Install any skill in seconds. Free to start, no credit card required.
Get Started Free →A tool for creating and managing Garry's Mod addons, including Lua scripting, content creation, and addon packaging. Use when: developing new addons, writing Lua scripts for GMod, organizing addon files, or when user mentions Garry's Mod, GMod, Lua scripting, or addon development.
.claude/skills/davila7-gmod-addon-maker/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 208% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 315% | 0% |
| case-04 | ✓→✓ | = Same ✓ | -1% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 69% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 17% | 0% |
You are a GMod addon development assistant, skilled in Lua scripting, content creation, and addon packaging for Garry's Mod.
Use this skill when:
When creating a GMod addon, follow these steps:
wiki.facepunch.com/gmod/hook). Most guessed URLs are 404 errors."gmod wiki <term>" first to extract the correct URL.https://wiki.facepunch.com/gmod and the search term is the API or concept you want to find. Do NOT guess URLs.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 3,641 | 8,055 | +121% | 1 | 1 | 0% | 629 | 1,936 | +208% | 0 | 0 | — |
case-02 | fail→pass | 1,683 | 4,203 | +150% | 1 | 1 | 0% | 296 | 1,228 | +315% | 0 | 0 | — |
case-03 | fail→fail | 2,883 | 6,313 | +119% | 1 | 1 | 0% | 392 | 1,667 | +325% | 0 | 0 | — |
case-04 | pass→pass | 13,295 | 14,678 | +10% | 1 | 1 | 0% | 2,628 | 2,593 | -1% | 0 | 0 | — |
case-05 | pass→pass | 3,741 | 3,998 | +7% | 1 | 1 | 0% | 667 | 1,125 | +69% | 0 | 0 | — |
case-06 | pass→pass | 5,594 | 3,492 | -38% | 1 | 1 | 0% | 909 | 1,060 | +17% | 0 | 0 | — |
case-07 | pass→pass | 7,408 | 7,053 | -5% | 1 | 1 | 0% | 1,430 | 1,755 | +23% | 0 | 0 | — |
case-08 | pass→pass | 9,702 | 8,684 | -10% | 1 | 1 | 0% | 1,697 | 2,100 | +24% | 0 | 0 | — |
case-09 | pass→pass | 12,329 | 10,936 | -11% | 1 | 1 | 0% | 2,055 | 2,428 | +18% | 0 | 0 | — |
case-10 | fail→fail | 9,062 | 5,868 | -35% | 1 | 1 | 0% | 1,538 | 1,477 | -4% | 0 | 0 | — |
case-11 | pass→pass | 11,987 | 9,395 | -22% | 1 | 1 | 0% | 2,086 | 2,245 | +8% | 0 | 0 | — |
case-12 | pass→pass | 10,485 | 6,913 | -34% | 1 | 1 | 0% | 1,887 | 1,910 | +1% | 0 | 0 | — |
case-13 | pass→pass | 2,462 | 2,727 | +11% | 1 | 1 | 0% | 477 | 972 | +104% | 0 | 0 | — |
case-14 | pass→pass | 8,325 | 4,927 | -41% | 1 | 1 | 0% | 1,480 | 1,404 | -5% | 0 | 0 | — |
case-15 | pass→pass | 8,659 | 5,669 | -35% | 1 | 1 | 0% | 1,714 | 1,647 | -4% | 0 | 0 | — |
case-16 | pass→pass | 3,212 | 2,125 | -34% | 1 | 1 | 0% | 565 | 858 | +52% | 0 | 0 | — |
case-17 | pass→pass | 3,777 | 2,686 | -29% | 1 | 1 | 0% | 698 | 925 | +33% | 0 | 0 | — |
case-18 | pass→pass | 7,926 | 7,193 | -9% | 1 | 1 | 0% | 1,619 | 1,926 | +19% | 0 | 0 | — |
case-19 | pass→pass | 7,747 | 5,338 | -31% | 1 | 1 | 0% | 1,368 | 1,440 | +5% | 0 | 0 | — |
case-20 | pass→pass | 12,750 | 12,472 | -2% | 1 | 1 | 0% | 2,862 | 2,619 | -8% | 0 | 0 | — |
case-21 | pass→pass | 11,915 | 9,693 | -19% | 1 | 1 | 0% | 2,445 | 2,468 | +1% | 0 | 0 | — |
case-22 | pass→pass | 7,923 | 7,931 | +0% | 1 | 1 | 0% | 1,686 | 2,347 | +39% | 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 +9 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.