Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Integrate markstream-vue2 into Vue CLI or Webpack 4 with export-map-safe CSS, CDN worker fallbacks, and conservative code-block defaults.
.claude/skills/sickn33-markstream-vue2-cli/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -36% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -27% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -14% | 0% |
Handle Vue CLI and Webpack 4 constraints that differ materially from modern Vue 2/Vite setup.
Use when Vue 2 runs on Vue CLI or Webpack 4 and package export maps or Vite worker imports are unavailable.
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 and only requested peers.markstream-vue2/dist/index.css, because legacy tooling may not understand the CSS export map.?worker imports. Use Markstream CDN worker helpers for KaTeX or Mermaid only when needed.stream-markdown code blocks over fragile Monaco worker wiring.content with smooth streaming for chat; set final and disable pacing/cursor for completed history.vue<script> import MarkdownRender from 'markstream-vue2' // Legacy Webpack may not resolve the package CSS export map. import 'markstream-vue2/dist/index.css' export default { components: { MarkdownRender }, data: () => ({ content: '# Answer', done: false }), } </script> <template> <MarkdownRender :content="content" :final="done" :fade="false" /> </template>
@vue/composition-api.Do not introduce CDN workers without reviewing CSP, network policy, and dependency trust. Preserve 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 | 14,807 | 8,355 | -44% | 1 | 1 | 0% | 3,270 | 2,108 | -36% | 0 | 0 | — |
case-02 | fail→pass | 18,695 | 10,257 | -45% | 1 | 1 | 0% | 3,513 | 2,485 | -29% | 0 | 0 | — |
case-03 | fail→pass | 20,122 | 9,637 | -52% | 1 | 1 | 0% | 4,318 | 2,369 | -45% | 0 | 0 | — |
case-04 | pass→pass | 13,030 | 8,469 | -35% | 1 | 1 | 0% | 2,561 | 1,906 | -26% | 0 | 0 | — |
case-05 | pass→pass | 20,361 | 11,455 | -44% | 1 | 1 | 0% | 4,270 | 2,716 | -36% | 0 | 0 | — |
case-06 | fail→fail | 15,758 | 11,548 | -27% | 1 | 1 | 0% | 3,187 | 2,934 | -8% | 0 | 0 | — |
case-07 | fail→pass | 7,331 | 3,323 | -55% | 1 | 1 | 0% | 1,503 | 1,094 | -27% | 0 | 0 | — |
case-08 | fail→pass | 11,334 | 7,640 | -33% | 1 | 1 | 0% | 2,237 | 1,920 | -14% | 0 | 0 | — |
case-09 | fail→pass | 13,900 | 5,931 | -57% | 1 | 1 | 0% | 2,300 | 1,302 | -43% | 0 | 0 | — |
case-10 | fail→pass | 13,721 | 5,439 | -60% | 1 | 1 | 0% | 2,180 | 1,394 | -36% | 0 | 0 | — |
case-11 | pass→pass | 11,203 | 4,600 | -59% | 1 | 1 | 0% | 2,166 | 1,296 | -40% | 0 | 0 | — |
case-12 | pass→pass | 18,986 | 11,756 | -38% | 1 | 1 | 0% | 3,069 | 2,292 | -25% | 0 | 0 | — |
case-13 | pass→pass | 6,051 | 3,762 | -38% | 1 | 1 | 0% | 1,213 | 1,117 | -8% | 0 | 0 | — |
case-14 | fail→pass | 12,107 | 3,545 | -71% | 1 | 1 | 0% | 2,193 | 1,001 | -54% | 0 | 0 | — |
case-15 | pass→pass | 18,562 | 11,037 | -41% | 1 | 1 | 0% | 3,181 | 2,314 | -27% | 0 | 0 | — |
case-16 | pass→pass | 7,567 | 3,358 | -56% | 1 | 1 | 0% | 1,405 | 1,029 | -27% | 0 | 0 | — |
case-17 | fail→pass | 11,972 | 3,444 | -71% | 1 | 1 | 0% | 2,096 | 987 | -53% | 0 | 0 | — |
case-18 | pass→pass | 7,373 | 2,705 | -63% | 1 | 1 | 0% | 1,158 | 904 | -22% | 0 | 0 | — |
case-19 | fail→fail | 9,234 | 5,499 | -40% | 1 | 1 | 0% | 1,627 | 1,365 | -16% | 0 | 0 | — |
case-20 | pass→pass | 15,804 | 5,392 | -66% | 1 | 1 | 0% | 2,964 | 1,402 | -53% | 0 | 0 | — |
case-21 | fail→pass | 14,625 | 7,494 | -49% | 1 | 1 | 0% | 2,529 | 1,906 | -25% | 0 | 0 | — |
case-22 | fail→fail | 7,340 | 1,969 | -73% | 1 | 1 | 0% | 1,102 | 754 | -32% | 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 +45 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.