Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when working on Deno projects and you want predictable module imports, permission-aware runtime behavior, and clean project structure.
.claude/skills/amariahak-deno-patterns/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -49% | 0% |
| case-02 | ✓→✓ | = Same ✓ | -7% | 0% |
| case-04 | ✓→✓ | = Same ✓ | -43% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 10% | 0% |
Use this skill when working on Deno projects and you want predictable module imports, permission-aware runtime behavior, and clean project structure.
Deno requires explicit permissions. Make them intentional:
--allow-net for network--allow-read for filesystem reads--allow-all in production scriptsCommon:
deno.json / deno.jsoncmod.ts as entrypoint for librariesmain.ts for appsdeno testdeno.json and entrypoints; trace imports.deno test and deno fmt if configured.--allow-all by default| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | pass→pass | 10,184 | 4,931 | -52% | 1 | 1 | 0% | 1,791 | 915 | -49% | 0 | 0 | — |
case-01 | fail→pass | 15,320 | 13,756 | -10% | 1 | 1 | 0% | 2,787 | 2,961 | +6% | 0 | 0 | — |
case-02 | pass→pass | 7,755 | 5,903 | -24% | 1 | 1 | 0% | 1,414 | 1,322 | -7% | 0 | 0 | — |
case-04 | pass→pass | 8,440 | 3,110 | -63% | 1 | 1 | 0% | 1,446 | 822 | -43% | 0 | 0 | — |
case-05 | pass→pass | 4,809 | 3,704 | -23% | 1 | 1 | 0% | 898 | 988 | +10% | 0 | 0 | — |
case-06 | pass→pass | 7,483 | 4,774 | -36% | 1 | 1 | 0% | 1,404 | 1,072 | -24% | 0 | 0 | — |
case-07 | pass→pass | 11,316 | 7,384 | -35% | 1 | 1 | 0% | 1,973 | 1,599 | -19% | 0 | 0 | — |
case-08 | pass→pass | 7,087 | 5,195 | -27% | 1 | 1 | 0% | 1,326 | 1,196 | -10% | 0 | 0 | — |
case-09 | pass→pass | 3,712 | 3,324 | -10% | 1 | 1 | 0% | 625 | 841 | +35% | 0 | 0 | — |
case-10 | pass→pass | 6,169 | 3,766 | -39% | 1 | 1 | 0% | 1,101 | 944 | -14% | 0 | 0 | — |
case-11 | pass→pass | 13,578 | 6,981 | -49% | 1 | 1 | 0% | 2,125 | 1,663 | -22% | 0 | 0 | — |
case-12 | pass→pass | 6,297 | 3,834 | -39% | 1 | 1 | 0% | 1,207 | 926 | -23% | 0 | 0 | — |
case-13 | pass→pass | 13,912 | 11,630 | -16% | 1 | 1 | 0% | 2,511 | 2,473 | -2% | 0 | 0 | — |
case-14 | pass→pass | 3,854 | 2,107 | -45% | 1 | 1 | 0% | 672 | 618 | -8% | 0 | 0 | — |
case-15 | pass→pass | 8,936 | 5,774 | -35% | 1 | 1 | 0% | 1,556 | 1,063 | -32% | 0 | 0 | — |
case-16 | pass→pass | 5,926 | 3,572 | -40% | 1 | 1 | 0% | 860 | 906 | +5% | 0 | 0 | — |
case-17 | pass→pass | 10,605 | 4,718 | -56% | 1 | 1 | 0% | 1,879 | 1,055 | -44% | 0 | 0 | — |
case-18 | pass→pass | 9,501 | 4,539 | -52% | 1 | 1 | 0% | 1,626 | 1,047 | -36% | 0 | 0 | — |
case-19 | pass→pass | 15,660 | 11,252 | -28% | 1 | 1 | 0% | 2,814 | 2,202 | -22% | 0 | 0 | — |
case-20 | pass→pass | 11,340 | 10,377 | -8% | 1 | 1 | 0% | 1,955 | 1,377 | -30% | 0 | 0 | — |
case-21 | pass→pass | 17,883 | 11,796 | -34% | 1 | 1 | 0% | 2,646 | 2,140 | -19% | 0 | 0 | — |
case-22 | pass→pass | 11,021 | 10,304 | -7% | 1 | 1 | 0% | 2,357 | 2,183 | -7% | 0 | 0 | — |
case-23 | pass→pass | 12,022 | 9,344 | -22% | 1 | 1 | 0% | 2,103 | 1,918 | -9% | 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. 23 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 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.