Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate markstream-vue2 into Vue 2.6 or 2.7 with correct Composition API decisions, CSS, streaming state, optional peers, and scoped overrides.
.claude/skills/sickn33-markstream-vue2/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -28% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -24% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -63% | 0% |
Handle Vue 2.6/2.7 compatibility decisions that the generic installer cannot resolve safely.
Use for Vue 2 integration when no bundler-specific edge case dominates. Use markstream-vue2-cli for Vue CLI/Webpack 4 and markstream-vue2-vite for Vite worker imports.
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.@vue/composition-api only for Vue 2.6 code that uses Composition API patterns; Vue 2.7 has built-in support.markstream-vue2/index.css after resets.<MarkdownRender :content="markdown" /> and smooth streaming auto.final, disable pacing/cursor, and enable fade only if desired.nodes only when another layer owns parsing. Use scoped mappings for overrides.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" :typewriter="!done" /> </template>
Review dependency and compatibility changes. Do not relax rendering safety for untrusted content.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 15,220 | 8,826 | -42% | 1 | 1 | 0% | 3,173 | 2,299 | -28% | 0 | 0 | — |
case-02 | fail→pass | 13,946 | 9,275 | -33% | 1 | 1 | 0% | 2,693 | 2,449 | -9% | 0 | 0 | — |
case-03 | fail→pass | 15,633 | 9,427 | -40% | 1 | 1 | 0% | 2,959 | 2,263 | -24% | 0 | 0 | — |
case-04 | fail→pass | 13,652 | 3,538 | -74% | 1 | 1 | 0% | 2,449 | 1,064 | -57% | 0 | 0 | — |
case-05 | fail→pass | 11,407 | 1,858 | -84% | 1 | 1 | 0% | 2,117 | 793 | -63% | 0 | 0 | — |
case-06 | pass→pass | 5,549 | 2,945 | -47% | 1 | 1 | 0% | 1,060 | 985 | -7% | 0 | 0 | — |
case-07 | pass→pass | 9,786 | 3,888 | -60% | 1 | 1 | 0% | 1,685 | 1,184 | -30% | 0 | 0 | — |
case-08 | pass→pass | 6,462 | 3,268 | -49% | 1 | 1 | 0% | 1,152 | 1,016 | -12% | 0 | 0 | — |
case-09 | fail→pass | 16,116 | 6,687 | -59% | 1 | 1 | 0% | 2,955 | 1,591 | -46% | 0 | 0 | — |
case-10 | fail→pass | 13,454 | 5,339 | -60% | 1 | 1 | 0% | 2,682 | 1,488 | -45% | 0 | 0 | — |
case-11 | pass→pass | 11,718 | 5,007 | -57% | 1 | 1 | 0% | 2,036 | 1,388 | -32% | 0 | 0 | — |
case-12 | fail→pass | 6,759 | 4,563 | -32% | 1 | 1 | 0% | 1,167 | 1,259 | +8% | 0 | 0 | — |
case-13 | pass→pass | 12,269 | 6,063 | -51% | 1 | 1 | 0% | 2,127 | 1,438 | -32% | 0 | 0 | — |
case-14 | fail→pass | 13,970 | 3,501 | -75% | 1 | 1 | 0% | 2,509 | 1,191 | -53% | 0 | 0 | — |
case-15 | pass→pass | 22,025 | 9,748 | -56% | 1 | 1 | 0% | 3,835 | 2,244 | -41% | 0 | 0 | — |
case-16 | fail→pass | 6,874 | 1,483 | -78% | 1 | 1 | 0% | 1,197 | 711 | -41% | 0 | 0 | — |
case-17 | fail→pass | 4,657 | 4,331 | -7% | 1 | 1 | 0% | 841 | 1,178 | +40% | 0 | 0 | — |
case-18 | fail→pass | 8,438 | 2,273 | -73% | 1 | 1 | 0% | 1,442 | 849 | -41% | 0 | 0 | — |
case-19 | fail→pass | 13,874 | 4,040 | -71% | 1 | 1 | 0% | 2,498 | 1,305 | -48% | 0 | 0 | — |
case-20 | fail→pass | 12,918 | 5,014 | -61% | 1 | 1 | 0% | 2,111 | 1,485 | -30% | 0 | 0 | — |
case-21 | pass→pass | 6,281 | 2,471 | -61% | 1 | 1 | 0% | 1,125 | 858 | -24% | 0 | 0 | — |
case-22 | pass→pass | 8,505 | 3,960 | -53% | 1 | 1 | 0% | 1,547 | 1,221 | -21% | 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 +64 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.