1 | 1 | 0% | 2,608 | 3,827 | +47% | 0 | 0 | — |
case-19 | pass→pass | 15,512 | 16,664 | +7% | 1 | 1 | 0% | 2,387 | 3,921 | +64% | 0 | 0 | — |
case-20 | pass→pass | 15,340 | 25,700 | +68% | 1 | 1 | 0% | 2,493 | 3,787 | +52% | 0 | 0 | — |
case-21 | pass→pass | 16,864 | 27,301 | +62% | 1 | 1 | 0% | 2,563 | 5,412 | +111% | 0 | 0 | — |
case-22 | pass→pass | 13,193 | 18,046 | +37% | 1 | 1 | 0% | 2,176 | 3,928 | +81% | 0 | 0 | — |
case-23 | pass→pass | 15,453 | 21,236 | +37% | 1 | 1 | 0% | 2,378 | 5,048 | +112% | 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. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 comparable cases. 2 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.