Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create visualize finance logic diagrams (e.g., Draw.io XML) to explain complex finance transmission chains or finance logic flows.
.claude/skills/rkiding-alphaear-logic-visualizer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | 49% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 38% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | -25% | 0% |
| case-01 | ✗→✗ | ＝ Same ✗ | 14% | 0% |
This skill specializes in creating visual representations of logic flows, specifically generating Draw.io XML compatible diagrams. It is useful for visualizing investment theses or signal transmission chains.
YOU (the Agent) are the Visualizer. Use the prompts in references/PROMPTS.md to generate the XML.
Workflow:
references/PROMPTS.md to convert your logical chain into XML.scripts/visualizer.py method render_drawio_to_html(xml_content, filename) to save the XML into a viewable HTML file for the user.Example Usage (Conceptual):
visualizer.render_drawio_to_html(xml_content="<mxGraphModel>...", filename="chain_visual.html")| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 8,943 | 11,331 | +27% | 1 | 1 | 0% | 1,874 | 2,796 | +49% | 0 | 0 | — |
case-01 | fail→fail | 23,806 | 25,664 | +8% | 1 | 1 | 0% | 5,677 | 6,466 | +14% | 0 | 0 | — |
case-02 | fail→fail | 27,594 | 23,488 | -15% | 1 | 1 | 0% | 6,185 | 6,457 | +4% | 0 | 0 | — |
case-03 | fail→fail | 29,184 | 35,774 | +23% | 1 | 1 | 0% | 6,177 | 4,970 | -20% | 0 | 0 | — |
case-04 | pass→pass | 12,578 | 16,131 | +28% | 1 | 1 | 0% | 2,779 | 3,836 | +38% | 0 | 0 | — |
case-05 | pass→pass | 12,465 | 8,296 | -33% | 1 | 1 | 0% | 2,808 | 2,107 | -25% | 0 | 0 | — |
case-07 | fail→fail | 25,351 | 22,337 | -12% | 1 | 1 | 0% | 6,174 | 6,446 | +4% | 0 | 0 | — |
case-08 | fail→pass | 16,199 | 29,723 | +83% | 1 | 1 | 0% | 3,657 | 6,317 | +73% | 0 | 0 | — |
case-09 | fail→fail | 27,096 | 25,533 | -6% | 1 | 1 | 0% | 6,168 | 6,440 | +4% | 0 | 0 | — |
case-10 | fail→fail | 30,544 | 27,252 | -11% | 1 | 1 | 0% | 6,027 | 6,442 | +7% | 0 | 0 | — |
case-11 | fail→fail | 25,749 | 24,470 | -5% | 1 | 1 | 0% | 6,169 | 5,930 | -4% | 0 | 0 | — |
case-12 | fail→fail | 25,962 | 25,504 | -2% | 1 | 1 | 0% | 6,166 | 6,438 | +4% | 0 | 0 | — |
case-13 | fail→fail | 28,865 | 26,893 | -7% | 1 | 1 | 0% | 6,168 | 6,440 | +4% | 0 | 0 | — |
case-14 | fail→fail | 26,454 | 49,076 | +86% | 1 | 1 | 0% | 6,166 | 6,438 | +4% | 0 | 0 | — |
case-15 | fail→fail | 16,891 | 26,181 | +55% | 1 | 1 | 0% | 2,929 | 6,435 | +120% | 0 | 0 | — |
case-16 | fail→fail | 25,692 | 24,088 | -6% | 1 | 1 | 0% | 6,163 | 6,436 | +4% | 0 | 0 | — |
case-17 | fail→fail | 27,746 | 24,953 | -10% | 1 | 1 | 0% | 6,165 | 6,437 | +4% | 0 | 0 | — |
case-18 | fail→fail | 27,571 | 26,751 | -3% | 1 | 1 | 0% | 6,166 | 6,438 | +4% | 0 | 0 | — |
case-19 | fail→fail | 19,178 | 25,382 | +32% | 1 | 1 | 0% | 3,724 | 6,437 | +73% | 0 | 0 | — |
case-20 | fail→fail | 27,353 | 26,185 | -4% | 1 | 1 | 0% | 6,162 | 6,435 | +4% | 0 | 0 | — |
case-21 | fail→fail | 25,759 | 25,105 | -3% | 1 | 1 | 0% | 6,167 | 6,439 | +4% | 0 | 0 | — |
case-22 | fail→fail | 16,686 | 26,306 | +58% | 1 | 1 | 0% | 3,239 | 6,436 | +99% | 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. The headline lift of +5 percentage points is the difference between those two pass rates over the 22 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.