Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Elixir development with engineer guidelines.
.claude/skills/amariahak-cursor-rules-for-elixir-development-with-engineer-guidelines/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✓→✗ | ▼ Worse | -35% | 0% |
| case-22 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
| case-23 | ✓→✓ | ＝ Same ✓ | 10% | 0% |
| case-24 | ✓→✓ | ＝ Same ✓ | 27% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | -37% | 0% |
Cursor rules for Elixir development with engineer guidelines.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/elixir-engineer-guidelines-cursorrules-prompt-file.mdc.
Act as an expert senior Elixir engineer.
Stack: Elixir, Phoenix, Docker, PostgreSQL, Tailwind CSS, LeftHook, Sobelow, Credo, Ecto, ExUnit, Plug, Phoenix LiveView, Phoenix LiveDashboard, Gettext, Jason, Swoosh, Finch, DNS Cluster, File System Watcher, Release Please, ExCoveralls
<type>optional scope]: <description>
optional body]
optional footer(s)]
Where:
type: One of the following:
scope (optional): A noun describing a section of the codebase (e.g., fluxcd, deployment).
description: A brief summary of the change in present tense.
body (optional): A more detailed explanation of the change.
footer (optional): One or more footers in the following format:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 24,371 | 13,298 | -45% | 1 | 1 | 0% | 2,415 | 2,662 | +10% | 0 | 0 | — |
case-23 | pass→pass | 15,830 | 17,050 | +8% | 1 | 1 | 0% | 2,765 | 3,039 | +10% | 0 | 0 | — |
case-24 | pass→pass | 11,637 | 14,314 | +23% | 1 | 1 | 0% | 2,100 | 2,662 | +27% | 0 | 0 | — |
case-01 | pass→pass | 12,971 | 6,802 | -48% | 1 | 1 | 0% | 2,264 | 1,427 | -37% | 0 | 0 | — |
case-02 | pass→pass | 13,534 | 4,582 | -66% | 1 | 1 | 0% | 2,241 | 1,029 | -54% | 0 | 0 | — |
case-03 | pass→pass | 10,352 | 5,923 | -43% | 1 | 1 | 0% | 1,734 | 1,197 | -31% | 0 | 0 | — |
case-04 | pass→pass | 12,990 | 8,658 | -33% | 1 | 1 | 0% | 2,211 | 1,703 | -23% | 0 | 0 | — |
case-05 | pass→pass | 11,169 | 6,724 | -40% | 1 | 1 | 0% | 1,826 | 1,389 | -24% | 0 | 0 | — |
case-06 | pass→pass | 11,001 | 5,272 | -52% | 1 | 1 | 0% | 1,786 | 1,225 | -31% | 0 | 0 | — |
case-07 | pass→fail | 9,822 | 6,279 | -36% | 1 | 1 | 0% | 1,945 | 1,269 | -35% | 0 | 0 | — |
case-08 | pass→pass | 10,143 | 5,092 | -50% | 1 | 1 | 0% | 1,737 | 1,214 | -30% | 0 | 0 | — |
case-09 | pass→pass | 13,259 | 6,608 | -50% | 1 | 1 | 0% | 2,210 | 1,394 | -37% | 0 | 0 | — |
case-10 | pass→pass | 3,575 | 2,618 | -27% | 1 | 1 | 0% | 618 | 603 | -2% | 0 | 0 | — |
case-11 | pass→pass | 2,117 | 2,008 | -5% | 1 | 1 | 0% | 344 | 565 | +64% | 0 | 0 | — |
case-12 | pass→pass | 5,167 | 2,747 | -47% | 1 | 1 | 0% | 849 | 700 | -18% | 0 | 0 | — |
case-13 | pass→pass | 12,286 | 9,210 | -25% | 1 | 1 | 0% | 1,940 | 1,740 | -10% | 0 | 0 | — |
case-14 | pass→pass | 13,057 | 7,070 | -46% | 1 | 1 | 0% | 1,815 | 1,349 | -26% | 0 | 0 | — |
case-15 | pass→pass | 7,457 | 4,998 | -33% | 1 | 1 | 0% | 1,233 | 1,061 | -14% | 0 | 0 | — |
case-16 | pass→pass | 3,563 | 2,350 | -34% | 1 | 1 | 0% | 588 | 615 | +5% | 0 | 0 | — |
case-17 | pass→pass | 3,482 | 2,681 | -23% | 1 | 1 | 0% | 610 | 677 | +11% | 0 | 0 | — |
case-18 | pass→pass | 7,105 | 5,547 | -22% | 1 | 1 | 0% | 1,216 | 1,097 | -10% | 0 | 0 | — |
case-19 | pass→pass | 9,929 | 4,924 | -50% | 1 | 1 | 0% | 1,831 | 1,135 | -38% | 0 | 0 | — |
case-20 | pass→pass | 8,556 | 2,415 | -72% | 1 | 1 | 0% | 1,586 | 632 | -60% | 0 | 0 | — |
case-21 | pass→pass | 9,089 | 3,624 | -60% | 1 | 1 | 0% | 1,663 | 857 | -48% | 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. 24 cases were attempted. The headline lift of -100 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Other measured skills in the registry, with their headline benchmark lift.