Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate markstream-vue2 into Vue 2 plus Vite with bundled worker imports, CSS ordering, Composition API compatibility, and safe streaming defaults.
.claude/skills/sickn33-markstream-vue2-vite/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -25% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -44% | 0% |
Use Vite-native worker bundling while preserving Vue 2 compatibility and rendering safety.
Use when the host is Vue 2 with Vite and needs bundled Mermaid or KaTeX workers. Use the generic Vue 2 skill when worker/bundler behavior is irrelevant.
Before changing dependencies or source files, inspect the existing package manager and project conventions, preview the intended edits, and obtain explicit user approval.
markstream-vue2/index.css after reset, Tailwind, or UnoCSS layers.?worker or ?worker&inline imports only when needed.@vue/composition-api only for Vue 2.6 code requiring it.content with smooth streaming for chat; set final and disable pacing/cursor for history.nodes only for externally owned parsing. Keep HTML safe and Mermaid strict.vue<script> import MarkdownRender from 'markstream-vue2' import 'markstream-vue2/index.css' export default { components: { MarkdownRender }, props: { content: String, done: Boolean }, } </script> <template> <MarkdownRender :content="content" :final="done" :fade="done" /> </template>
Review worker source, CSP, dependency changes, and bundle impact. Do not relax safe rendering defaults.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 22,995 | 6,495 | -72% | 1 | 1 | 0% | 4,427 | 1,620 | -63% | 0 | 0 | — |
case-02 | fail→pass | 19,164 | 9,765 | -49% | 1 | 1 | 0% | 3,829 | 2,278 | -41% | 0 | 0 | — |
case-03 | fail→pass | 20,857 | 9,650 | -54% | 1 | 1 | 0% | 3,970 | 2,239 | -44% | 0 | 0 | — |
case-04 | fail→pass | 10,834 | 6,393 | -41% | 1 | 1 | 0% | 2,133 | 1,594 | -25% | 0 | 0 | — |
case-14 | pass→fail | 14,480 | 7,852 | -46% | 1 | 1 | 0% | 2,519 | 1,722 | -32% | 0 | 0 | — |
case-05 | pass→pass | 6,356 | 4,910 | -23% | 1 | 1 | 0% | 1,323 | 1,301 | -2% | 0 | 0 | — |
case-06 | fail→pass | 17,296 | 7,839 | -55% | 1 | 1 | 0% | 3,339 | 1,866 | -44% | 0 | 0 | — |
case-07 | fail→pass | 13,437 | 6,867 | -49% | 1 | 1 | 0% | 2,729 | 1,632 | -40% | 0 | 0 | — |
case-08 | pass→pass | 9,364 | 4,656 | -50% | 1 | 1 | 0% | 1,788 | 1,243 | -30% | 0 | 0 | — |
case-09 | pass→pass | 8,992 | 3,369 | -63% | 1 | 1 | 0% | 1,689 | 1,050 | -38% | 0 | 0 | — |
case-10 | pass→pass | 9,281 | 2,682 | -71% | 1 | 1 | 0% | 1,712 | 904 | -47% | 0 | 0 | — |
case-11 | pass→pass | 21,931 | 12,437 | -43% | 1 | 1 | 0% | 4,219 | 2,549 | -40% | 0 | 0 | — |
case-12 | fail→pass | 6,331 | 3,300 | -48% | 1 | 1 | 0% | 1,206 | 1,031 | -15% | 0 | 0 | — |
case-13 | fail→pass | 10,768 | 3,582 | -67% | 1 | 1 | 0% | 1,853 | 914 | -51% | 0 | 0 | — |
case-15 | pass→pass | 13,408 | 10,791 | -20% | 1 | 1 | 0% | 2,315 | 2,167 | -6% | 0 | 0 | — |
case-16 | pass→pass | 10,347 | 5,405 | -48% | 1 | 1 | 0% | 1,848 | 1,377 | -25% | 0 | 0 | — |
case-17 | pass→pass | 11,600 | 4,260 | -63% | 1 | 1 | 0% | 1,879 | 1,102 | -41% | 0 | 0 | — |
case-18 | pass→pass | 11,923 | 4,942 | -59% | 1 | 1 | 0% | 2,704 | 1,404 | -48% | 0 | 0 | — |
case-19 | pass→pass | 7,527 | 3,291 | -56% | 1 | 1 | 0% | 1,364 | 944 | -31% | 0 | 0 | — |
case-20 | pass→pass | 10,067 | 6,780 | -33% | 1 | 1 | 0% | 1,988 | 1,795 | -10% | 0 | 0 | — |
case-21 | pass→pass | 6,741 | 7,624 | +13% | 1 | 1 | 0% | 1,276 | 1,911 | +50% | 0 | 0 | — |
case-22 | pass→pass | 11,480 | 7,914 | -31% | 1 | 1 | 0% | 2,227 | 2,066 | -7% | 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. 1 case got worse with the skill loaded, and it is 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.