Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →macOS screen recorder that captures the main display PLUS system audio via ScreenCaptureKit — no BlackHole/loopback driver, no sudo, just the standard Screen Recording permission. CLI-driven; fills the headless-screen-recording-with-system-sound gap QuickTime and `screencapture -v` can't.
.claude/skills/sickn33-macos-screen-recorder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -71% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -47% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -59% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -52% | 0% |
Use when you need to script a screen recording WITH system sound on macOS from the CLI (demos, captures, voice-demo recording) — the case QuickTime and screencapture -v can't cover without a virtual audio device.
_Source: connerkward/macos-screen-recorder-system-audio (MIT)._
sck-record.swift → compiled sck-record (binary gitignored; built by setup-machine, or swiftc -O sck-record.swift -o sck-record). Records the main display + system audio via ScreenCaptureKit.
./sck-record <out.mp4> <seconds>The one true differentiator: system audio from the CLI with zero install — no BlackHole / loopback virtual device, no sudo; only the standard Screen Recording permission (granted once to whatever app shells out). It is not a general "better than OBS/Screen Studio" tool — it fills exactly the headless-CLI-with-system-audio gap.
sck-record is the raw capture primitive — it records, nothing more. To polish a recording afterward (idle speed-up, auto-zoom, keystroke chips, smoothed cursor, vertical export), pair it with screenstudio-alternative-skill: record with sck-record --no-cursor <out.mp4> <seconds>, then run its post-production pass on the resulting mp4. (Auto-zoom and keystroke overlays additionally need an input-event log captured during recording, which that skill supplies; sck-record's pixels alone cover idle speed-up, cursor smoothing, and vertical export.)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,740 | 3,132 | -86% | 1 | 1 | 0% | 3,879 | 1,113 | -71% | 0 | 0 | — |
case-02 | fail→pass | 12,859 | 4,211 | -67% | 1 | 1 | 0% | 2,295 | 1,227 | -47% | 0 | 0 | — |
case-03 | fail→pass | 12,873 | 2,561 | -80% | 1 | 1 | 0% | 2,229 | 921 | -59% | 0 | 0 | — |
case-04 | fail→pass | 6,365 | 1,909 | -70% | 1 | 1 | 0% | 1,166 | 829 | -29% | 0 | 0 | — |
case-05 | pass→pass | 9,646 | 3,798 | -61% | 1 | 1 | 0% | 1,736 | 1,175 | -32% | 0 | 0 | — |
case-06 | pass→pass | 7,336 | 3,112 | -58% | 1 | 1 | 0% | 1,211 | 979 | -19% | 0 | 0 | — |
case-07 | fail→pass | 11,528 | 2,858 | -75% | 1 | 1 | 0% | 2,246 | 1,076 | -52% | 0 | 0 | — |
case-08 | pass→pass | 11,360 | 3,507 | -69% | 1 | 1 | 0% | 2,071 | 1,101 | -47% | 0 | 0 | — |
case-09 | fail→pass | 19,433 | 8,180 | -58% | 1 | 1 | 0% | 2,965 | 1,953 | -34% | 0 | 0 | — |
case-10 | pass→pass | 12,215 | 4,489 | -63% | 1 | 1 | 0% | 1,999 | 1,139 | -43% | 0 | 0 | — |
case-11 | pass→pass | 10,404 | 8,376 | -19% | 1 | 1 | 0% | 1,963 | 1,999 | +2% | 0 | 0 | — |
case-12 | pass→pass | 23,059 | 20,982 | -9% | 1 | 1 | 0% | 3,867 | 4,009 | +4% | 0 | 0 | — |
case-13 | pass→pass | 7,553 | 5,928 | -22% | 1 | 1 | 0% | 1,256 | 1,569 | +25% | 0 | 0 | — |
case-14 | pass→pass | 9,780 | 6,332 | -35% | 1 | 1 | 0% | 1,802 | 1,513 | -16% | 0 | 0 | — |
case-15 | fail→pass | 13,801 | 2,258 | -84% | 1 | 1 | 0% | 884 | 879 | -1% | 0 | 0 | — |
case-16 | fail→pass | 7,809 | 3,083 | -61% | 1 | 1 | 0% | 1,489 | 989 | -34% | 0 | 0 | — |
case-17 | pass→pass | 13,220 | 11,578 | -12% | 1 | 1 | 0% | 2,046 | 2,309 | +13% | 0 | 0 | — |
case-22 | pass→pass | 9,049 | 3,387 | -63% | 1 | 1 | 0% | 1,510 | 1,001 | -34% | 0 | 0 | — |
case-18 | pass→pass | 10,112 | 2,446 | -76% | 1 | 1 | 0% | 1,790 | 920 | -49% | 0 | 0 | — |
case-19 | pass→pass | 11,246 | 8,894 | -21% | 1 | 1 | 0% | 2,128 | 2,131 | +0% | 0 | 0 | — |
case-20 | fail→pass | 17,323 | 4,523 | -74% | 1 | 1 | 0% | 2,748 | 1,285 | -53% | 0 | 0 | — |
case-21 | fail→pass | 12,114 | 2,747 | -77% | 1 | 1 | 0% | 1,873 | 990 | -47% | 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 +45 percentage points is the difference between those two pass rates over the 21 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.