performance-smoke-testing
Use when a criterion mentions speed or limits, or the change touches a list, query, endpoint or page that could get slower - timing loops, the N-vs-10N data check and Lighthouse on a production build
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-15
- Stars
- ★ 122
- Forks
- 18
01 前言 Front Matter
- name
- performance-smoke-testing
- category
- qa
- description
- Use when a criterion mentions speed or limits, or the change touches a list, query, endpoint or page that could get slower - timing loops, the N-vs-10N data check and Lighthouse on a production build
03 SKILL.md 正文
Performance Smoke Testing
Not full load testing — a smoke check run locally, never against stage or prod.
API
for i in $(seq 20); do curl -s -o /dev/null -w '%{time_total}\n' "$BASE/api/tasks?limit=50"; done | sort -n | awk '{a[NR]=$1} END{print "p50="a[int(NR*.5)]" p95="a[int(NR*.95)]" max="a[NR]}'
Then run the same with 10x the seeded rows. p95 growing more than 3x for 10x the data is an N+1 suspicion — report it with the two numbers. Fail bar: p95 >1s for a simple read on localhost, or any number a criterion states explicitly. 0.5-1s is a note, not a fail.
Concurrency smoke
Only when the change implies it (a shared resource, a write path under contention):
npx -y autocannon -c 10 -d 10 <url>
Errors must be 0.
Web
Measure a production build, never a dev server — dev builds are unoptimized and that is where false fails come from:
npm run build && (nohup npx vite preview --port 4173 > "$QA/preview.log" 2>&1 &)
CHROME_PATH="$CHROME_BIN" npx -y lighthouse@13 http://localhost:4173/<page> --only-categories=performance --form-factor=mobile --screenEmulation.width=360 --chrome-flags="--headless=new" --output=json --output-path="$QA/lh-perf.json"
Report LCP/CLS/TBT against "good": LCP ≤2.5s, CLS ≤0.1, TBT ≤200ms. Fail only for a criterion's own number or a CLS shift you can see on a changed screen; other misses are notes, not fails.
Never
Load-test stage or prod. Use k6 only when the repo already ships k6 scripts — not as the default tool.
Recording
Record cases as category: other with a title prefix perf: — the category enum has no performance value of its own.
04 同仓库更多 Skills
visual-craft
暂无简介
ux-copy
Use when you write any words a user reads in a mockup or a hand-off - content language and voice, buttons, labels, errors, empty states, confirmations, numbers and dates, and the longest-string check
screen-mockup-html
Use when you draw screens as the design task's HTML mockup - ONE canvas document holding every screen and every variant side by side, the sanitizer-safe recipe, phone and wide frames, the states grid, static control states, and the loopback self-check with screenshots at 375, 768 and 1440 attached to the task
performance-awareness
How the performance score moves for your role. Use when the score context shows a declining trend, or before handing off work you have not self-checked against every criterion.
design-variants
Use when a screen design needs variants - how many, variants as side-by-side rows on the one canvas, what makes two variants genuinely different, recommending one, how the human's choice is read, and narrowing to the chosen one in revision
design-system-authoring
Use when you derive, change or extend a design system - where tokens live per stack, the DTCG token tree, role-based names for both themes, base vs layer vs drift, the DESIGN.md section order, the inventory format, the contrast check and the lint every proposal returns