Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions. Use for desktop app interaction: list apps/windows, get app state, read visible UI, click controls, type, press keys, scroll, drag, set values, or perform accessibility actions. Also use for browser windows, webviews, Orca app UI, or other desktop UI. Triggers include "computer use", "orca computer", "read Spotify", "read Slack", "control/click/read in a des
.claude/skills/stablyai-computer-use/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -71% | 0% |
This discovery stub loads the version-matched guide from the Orca executable used for this session.
Choose the executable once and reuse it for every later command:
ORCA_CLI_COMMAND environment variable is set, use its value. Orca exports thisfor managed WSL sessions.
ORCA_DEV_REPO_ROOT, use orca-dev.orca-ide. Never run bareorca there — outside Orca's terminals it normally resolves to the GNOME Orca screen reader (/usr/bin/orca) and starts speech on the user's machine.
orca.Below, ORCA is a placeholder for the executable you resolved. Substitute it before running anything; do not create a shell variable or run ORCA literally. This works the same way in POSIX shells, PowerShell, and cmd.exe.
If the selected executable cannot run, report its exact error and stop. Do not fall through to another executable, which could silently target a different Orca build.
textORCA skills get computer-use
Prefer --json. Use the selected executable's --help for commands or flags the guide does not cover. If a command reports that Orca is not running, start it with ORCA open --json and retry. If skills get is unknown, explain that updating Orca restores the guide; use --help for read-only discovery and do not guess unsupported commands.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | pass→pass | 27,209 | 17,723 | -35% | 1 | 1 | 0% | 1,828 | 2,557 | +40% | 0 | 0 | — |
case-01 | fail→fail | 23,647 | 17,649 | -25% | 1 | 1 | 0% | 2,010 | 796 | -60% | 0 | 0 | — |
case-02 | fail→fail | 15,863 | 17,067 | +8% | 1 | 1 | 0% | 352 | 711 | +102% | 0 | 0 | — |
case-03 | fail→fail | 14,959 | 20,742 | +39% | 1 | 1 | 0% | 214 | 949 | +343% | 0 | 0 | — |
case-04 | fail→pass | 17,337 | 9,183 | -47% | 1 | 1 | 0% | 2,124 | 1,188 | -44% | 0 | 0 | — |
case-05 | fail→pass | 16,868 | 7,619 | -55% | 1 | 1 | 0% | 2,108 | 842 | -60% | 0 | 0 | — |
case-06 | fail→pass | 14,857 | 8,027 | -46% | 1 | 1 | 0% | 1,591 | 906 | -43% | 0 | 0 | — |
case-07 | pass→pass | 14,183 | 7,226 | -49% | 1 | 1 | 0% | 1,384 | 675 | -51% | 0 | 0 | — |
case-08 | fail→fail | 15,659 | 20,772 | +33% | 1 | 1 | 0% | 1,734 | 1,028 | -41% | 0 | 0 | — |
case-09 | fail→pass | 16,140 | 8,051 | -50% | 1 | 1 | 0% | 1,695 | 808 | -52% | 0 | 0 | — |
case-10 | fail→pass | 46,871 | 8,088 | -83% | 1 | 1 | 0% | 2,923 | 848 | -71% | 0 | 0 | — |
case-11 | fail→pass | 8,546 | 6,979 | -18% | 1 | 1 | 0% | 507 | 648 | +28% | 0 | 0 | — |
case-12 | fail→pass | 14,804 | 7,354 | -50% | 1 | 1 | 0% | 1,638 | 766 | -53% | 0 | 0 | — |
case-13 | pass→pass | 10,510 | 7,529 | -28% | 1 | 1 | 0% | 860 | 787 | -8% | 0 | 0 | — |
case-14 | pass→pass | 10,876 | 7,261 | -33% | 1 | 1 | 0% | 876 | 788 | -10% | 0 | 0 | — |
case-15 | pass→pass | 15,141 | 7,904 | -48% | 1 | 1 | 0% | 1,370 | 863 | -37% | 0 | 0 | — |
case-16 | pass→pass | 11,124 | 6,476 | -42% | 1 | 1 | 0% | 799 | 587 | -27% | 0 | 0 | — |
case-17 | pass→pass | 14,219 | 7,024 | -51% | 1 | 1 | 0% | 1,354 | 711 | -47% | 0 | 0 | — |
case-18 | pass→pass | 19,169 | 11,281 | -41% | 1 | 1 | 0% | 1,992 | 1,233 | -38% | 0 | 0 | — |
case-19 | fail→pass | 13,234 | 7,566 | -43% | 1 | 1 | 0% | 1,312 | 767 | -42% | 0 | 0 | — |
case-20 | fail→pass | 24,221 | 8,278 | -66% | 1 | 1 | 0% | 2,576 | 870 | -66% | 0 | 0 | — |
case-22 | pass→pass | 13,231 | 11,392 | -14% | 1 | 1 | 0% | 1,321 | 1,372 | +4% | 0 | 0 | — |
case-23 | pass→pass | 19,415 | 27,351 | +41% | 1 | 1 | 0% | 2,611 | 2,249 | -14% | 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. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 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 +39 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 9/1/2026 | +33% |
| gemini-3.6-flash | verified | 8/7/2026 | +50% |
Other measured skills in the registry, with their headline benchmark lift.