Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate markstream-vue into Nuxt 3 or 4 with SSR-safe client boundaries, renderer modes, explicit CSS, and browser-only optional peers.
.claude/skills/sickn33-markstream-nuxt/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -47% | 0% |
Integrate markstream-vue into Nuxt while keeping hydration, browser-only peers, workers, and streaming behavior on the correct side of SSR boundaries.
Use for Nuxt 3 or 4 pages, components, or plugins. Use markstream-vue for non-Nuxt Vue applications and markstream-install when the framework is not yet known.
Before changing dependencies or source files, inspect the existing package manager and project conventions, preview the intended edits, and obtain explicit user approval.
<ClientOnly>, .client plugins, dynamic imports, or guarded initialization.markstream-vue/index.css explicitly from a client-safe shell or plugin.content: mode="chat" for AI streams, docs for rich documents, and minimal for lightweight non-chat surfaces.auto mode for SSR; do not force true on first-screen server content.final, disable pacing/cursor, and enable fade only if desired.vue<script setup lang="ts"> import MarkdownRender from 'markstream-vue' import 'markstream-vue/index.css' defineProps<{ markdown: string; done: boolean }>() </script> <template> <MarkdownRender mode="chat" :content="markdown" :final="done" :fade="done" :typewriter="!done" :smooth-streaming="done ? false : 'auto'" html-policy="safe" /> </template>
Do not expose trusted HTML or loose Mermaid settings to untrusted model output. Review dependency and runtime-boundary changes.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,435 | 10,327 | -47% | 1 | 1 | 0% | 3,542 | 2,478 | -30% | 0 | 0 | — |
case-02 | fail→pass | 12,077 | 10,999 | -9% | 1 | 1 | 0% | 2,272 | 2,687 | +18% | 0 | 0 | — |
case-03 | fail→pass | 18,743 | 8,596 | -54% | 1 | 1 | 0% | 3,720 | 2,229 | -40% | 0 | 0 | — |
case-04 | fail→pass | 6,662 | 3,087 | -54% | 1 | 1 | 0% | 1,086 | 1,032 | -5% | 0 | 0 | — |
case-05 | pass→pass | 9,527 | 2,094 | -78% | 1 | 1 | 0% | 1,898 | 886 | -53% | 0 | 0 | — |
case-06 | pass→pass | 11,057 | 3,968 | -64% | 1 | 1 | 0% | 1,803 | 1,171 | -35% | 0 | 0 | — |
case-07 | pass→pass | 12,589 | 3,933 | -69% | 1 | 1 | 0% | 1,980 | 1,177 | -41% | 0 | 0 | — |
case-08 | pass→pass | 10,454 | 4,738 | -55% | 1 | 1 | 0% | 1,772 | 1,252 | -29% | 0 | 0 | — |
case-09 | pass→pass | 11,826 | 3,481 | -71% | 1 | 1 | 0% | 1,851 | 1,141 | -38% | 0 | 0 | — |
case-10 | pass→pass | 12,521 | 7,338 | -41% | 1 | 1 | 0% | 2,116 | 1,858 | -12% | 0 | 0 | — |
case-11 | pass→pass | 3,424 | 2,295 | -33% | 1 | 1 | 0% | 498 | 895 | +80% | 0 | 0 | — |
case-12 | fail→pass | 11,173 | 2,977 | -73% | 1 | 1 | 0% | 1,923 | 1,028 | -47% | 0 | 0 | — |
case-13 | fail→pass | 13,766 | 4,450 | -68% | 1 | 1 | 0% | 2,467 | 1,304 | -47% | 0 | 0 | — |
case-14 | fail→pass | 8,503 | 2,442 | -71% | 1 | 1 | 0% | 1,458 | 890 | -39% | 0 | 0 | — |
case-15 | pass→pass | 14,529 | 9,720 | -33% | 1 | 1 | 0% | 2,785 | 2,149 | -23% | 0 | 0 | — |
case-16 | pass→pass | 8,628 | 2,503 | -71% | 1 | 1 | 0% | 1,484 | 934 | -37% | 0 | 0 | — |
case-17 | pass→pass | 7,546 | 3,544 | -53% | 1 | 1 | 0% | 1,257 | 1,011 | -20% | 0 | 0 | — |
case-18 | pass→pass | 13,990 | 8,093 | -42% | 1 | 1 | 0% | 2,324 | 1,821 | -22% | 0 | 0 | — |
case-19 | fail→pass | 16,049 | 2,992 | -81% | 1 | 1 | 0% | 2,701 | 1,024 | -62% | 0 | 0 | — |
case-20 | pass→pass | 6,979 | 3,634 | -48% | 1 | 1 | 0% | 1,284 | 1,183 | -8% | 0 | 0 | — |
case-21 | pass→pass | 6,558 | 4,744 | -28% | 1 | 1 | 0% | 1,279 | 1,234 | -4% | 0 | 0 | — |
case-22 | pass→pass | 14,335 | 12,348 | -14% | 1 | 1 | 0% | 2,904 | 2,972 | +2% | 0 | 0 | — |
case-23 | pass→pass | 5,493 | 5,618 | +2% | 1 | 1 | 0% | 1,115 | 1,582 | +42% | 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 +35 percentage points is the difference between those two pass rates over the 23 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.