Adonis0123/adonis-skills / skills/desktop-agent-activity
desktop-agent-activity
VerifiedUse when 查 Orca/Claude Code 是否还在干活. Process+files first.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.0 KB |
| references/display-asleep-lock-tui.md | markdown | 1.5 KB |
| references/orca-claude-liveness.md | markdown | 3.1 KB |
references/display-asleep-lock-tui.md
View on GitHub# Display asleep / lock screen → Orca TUI log
When the user asks to **look at** Orca / Claude Code (Kimi CU or `computer_use`) and also says **允许抢焦点 / 我没在操作 / 你要智能一点**.
This does **not** replace process+CPU+mtime (`SKILL.md` §1–4). It is the look-at-screen path.
## Order
1. `system_profiler SPDisplaysDataType` — if `Display Asleep: Yes`, window capture will fail (`could not create image`). One `caffeinate -u -t 4` if focus is allowed; then **one** full-display shot.
2. Full display is lock screen (date + large clock + Touch ID / Enter Password) → **stop**. Do not click, type, or unlock. Mention that the display was woken. Finish from TUI log.
3. Unlocked → at most **one** Orca window capture. Electron ScreenCaptureKit may still fail (`px_capture_unavailable`). Fail once → log; do **not** click window-center / re-raise / swap Kimi `mode=image`.
4. Do not pass cua-driver `window_id` to Kimi. Kimi `app` = bundle id (`com.stablyai.orca`); `mode` only `full|image|ax`.
## TUI log
Newest dir under `~/Library/Application Support/orca/terminal-history/` whose name contains the repo. Read `output.log` (it keeps growing). `checkpoint.json` `lastTitle` can lag.
| Tail | Verdict |
|------|---------|
| `Gallivanting…` / hooks, duration climbing | still working |
| `Baked for …` + `❯` | **done, waiting for you** |
| permission / question prompt | stuck on input |
If the next user message is `锁屏`, use the dedicated `lock_screen` path — not `computer_use`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |