Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate markstream-vue into plain Vue 3 with renderer modes, code and DOM choices, streaming state, virtualization, optional peers, and scoped components.
.claude/skills/sickn33-markstream-vue/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -55% | 0% |
Configure the Vue 3 renderer beyond generic installation: surface modes, streaming lifecycle, code rendering, long-message virtualization, and scoped overrides.
Use for a plain Vue 3 application after the package has been selected. Use markstream-nuxt when SSR-specific Nuxt boundaries matter.
Before changing dependencies or source files, inspect the existing package manager and project conventions, preview the intended edits, and obtain explicit user approval.
markstream-vue/index.css after resets.content. Use mode="chat" for AI streams, docs for rich documents, and minimal for lightweight non-chat surfaces.pre without a peer, shiki with stream-markdown, or compatibility-named monaco backed by stream-diffs.auto, no fade, and an optional cursor. On completion keep the same mode, set final, and disable pacing/cursor.nodes only for worker parsing or structural AST ownership.vue<script setup lang="ts"> import MarkdownRender from 'markstream-vue' import 'markstream-vue/index.css' defineProps<{ content: string; isDone: boolean }>() </script> <template> <MarkdownRender mode="chat" :content="content" :final="isDone" :fade="isDone" :typewriter="!isDone" :smooth-streaming="isDone ? false : 'auto'" html-policy="safe" /> </template>
Review dependency changes. Never enable trusted HTML or loose Mermaid rendering for untrusted model output.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,206 | 7,387 | -51% | 1 | 1 | 0% | 2,851 | 1,886 | -34% | 0 | 0 | — |
case-02 | fail→fail | 18,306 | 10,912 | -40% | 1 | 1 | 0% | 3,021 | 2,407 | -20% | 0 | 0 | — |
case-11 | fail→pass | 10,524 | 2,841 | -73% | 1 | 1 | 0% | 1,747 | 975 | -44% | 0 | 0 | — |
case-03 | fail→pass | 18,581 | 6,900 | -63% | 1 | 1 | 0% | 4,068 | 1,651 | -59% | 0 | 0 | — |
case-04 | fail→pass | 16,283 | 4,443 | -73% | 1 | 1 | 0% | 2,877 | 1,404 | -51% | 0 | 0 | — |
case-05 | pass→pass | 13,826 | 3,685 | -73% | 1 | 1 | 0% | 2,455 | 1,156 | -53% | 0 | 0 | — |
case-06 | fail→pass | 15,743 | 3,884 | -75% | 1 | 1 | 0% | 2,765 | 1,241 | -55% | 0 | 0 | — |
case-07 | fail→pass | 8,328 | 3,060 | -63% | 1 | 1 | 0% | 1,559 | 1,069 | -31% | 0 | 0 | — |
case-08 | fail→pass | 10,456 | 3,259 | -69% | 1 | 1 | 0% | 1,868 | 1,100 | -41% | 0 | 0 | — |
case-09 | pass→pass | 10,687 | 4,784 | -55% | 1 | 1 | 0% | 1,799 | 1,393 | -23% | 0 | 0 | — |
case-10 | pass→pass | 7,303 | 3,731 | -49% | 1 | 1 | 0% | 1,113 | 1,172 | +5% | 0 | 0 | — |
case-12 | pass→pass | 4,645 | 2,489 | -46% | 1 | 1 | 0% | 738 | 1,010 | +37% | 0 | 0 | — |
case-13 | fail→pass | 12,995 | 8,444 | -35% | 1 | 1 | 0% | 2,471 | 2,102 | -15% | 0 | 0 | — |
case-14 | fail→pass | 7,289 | 1,736 | -76% | 1 | 1 | 0% | 1,146 | 809 | -29% | 0 | 0 | — |
case-15 | pass→pass | 11,376 | 4,917 | -57% | 1 | 1 | 0% | 1,936 | 1,395 | -28% | 0 | 0 | — |
case-16 | pass→pass | 14,162 | 5,465 | -61% | 1 | 1 | 0% | 2,432 | 1,535 | -37% | 0 | 0 | — |
case-17 | fail→pass | 8,235 | 1,601 | -81% | 1 | 1 | 0% | 1,276 | 784 | -39% | 0 | 0 | — |
case-18 | pass→pass | 15,458 | 14,366 | -7% | 1 | 1 | 0% | 2,512 | 2,769 | +10% | 0 | 0 | — |
case-19 | pass→pass | 13,362 | 6,635 | -50% | 1 | 1 | 0% | 2,123 | 1,647 | -22% | 0 | 0 | — |
case-20 | fail→pass | 20,839 | 8,992 | -57% | 1 | 1 | 0% | 3,681 | 2,076 | -44% | 0 | 0 | — |
case-21 | pass→pass | 17,360 | 9,122 | -47% | 1 | 1 | 0% | 3,403 | 2,368 | -30% | 0 | 0 | — |
case-22 | pass→pass | 14,404 | 14,490 | +1% | 1 | 1 | 0% | 3,100 | 3,725 | +20% | 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 +50 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.