Individual skill
ComputerUse
Front door for driving this Mac: anything with a DOM, AX, CLI, or API handle routes to Interceptor; pixel-only GUI work goes to a vision agent, OpenAI Astra via codex exec or a tool-less Claude acting through Interceptor's bridge, picked per task class by a measured bake-off, under a deny list, step caps, and a read-back that decides pass/fail. USE WHEN computer use, drive the computer, control the mac, operate this app for me, do it in the GUI, pixel-only app, no API for this, canvas UI, computer-use bake-off, Claude vs OpenAI computer use. NOT FOR DOM/AX handles or web verification (Interceptor), scraping (a scraping skill, BrightData).
LifeOS/install/skills/ComputerUse/SKILL.md
Source commit b7efec97d8c3885feee285bee468c35602fb0606
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.
Repository context
- Repository stars (not skill ratings)
- 19,767
- Repository last updated
- Nov 5, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- augmentation Repository topic
- productivity Repository topic
- humans Repository topic
- ai-harness Repository topic
- intent-engineering Repository topic
- personal-ai Repository topic
- coding Repository topic
- lifeos Repository topic
- design Derived category
- design-interface Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
Config.example.mddoc · 1,021 bytesInstructions.mddoc · 1,065 bytesIntents/BakeOff.mddoc · 1,775 bytesIntents/Drive.mddoc · 2,295 bytesIntents/Probe.mddoc · 1,319 bytesReferences/VisionLegs.mddoc · 1,436 bytesSKILL.mdcore · 12,695 bytesSKILL.mdcore · 12,695 bytesSKILL.mdcore · 12,695 bytesSetup.mddoc · 4,332 bytesTools/BakeOff.tsruns · 10,903 bytesTools/ClaudeLeg.tsruns · 13,854 bytesTools/Probe.tsruns · 2,866 bytesTools/Route.tsruns · 3,981 bytesTools/Run.tsruns · 35,910 bytesTools/WindowBounds.tsruns · 4,248 bytes
Read excerpt
# ComputerUse
**Contents:** Ideal State · Intent Routing · The routing table · The supervised run · Data & Config · Gotchas · Examples
One skill routes every computer-use task by a rule you can read, then supervises the run so the vision leg never grades itself, never sees what it must not, and never runs away.
## Ideal State
- Every task is routed by the readable rule before anything runs: verification and anything with a DOM, AX, CLI or API handle go to Interceptor, and only pixel-only work goes to the measured vision pick.
- A vision run's verdict comes only from its declared verifier, never from the agent's own report, and no run starts without one.
- The vision leg never sees a running credential app, a visible communications app or a denied host, never acts outside its allowlisted app, and stops at its step and wall-clock caps.
- Send, buy, delete, publish or confirm happens only when the principal named that exact action, and every refusal is reported rather than worked around.
## Intent Routing