Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Deno development with integration techniques.
.claude/skills/amariahak-cursor-rules-for-deno-development-with-integration-techniques/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -79% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-19 | ✓→✗ | ▼ Worse | -19% | 0% |
| case-06 | ✓→✓ | ＝ Same ✓ | -14% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | -22% | 0% |
Cursor rules for Deno development with integration techniques.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/deno-integration-techniques-cursorrules-prompt-fil.mdc.
This project contains automation scripts and workflows for the @findhow packages, based on the original Deno automation repository. The goal is to provide consistent and efficient automation for the @findhow ecosystem.
The purpose of this project is to refactor and adapt the automation scripts from denoland/automation for use with the configured @findhow package repositories.
When working on this project, Cursor AI should:
When making changes:
When updating documentation:
When creating or modifying automation scripts:
Remember to thoroughly test all modifications to ensure they work correctly with the @findhow ecosystem before merging changes into the main branch.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | pass→pass | 5,316 | 4,057 | -24% | 1 | 1 | 0% | 1,003 | 865 | -14% | 0 | 0 | — |
case-01 | fail→fail | 34,222 | 14,044 | -59% | 1 | 1 | 0% | 1,287 | 3,064 | +138% | 0 | 0 | — |
case-02 | pass→pass | 12,121 | 8,374 | -31% | 1 | 1 | 0% | 2,358 | 1,835 | -22% | 0 | 0 | — |
case-03 | pass→pass | 9,910 | 5,713 | -42% | 1 | 1 | 0% | 1,563 | 1,122 | -28% | 0 | 0 | — |
case-04 | fail→pass | 15,409 | 1,967 | -87% | 1 | 1 | 0% | 2,444 | 517 | -79% | 0 | 0 | — |
case-05 | fail→pass | 5,906 | 2,286 | -61% | 1 | 1 | 0% | 1,024 | 567 | -45% | 0 | 0 | — |
case-07 | pass→pass | 7,697 | 7,623 | -1% | 1 | 1 | 0% | 1,245 | 1,487 | +19% | 0 | 0 | — |
case-08 | pass→pass | 13,166 | 8,233 | -37% | 1 | 1 | 0% | 2,442 | 1,701 | -30% | 0 | 0 | — |
case-09 | pass→pass | 7,724 | 5,658 | -27% | 1 | 1 | 0% | 1,251 | 1,121 | -10% | 0 | 0 | — |
case-10 | pass→pass | 10,960 | 6,998 | -36% | 1 | 1 | 0% | 1,972 | 1,601 | -19% | 0 | 0 | — |
case-11 | pass→pass | 16,371 | 12,526 | -23% | 1 | 1 | 0% | 2,182 | 2,418 | +11% | 0 | 0 | — |
case-12 | fail→fail | 11,541 | 7,628 | -34% | 1 | 1 | 0% | 2,132 | 1,390 | -35% | 0 | 0 | — |
case-13 | pass→pass | 11,861 | 5,850 | -51% | 1 | 1 | 0% | 2,197 | 1,266 | -42% | 0 | 0 | — |
case-14 | pass→pass | 10,418 | 7,791 | -25% | 1 | 1 | 0% | 1,975 | 1,660 | -16% | 0 | 0 | — |
case-15 | pass→pass | 22,518 | 8,146 | -64% | 1 | 1 | 0% | 2,217 | 1,686 | -24% | 0 | 0 | — |
case-16 | pass→pass | 15,930 | 10,004 | -37% | 1 | 1 | 0% | 2,598 | 2,063 | -21% | 0 | 0 | — |
case-17 | pass→pass | 6,682 | 5,441 | -19% | 1 | 1 | 0% | 1,298 | 1,235 | -5% | 0 | 0 | — |
case-18 | pass→pass | 10,793 | 9,019 | -16% | 1 | 1 | 0% | 1,881 | 1,945 | +3% | 0 | 0 | — |
case-19 | pass→fail | 12,164 | 9,179 | -25% | 1 | 1 | 0% | 2,453 | 1,975 | -19% | 0 | 0 | — |
case-20 | pass→pass | 10,601 | 10,998 | +4% | 1 | 1 | 0% | 2,311 | 2,399 | +4% | 0 | 0 | — |
case-21 | pass→pass | 11,815 | 12,186 | +3% | 1 | 1 | 0% | 2,393 | 2,805 | +17% | 0 | 0 | — |
case-22 | pass→pass | 7,809 | 6,812 | -13% | 1 | 1 | 0% | 1,271 | 1,295 | +2% | 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 21 counted toward the lift figure. The other 1 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 +5 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is 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.