Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate the beta markstream-svelte renderer into Svelte 5 or SvelteKit with runes, explicit CSS, smooth streaming, workers, and SSR-safe boundaries.
.claude/skills/sickn33-markstream-svelte/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -42% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -8% | 0% |
Integrate Markstream using Svelte 5 runes and SvelteKit-safe browser boundaries.
Use for Svelte 5 or SvelteKit package setup, streaming state, workers, or scoped custom components. Svelte 4 is unsupported.
Before changing dependencies or source files, inspect the existing package manager and project conventions, preview the intended edits, and obtain explicit user approval.
<MarkdownRender {content} /> and smooth streaming auto.final, disable pacing/cursor, and enable fade only if desired.nodes only for worker-owned parsing or shared AST state.$props() and callbacks. Configure KaTeX or Mermaid workers only when requested.customComponents; use scoped registration only when sharing is intentional.svelte-check, build, or e2e.svelte<script lang="ts"> import MarkdownRender from 'markstream-svelte' import 'markstream-svelte/index.css' let { content, isDone }: { content: string; isDone: boolean } = $props() </script> <MarkdownRender {content} final={isDone} fade={isDone} typewriter={!isDone} smoothStreaming={isDone ? false : 'auto'} htmlPolicy="safe" />
Keep safe HTML and strict Mermaid defaults. Review dependencies and never run browser-only peers during SSR.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,766 | 7,648 | -61% | 1 | 1 | 0% | 3,963 | 1,933 | -51% | 0 | 0 | — |
case-02 | fail→pass | 12,900 | 7,649 | -41% | 1 | 1 | 0% | 2,550 | 1,914 | -25% | 0 | 0 | — |
case-03 | fail→pass | 19,490 | 8,354 | -57% | 1 | 1 | 0% | 3,636 | 2,123 | -42% | 0 | 0 | — |
case-04 | fail→pass | 7,287 | 2,730 | -63% | 1 | 1 | 0% | 1,320 | 900 | -32% | 0 | 0 | — |
case-05 | pass→pass | 11,496 | 4,171 | -64% | 1 | 1 | 0% | 2,036 | 1,220 | -40% | 0 | 0 | — |
case-06 | fail→fail | 9,837 | 5,722 | -42% | 1 | 1 | 0% | 1,745 | 1,503 | -14% | 0 | 0 | — |
case-07 | fail→pass | 7,549 | 4,246 | -44% | 1 | 1 | 0% | 1,269 | 1,169 | -8% | 0 | 0 | — |
case-08 | fail→pass | 6,841 | 2,227 | -67% | 1 | 1 | 0% | 1,176 | 860 | -27% | 0 | 0 | — |
case-09 | fail→pass | 10,593 | 4,468 | -58% | 1 | 1 | 0% | 1,832 | 1,140 | -38% | 0 | 0 | — |
case-10 | pass→pass | 9,648 | 3,028 | -69% | 1 | 1 | 0% | 1,616 | 962 | -40% | 0 | 0 | — |
case-11 | pass→pass | 13,697 | 8,003 | -42% | 1 | 1 | 0% | 2,571 | 1,989 | -23% | 0 | 0 | — |
case-12 | pass→pass | 6,342 | 2,070 | -67% | 1 | 1 | 0% | 1,124 | 808 | -28% | 0 | 0 | — |
case-13 | pass→pass | 5,620 | 2,576 | -54% | 1 | 1 | 0% | 930 | 876 | -6% | 0 | 0 | — |
case-14 | pass→pass | 6,498 | 3,713 | -43% | 1 | 1 | 0% | 952 | 1,056 | +11% | 0 | 0 | — |
case-15 | pass→pass | 4,069 | 2,243 | -45% | 1 | 1 | 0% | 653 | 823 | +26% | 0 | 0 | — |
case-16 | pass→pass | 9,914 | 3,273 | -67% | 1 | 1 | 0% | 1,676 | 936 | -44% | 0 | 0 | — |
case-17 | pass→pass | 8,290 | 3,818 | -54% | 1 | 1 | 0% | 1,339 | 1,133 | -15% | 0 | 0 | — |
case-18 | pass→pass | 9,045 | 2,562 | -72% | 1 | 1 | 0% | 1,578 | 893 | -43% | 0 | 0 | — |
case-19 | pass→pass | 4,564 | 1,852 | -59% | 1 | 1 | 0% | 751 | 739 | -2% | 0 | 0 | — |
case-20 | pass→pass | 14,980 | 12,080 | -19% | 1 | 1 | 0% | 3,198 | 2,938 | -8% | 0 | 0 | — |
case-21 | pass→pass | 10,999 | 10,393 | -6% | 1 | 1 | 0% | 2,310 | 2,247 | -3% | 0 | 0 | — |
case-22 | pass→pass | 10,412 | 8,046 | -23% | 1 | 1 | 0% | 2,157 | 2,072 | -4% | 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 +32 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.