Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.
.claude/skills/bilal140202-peon-ping-toggle/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -62% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -38% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -49% | 0% |
Toggle peon-ping sounds on or off. Also handles any peon-ping configuration changes.
On Unix, run the following command using the Bash tool:
bashbash "${CLAUDE_CONFIG_DIR:-$HOME/.claude}"/hooks/peon-ping/peon.sh toggle
On Windows, use the PowerShell tool:
powershell$claudeDir = $env:CLAUDE_CONFIG_DIR if (-not $claudeDir -or $claudeDir -eq "") { $claudeDir = Join-Path $HOME ".claude" } & (Join-Path $claudeDir "hooks/peon-ping/peon.ps1") toggle
Report the output to the user. The command will print either:
peon-ping: sounds paused — sounds are now mutedpeon-ping: sounds resumed — sounds are now activeThis command toggles the master audio switch (enabled config). When disabled:
For notification-only control, use /peon-ping-config to set desktop_notifications: false. This keeps sounds playing while suppressing desktop popups.
"Mute peon-ping completely" → Sets enabled: false "Just disable the popups but keep sounds" → Sets desktop_notifications: false (use /peon-ping-config instead)
For any other peon-ping setting changes (volume, pack rotation, categories, active pack, etc.), use the peon-ping-config skill.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→fail | 5,614 | 4,189 | -25% | 1 | 1 | 0% | 419 | 593 | +42% | 0 | 0 | — |
case-01 | fail→fail | 6,707 | 4,290 | -36% | 1 | 1 | 0% | 1,207 | 694 | -43% | 0 | 0 | — |
case-02 | fail→fail | 3,227 | 4,241 | +31% | 1 | 1 | 0% | 509 | 629 | +24% | 0 | 0 | — |
case-04 | fail→pass | 9,590 | 2,225 | -77% | 1 | 1 | 0% | 1,764 | 808 | -54% | 0 | 0 | — |
case-05 | fail→pass | 12,690 | 2,766 | -78% | 1 | 1 | 0% | 2,585 | 980 | -62% | 0 | 0 | — |
case-06 | fail→pass | 9,664 | 2,783 | -71% | 1 | 1 | 0% | 1,877 | 951 | -49% | 0 | 0 | — |
case-07 | fail→fail | 8,466 | 5,063 | -40% | 1 | 1 | 0% | 1,717 | 590 | -66% | 0 | 0 | — |
case-08 | fail→pass | 7,855 | 2,744 | -65% | 1 | 1 | 0% | 1,622 | 1,004 | -38% | 0 | 0 | — |
case-09 | fail→pass | 9,875 | 2,574 | -74% | 1 | 1 | 0% | 1,616 | 826 | -49% | 0 | 0 | — |
case-10 | fail→fail | 5,394 | 7,144 | +32% | 1 | 1 | 0% | 1,000 | 889 | -11% | 0 | 0 | — |
case-11 | fail→pass | 8,063 | 9,967 | +24% | 1 | 1 | 0% | 1,353 | 1,651 | +22% | 0 | 0 | — |
case-12 | fail→fail | 5,271 | 9,014 | +71% | 1 | 1 | 0% | 957 | 1,014 | +6% | 0 | 0 | — |
case-13 | fail→fail | 7,851 | 8,569 | +9% | 1 | 1 | 0% | 1,395 | 896 | -36% | 0 | 0 | — |
case-14 | fail→pass | 7,506 | 2,468 | -67% | 1 | 1 | 0% | 1,115 | 816 | -27% | 0 | 0 | — |
case-15 | pass→pass | 2,068 | 2,597 | +26% | 1 | 1 | 0% | 344 | 767 | +123% | 0 | 0 | — |
case-16 | pass→pass | 9,192 | 2,990 | -67% | 1 | 1 | 0% | 1,645 | 867 | -47% | 0 | 0 | — |
case-17 | fail→fail | 10,935 | 1,738 | -84% | 1 | 1 | 0% | 2,059 | 727 | -65% | 0 | 0 | — |
case-18 | fail→fail | 7,673 | 2,830 | -63% | 1 | 1 | 0% | 1,474 | 859 | -42% | 0 | 0 | — |
case-19 | fail→fail | 3,726 | 3,604 | -3% | 1 | 1 | 0% | 595 | 566 | -5% | 0 | 0 | — |
case-20 | fail→pass | 8,296 | 2,029 | -76% | 1 | 1 | 0% | 1,293 | 764 | -41% | 0 | 0 | — |
case-21 | fail→fail | 8,908 | 4,697 | -47% | 1 | 1 | 0% | 1,477 | 1,169 | -21% | 0 | 0 | — |
case-22 | pass→pass | 10,929 | 2,115 | -81% | 1 | 1 | 0% | 1,733 | 661 | -62% | 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 16 counted toward the lift figure. The other 6 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 +36 percentage points is the difference between those two pass rates over the 16 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.