Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Rename the current Claude session for peon-ping notifications and terminal tab title. Use when user wants to give this session a custom name like "/peon-ping-rename Auth Refactor". Call with no argument to reset to auto-detect.
.claude/skills/bilal140202-peon-ping-rename/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -46% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 62% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -38% | 0% |
Give the current session a custom name shown in desktop notification titles and the terminal tab title.
When the user types /peon-ping-rename <name>, a UserPromptSubmit hook intercepts the command before it reaches the model:
session_names[session_id] = name to .state.jsonOn every subsequent hook event, peon.sh reads session_names[session_id] as the highest-priority project name. Multiple tabs in the same repo each get independent names.
/peon-ping-rename Auth Refactor
/peon-ping-rename API: payments
/peon-ping-rename ← reset to auto-detectNames are capped at 50 characters. Allowed: letters, numbers, spaces, dots, hyphens, underscores.
bashecho "$CLAUDE_SESSION_ID"
bashpython3 -c " import json, os, time state_path = os.path.expanduser('~/.claude/hooks/peon-ping/.state.json') try: state = json.load(open(state_path)) except: state = {} state.setdefault('session_names', {})['SESSION_ID_HERE'] = 'My Session Name' json.dump(state, open(state_path, 'w'), indent=2) "
Submit any prompt — peon.sh will pick up the new name on the next UserPromptSubmit or Stop event.
/peon-ping-renameOr remove the session ID from session_names in .state.json directly.
/peon-ping-rename > CLAUDE_SESSION_NAME env var > .peon-label file > notification_title_script > project_name_map > notification_title_override > git repo name > folder name
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 12,364 | 3,868 | -69% | 1 | 1 | 0% | 2,355 | 1,275 | -46% | 0 | 0 | — |
case-02 | fail→pass | 8,667 | 2,166 | -75% | 1 | 1 | 0% | 1,671 | 960 | -43% | 0 | 0 | — |
case-03 | fail→pass | 7,251 | 6,657 | -8% | 1 | 1 | 0% | 1,376 | 2,229 | +62% | 0 | 0 | — |
case-04 | fail→pass | 6,960 | 3,641 | -48% | 1 | 1 | 0% | 1,310 | 1,395 | +6% | 0 | 0 | — |
case-05 | fail→pass | 10,936 | 3,426 | -69% | 1 | 1 | 0% | 2,065 | 1,273 | -38% | 0 | 0 | — |
case-06 | pass→pass | 3,918 | 2,985 | -24% | 1 | 1 | 0% | 716 | 991 | +38% | 0 | 0 | — |
case-07 | pass→pass | 3,976 | 2,655 | -33% | 1 | 1 | 0% | 703 | 1,061 | +51% | 0 | 0 | — |
case-08 | fail→pass | 6,026 | 3,502 | -42% | 1 | 1 | 0% | 1,138 | 1,200 | +5% | 0 | 0 | — |
case-09 | fail→pass | 6,587 | 3,428 | -48% | 1 | 1 | 0% | 1,017 | 1,164 | +14% | 0 | 0 | — |
case-10 | pass→pass | 7,453 | 1,775 | -76% | 1 | 1 | 0% | 1,238 | 803 | -35% | 0 | 0 | — |
case-11 | fail→pass | 10,465 | 7,036 | -33% | 1 | 1 | 0% | 2,173 | 1,822 | -16% | 0 | 0 | — |
case-12 | fail→pass | 11,002 | 988 | -91% | 1 | 1 | 0% | 2,028 | 706 | -65% | 0 | 0 | — |
case-13 | pass→pass | 15,576 | 19,695 | +26% | 1 | 1 | 0% | 3,011 | 4,193 | +39% | 0 | 0 | — |
case-14 | pass→pass | 11,085 | 10,580 | -5% | 1 | 1 | 0% | 2,129 | 2,831 | +33% | 0 | 0 | — |
case-15 | pass→pass | 8,580 | 9,970 | +16% | 1 | 1 | 0% | 2,077 | 2,410 | +16% | 0 | 0 | — |
case-16 | pass→pass | 10,594 | 5,247 | -50% | 1 | 1 | 0% | 1,927 | 1,533 | -20% | 0 | 0 | — |
case-17 | fail→fail | 8,843 | 1,178 | -87% | 1 | 1 | 0% | 1,735 | 731 | -58% | 0 | 0 | — |
case-18 | fail→pass | 5,668 | 2,433 | -57% | 1 | 1 | 0% | 1,047 | 1,004 | -4% | 0 | 0 | — |
case-19 | pass→pass | 4,218 | 2,129 | -50% | 1 | 1 | 0% | 944 | 947 | +0% | 0 | 0 | — |
case-20 | pass→pass | 9,126 | 2,159 | -76% | 1 | 1 | 0% | 1,657 | 886 | -47% | 0 | 0 | — |
case-21 | pass→pass | 4,470 | 1,173 | -74% | 1 | 1 | 0% | 776 | 692 | -11% | 0 | 0 | — |
case-22 | pass→pass | 11,966 | 3,732 | -69% | 1 | 1 | 0% | 2,103 | 1,256 | -40% | 0 | 0 | — |
case-23 | pass→pass | 4,850 | 2,349 | -52% | 1 | 1 | 0% | 823 | 977 | +19% | 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. The headline lift of +43 percentage points is the difference between those two pass rates over the 23 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.