Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transiti
.claude/skills/kunanonj-cursor-plugin-modern-web-modern-web-guidance/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -2% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 14% | 0% |
A skill to search for specific web development use cases and retrieve their corresponding best practice guides.
Must use this skill:
Search with an action-oriented query summarizing what you want to achieve using the search command. Run modern-web-guidance directly with npx.
shnpx -y modern-web-guidance@latest search "<query>" --skill-version 2026_05_16-c5e7870
Example Output:
json[ { "id": "optimize-image-priority", "description": "Optimize the loading priority of Largest Contentful Paint (LCP) candidate images.", "category": "performance", "featuresUsed": [ "Fetch priority" ], "tokenCount": 985, "similarity": 0.7289 }, { "id": "defer-rendering-heavy-content", "description": "Reduce rendering times in content-heavy web pages by deferring rendering for offscreen content.", "category": "performance", "featuresUsed": [ "content-visibility", "hidden=\"until-found\"" ], "tokenCount": 1250, "similarity": 0.6961 } ]
> Note: If search results are vague, return no matches, or show low similarity scores, run the list command to browse all guides: > sh > npx -y modern-web-guidance@latest list >
Once you have a relevant id from the search results, call this script using the retrieve command to get the full guide. You can pass multiple IDs separated by commas.
shnpx -y modern-web-guidance@latest retrieve "<id>"
Example Output: The markdown content of the guide describing implementation steps...
npx may fail. Use npx.cmd ... instead.npx -y modern-web-guidance… command hangs, you may be offline. Try running again in offlinemode: npx --offline ….
--skill-version flag is used to determine if this SKILL.md is out of date. If it is, a warningmessage is logged to stderr.
No defined policy format. This is an example: **Browser Support:** Allow Newly Available features, but only adopt custom fallback code that adds <= 20 lines and does not require external dependencies.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,569 | 4,500 | -41% | 1 | 1 | 0% | 1,515 | 1,499 | -1% | 0 | 0 | — |
case-02 | fail→fail | 9,999 | 4,571 | -54% | 1 | 1 | 0% | 2,117 | 1,369 | -35% | 0 | 0 | — |
case-03 | fail→fail | 11,163 | 4,625 | -59% | 1 | 1 | 0% | 2,381 | 1,440 | -40% | 0 | 0 | — |
case-04 | fail→pass | 6,943 | 2,750 | -60% | 1 | 1 | 0% | 1,365 | 1,744 | +28% | 0 | 0 | — |
case-05 | fail→pass | 8,155 | 2,054 | -75% | 1 | 1 | 0% | 1,512 | 1,488 | -2% | 0 | 0 | — |
case-06 | fail→pass | 14,762 | 2,050 | -86% | 1 | 1 | 0% | 904 | 1,551 | +72% | 0 | 0 | — |
case-07 | fail→fail | 7,326 | 1,288 | -82% | 1 | 1 | 0% | 1,362 | 1,362 | 0% | 0 | 0 | — |
case-08 | pass→pass | 7,680 | 1,619 | -79% | 1 | 1 | 0% | 1,396 | 1,409 | +1% | 0 | 0 | — |
case-09 | pass→pass | 9,904 | 3,419 | -65% | 1 | 1 | 0% | 1,802 | 1,614 | -10% | 0 | 0 | — |
case-10 | pass→pass | 4,246 | 2,246 | -47% | 1 | 1 | 0% | 751 | 1,566 | +109% | 0 | 0 | — |
case-11 | fail→pass | 11,048 | 4,769 | -57% | 1 | 1 | 0% | 2,003 | 1,881 | -6% | 0 | 0 | — |
case-12 | fail→fail | 13,626 | 6,660 | -51% | 1 | 1 | 0% | 2,105 | 1,691 | -20% | 0 | 0 | — |
case-13 | fail→pass | 8,895 | 3,302 | -63% | 1 | 1 | 0% | 1,419 | 1,623 | +14% | 0 | 0 | — |
case-14 | pass→fail | 13,802 | 5,450 | -61% | 1 | 1 | 0% | 2,076 | 1,406 | -32% | 0 | 0 | — |
case-15 | pass→fail | 14,273 | 5,669 | -60% | 1 | 1 | 0% | 2,941 | 1,584 | -46% | 0 | 0 | — |
case-16 | pass→pass | 7,584 | 2,471 | -67% | 1 | 1 | 0% | 1,342 | 1,553 | +16% | 0 | 0 | — |
case-17 | pass→pass | 6,794 | 1,790 | -74% | 1 | 1 | 0% | 1,246 | 1,410 | +13% | 0 | 0 | — |
case-18 | pass→pass | 7,072 | 2,168 | -69% | 1 | 1 | 0% | 1,188 | 1,438 | +21% | 0 | 0 | — |
case-19 | pass→pass | 10,038 | 2,273 | -77% | 1 | 1 | 0% | 1,537 | 1,544 | +0% | 0 | 0 | — |
case-20 | pass→fail | 9,091 | 4,346 | -52% | 1 | 1 | 0% | 1,789 | 1,364 | -24% | 0 | 0 | — |
case-21 | pass→fail | 8,333 | 4,575 | -45% | 1 | 1 | 0% | 1,718 | 1,315 | -23% | 0 | 0 | — |
case-22 | pass→fail | 6,907 | 5,358 | -22% | 1 | 1 | 0% | 1,484 | 1,431 | -4% | 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, and 12 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 12 comparable cases. 5 cases got worse with the skill loaded, and they are 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.