Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Provides information about the bitwize-music plugin, its version, and its creator. Use when the user asks about the plugin, its purpose, version, or capabilities.
.claude/skills/bitwize-music-studio-about/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 206% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 214% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 129% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 43% | 0% |
Read the version from ${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json (the version field), then display:
Version: (version from plugin.json)
Who Am I
I'm bitwize—a hacker who loves music and experimenting with new technology. When AI music generation tools started getting good, I couldn't resist seeing what was possible.
Website: https://www.bitwizemusic.com/
Behind the Music: https://www.bitwizemusic.com/behind-the-music/
Discord: https://discord.gg/dMURByGF
Share What You Make: Tag @bitwizemusic on X/Twitter with anything interesting you create!
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,983 | 14,343 | +105% | 1 | 1 | 0% | 1,194 | 3,249 | +172% | 0 | 0 | — |
case-02 | fail→fail | 7,156 | 9,005 | +26% | 1 | 1 | 0% | 1,135 | 1,033 | -9% | 0 | 0 | — |
case-03 | fail→fail | 12,596 | 6,654 | -47% | 1 | 1 | 0% | 2,106 | 533 | -75% | 0 | 0 | — |
case-04 | pass→pass | 13,743 | 14,970 | +9% | 1 | 1 | 0% | 2,214 | 3,008 | +36% | 0 | 0 | — |
case-05 | pass→pass | 11,897 | 14,276 | +20% | 1 | 1 | 0% | 1,941 | 2,690 | +39% | 0 | 0 | — |
case-06 | pass→pass | 9,979 | 20,087 | +101% | 1 | 1 | 0% | 1,652 | 3,633 | +120% | 0 | 0 | — |
case-07 | fail→pass | 4,723 | 10,369 | +120% | 1 | 1 | 0% | 785 | 2,399 | +206% | 0 | 0 | — |
case-08 | fail→pass | 8,389 | 18,659 | +122% | 1 | 1 | 0% | 947 | 2,970 | +214% | 0 | 0 | — |
case-09 | fail→fail | 7,752 | 7,124 | -8% | 1 | 1 | 0% | 1,198 | 660 | -45% | 0 | 0 | — |
case-10 | fail→pass | 4,696 | 7,263 | +55% | 1 | 1 | 0% | 719 | 1,648 | +129% | 0 | 0 | — |
case-11 | fail→pass | 7,498 | 11,644 | +55% | 1 | 1 | 0% | 1,305 | 1,744 | +34% | 0 | 0 | — |
case-12 | fail→pass | 7,131 | 7,033 | -1% | 1 | 1 | 0% | 1,027 | 1,470 | +43% | 0 | 0 | — |
case-13 | fail→pass | 7,110 | 14,700 | +107% | 1 | 1 | 0% | 1,164 | 2,973 | +155% | 0 | 0 | — |
case-14 | fail→pass | 10,817 | 1,453 | -87% | 1 | 1 | 0% | 1,754 | 401 | -77% | 0 | 0 | — |
case-15 | fail→pass | 8,424 | 2,660 | -68% | 1 | 1 | 0% | 1,287 | 556 | -57% | 0 | 0 | — |
case-16 | fail→pass | 5,741 | 10,083 | +76% | 1 | 1 | 0% | 986 | 2,126 | +116% | 0 | 0 | — |
case-17 | fail→pass | 7,824 | 5,180 | -34% | 1 | 1 | 0% | 1,219 | 1,071 | -12% | 0 | 0 | — |
case-18 | fail→pass | 8,313 | 12,536 | +51% | 1 | 1 | 0% | 1,337 | 2,208 | +65% | 0 | 0 | — |
case-19 | fail→pass | 10,880 | 1,845 | -83% | 1 | 1 | 0% | 1,381 | 449 | -67% | 0 | 0 | — |
case-20 | fail→pass | 8,881 | 12,707 | +43% | 1 | 1 | 0% | 1,508 | 2,039 | +35% | 0 | 0 | — |
case-21 | fail→pass | 7,333 | 12,823 | +75% | 1 | 1 | 0% | 1,262 | 1,892 | +50% | 0 | 0 | — |
case-22 | fail→pass | 9,038 | 10,717 | +19% | 1 | 1 | 0% | 1,353 | 2,140 | +58% | 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 19 counted toward the lift figure. The other 3 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 +68 percentage points is the difference between those two pass rates over the 19 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.