Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Cursor rules for Elixir development with Phoenix and Docker integration.
.claude/skills/amariahak-cursor-rules-for-elixir-development-with-phoenix-and-docker-integration/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 37% | 0% |
Cursor rules for Elixir development with Phoenix and Docker integration.
Synced from https://github.com/PatrickJS/awesome-cursorrules/tree/main/rules/elixir-phoenix-docker-setup-cursorrules-prompt-fil.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
optional scope]: optional body]optional footer(s)]
Where:
build: Changes that affect the build system or external dependencies (e.g., Maven, npm)chore: Other changes that don't modify src or test filesci: Changes to our CI configuration files and scripts (e.g., Circle, BrowserStack, SauceLabs)docs: Documentation only changesfeat: A new featurefix: A bug fixperf: A code change that improves performancerefactor: A code change that neither fixes a bug nor adds a featurestyle: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc)test: Adding missing tests or correcting existing testsfluxcd, deployment).BREAKING CHANGE: (for breaking changes)<issue_tracker_id>: (e.g., Jira-123: Fixed bug in authentication)| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-22 | pass→pass | 14,419 | 13,121 | -9% | 1 | 1 | 0% | 2,613 | 2,514 | -4% | 0 | 0 | — |
case-02 | fail→fail | 13,199 | 5,745 | -56% | 1 | 1 | 0% | 2,550 | 1,565 | -39% | 0 | 0 | — |
case-01 | fail→pass | 15,427 | 10,991 | -29% | 1 | 1 | 0% | 3,017 | 2,728 | -10% | 0 | 0 | — |
case-03 | fail→pass | 11,024 | 11,098 | +1% | 1 | 1 | 0% | 2,190 | 2,553 | +17% | 0 | 0 | — |
case-04 | fail→fail | 9,862 | 4,807 | -51% | 1 | 1 | 0% | 1,852 | 1,461 | -21% | 0 | 0 | — |
case-05 | fail→pass | 6,826 | 4,635 | -32% | 1 | 1 | 0% | 1,085 | 1,333 | +23% | 0 | 0 | — |
case-06 | fail→pass | 5,336 | 4,192 | -21% | 1 | 1 | 0% | 859 | 1,127 | +31% | 0 | 0 | — |
case-07 | fail→pass | 6,801 | 6,062 | -11% | 1 | 1 | 0% | 1,129 | 1,550 | +37% | 0 | 0 | — |
case-08 | fail→pass | 19,479 | 18,969 | -3% | 1 | 1 | 0% | 3,803 | 3,264 | -14% | 0 | 0 | — |
case-09 | fail→pass | 6,766 | 3,679 | -46% | 1 | 1 | 0% | 1,221 | 1,022 | -16% | 0 | 0 | — |
case-10 | fail→fail | 5,830 | 4,972 | -15% | 1 | 1 | 0% | 875 | 1,482 | +69% | 0 | 0 | — |
case-11 | fail→pass | 5,047 | 5,896 | +17% | 1 | 1 | 0% | 846 | 1,489 | +76% | 0 | 0 | — |
case-16 | fail→pass | 16,464 | 12,031 | -27% | 1 | 1 | 0% | 3,267 | 2,950 | -10% | 0 | 0 | — |
case-12 | fail→pass | 7,335 | 4,761 | -35% | 1 | 1 | 0% | 1,220 | 1,476 | +21% | 0 | 0 | — |
case-13 | fail→pass | 6,466 | 6,867 | +6% | 1 | 1 | 0% | 1,033 | 1,282 | +24% | 0 | 0 | — |
case-14 | fail→pass | 6,068 | 5,702 | -6% | 1 | 1 | 0% | 1,008 | 1,274 | +26% | 0 | 0 | — |
case-15 | fail→pass | 10,527 | 3,866 | -63% | 1 | 1 | 0% | 1,676 | 1,273 | -24% | 0 | 0 | — |
case-17 | fail→pass | 4,701 | 3,882 | -17% | 1 | 1 | 0% | 842 | 1,206 | +43% | 0 | 0 | — |
case-18 | fail→pass | 6,017 | 3,071 | -49% | 1 | 1 | 0% | 526 | 1,084 | +106% | 0 | 0 | — |
case-19 | fail→pass | 18,922 | 12,934 | -32% | 1 | 1 | 0% | 3,242 | 2,905 | -10% | 0 | 0 | — |
case-20 | pass→pass | 14,323 | 20,318 | +42% | 1 | 1 | 0% | 3,060 | 2,958 | -3% | 0 | 0 | — |
case-21 | pass→pass | 8,691 | 8,959 | +3% | 1 | 1 | 0% | 1,634 | 2,344 | +43% | 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. The headline lift of +73 percentage points is the difference between those two pass rates over the 22 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.