Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.
.claude/skills/nanocoai-add-macos-statusbar/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -18% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -23% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -15% | 0% |
Adds a persistent menu bar icon that shows NanoClaw's running status and lets the user start, stop, or restart the service — similar to how Docker Desktop appears in the menu bar.
macOS only. Requires Xcode Command Line Tools (swiftc).
If not on macOS, stop and tell the user:
> This skill is macOS only. The menu bar status indicator uses AppKit and requires swiftc (Xcode Command Line Tools).
bashwhich swiftc
If not found, tell the user:
> Xcode Command Line Tools are required. Install them by running: > > bash > xcode-select --install > > > Then re-run /add-macos-statusbar.
bashlaunchctl list | grep com.nanoclaw.statusbar
If it returns a PID (not -), tell the user it's already installed and skip to Phase 3 (Verify).
The source lives in the skill directory. Compile it into dist/:
bashmkdir -p dist swiftc -O -o dist/statusbar "${CLAUDE_SKILL_DIR}/add/src/statusbar.swift"
This produces a small native binary at dist/statusbar.
On macOS Sequoia or later, clear the quarantine attribute so the binary can run:
bashxattr -cr dist/statusbar
Determine the absolute project root and home directory:
bashpwd echo $HOME
Create ~/Library/LaunchAgents/com.nanoclaw.statusbar.plist, substituting the actual values for {PROJECT_ROOT} and {HOME}:
xml<?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> <plist version="1.0"> <dict> <key>Label</key> <string>com.nanoclaw.statusbar</string> <key>ProgramArguments</key> <array> <string>{PROJECT_ROOT}/dist/statusbar</string> </array> <key>RunAtLoad</key> <true/> <key>KeepAlive</key> <true/> <key>EnvironmentVariables</key> <dict> <key>HOME</key> <string>{HOME}</string> </dict> <key>StandardOutPath</key> <string>{PROJECT_ROOT}/logs/statusbar.log</string> <key>StandardErrorPath</key> <string>{PROJECT_ROOT}/logs/statusbar.error.log</string> </dict> </plist>
bashlaunchctl load ~/Library/LaunchAgents/com.nanoclaw.statusbar.plist
bashlaunchctl list | grep com.nanoclaw.statusbar
The first column should show a PID (not -).
Tell the user:
> The bolt icon should now appear in your macOS menu bar. Click it to see NanoClaw's status and control the service. > > - Green dot — NanoClaw is running > - Red dot — NanoClaw is stopped > > Use Restart after making code changes, and View Logs to open the log file directly.
To uninstall, follow REMOVE.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 14,295 | 2,291 | -84% | 1 | 1 | 0% | 3,438 | 1,045 | -70% | 0 | 0 | — |
case-02 | fail→fail | 10,267 | 2,642 | -74% | 1 | 1 | 0% | 2,154 | 1,159 | -46% | 0 | 0 | — |
case-03 | fail→fail | 18,903 | 4,391 | -77% | 1 | 1 | 0% | 3,864 | 1,015 | -74% | 0 | 0 | — |
case-04 | fail→pass | 7,229 | 1,393 | -81% | 1 | 1 | 0% | 1,231 | 1,010 | -18% | 0 | 0 | — |
case-05 | pass→fail | 9,243 | 2,839 | -69% | 1 | 1 | 0% | 1,498 | 1,144 | -24% | 0 | 0 | — |
case-06 | pass→pass | 11,282 | 3,308 | -71% | 1 | 1 | 0% | 1,648 | 1,392 | -16% | 0 | 0 | — |
case-21 | pass→pass | 12,982 | 6,072 | -53% | 1 | 1 | 0% | 2,428 | 2,030 | -16% | 0 | 0 | — |
case-07 | fail→pass | 10,445 | 2,047 | -80% | 1 | 1 | 0% | 848 | 1,178 | +39% | 0 | 0 | — |
case-08 | pass→pass | 70,184 | 2,405 | -97% | 1 | 1 | 0% | 1,881 | 1,354 | -28% | 0 | 0 | — |
case-09 | pass→fail | 10,892 | 53,915 | +395% | 1 | 1 | 0% | 2,062 | 1,351 | -34% | 0 | 0 | — |
case-10 | pass→pass | 3,591 | 2,271 | -37% | 1 | 1 | 0% | 497 | 1,225 | +146% | 0 | 0 | — |
case-11 | fail→pass | 7,547 | 1,945 | -74% | 1 | 1 | 0% | 1,499 | 1,156 | -23% | 0 | 0 | — |
case-12 | fail→fail | 5,875 | 1,604 | -73% | 1 | 1 | 0% | 1,015 | 1,087 | +7% | 0 | 0 | — |
case-13 | pass→pass | 3,140 | 2,282 | -27% | 1 | 1 | 0% | 614 | 1,221 | +99% | 0 | 0 | — |
case-14 | pass→pass | 3,675 | 1,712 | -53% | 1 | 1 | 0% | 707 | 1,095 | +55% | 0 | 0 | — |
case-15 | fail→pass | 7,522 | 1,684 | -78% | 1 | 1 | 0% | 1,371 | 1,102 | -20% | 0 | 0 | — |
case-16 | fail→pass | 6,659 | 1,286 | -81% | 1 | 1 | 0% | 1,256 | 1,070 | -15% | 0 | 0 | — |
case-17 | fail→pass | 8,183 | 1,524 | -81% | 1 | 1 | 0% | 1,224 | 1,052 | -14% | 0 | 0 | — |
case-18 | fail→pass | 15,572 | 1,931 | -88% | 1 | 1 | 0% | 1,600 | 1,050 | -34% | 0 | 0 | — |
case-19 | pass→pass | 6,435 | 1,357 | -79% | 1 | 1 | 0% | 820 | 1,004 | +22% | 0 | 0 | — |
case-20 | pass→pass | 5,153 | 1,547 | -70% | 1 | 1 | 0% | 844 | 1,012 | +20% | 0 | 0 | — |
case-22 | pass→pass | 10,732 | 8,565 | -20% | 1 | 1 | 0% | 2,177 | 2,445 | +12% | 0 | 0 | — |
case-23 | pass→pass | 8,334 | 4,944 | -41% | 1 | 1 | 0% | 1,347 | 1,685 | +25% | 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 20 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 +22 percentage points is the difference between those two pass rates over the 20 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
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.