Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.
.claude/skills/github-squad-commands/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 83% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 158% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 191% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 118% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 188% | 0% |
When the user triggers this skill ("squad commands", "help", "what can squad do", etc.):
ask_user choice list: 📋 Squad Commands — pick a category:
ask_user list.ask_user is unavailable, render as a markdown table instead.Argument collection: For entries with args, iterate the list sequentially. Use ask_user with choices when choices is provided; free-text prompt otherwise. If the user says "just do it" or "defaults are fine," skip remaining args and use their defaults.
Confirmation template:
⚠️ This will {action-description}.
{what will change}
Proceed? (yes / no)state-backend: Which state backend? | choices: {worktree, git-notes, orphan, two-layer} | default: (keep current)stateBackend: Which state backend? | choices: {worktree, git-notes, orphan, two-layer} | default: (keep current)role: What role should this agent fill? (e.g., Frontend Dev, Backend Dev, QA Engineer)name: Preferred name or casting universe? | default: (auto-cast from active universe)member: Which team member to remove? (name or role)member: Which team member?newRole: New role?gh auth login to have been run in the terminal.interval: How often should Ralph poll? (in minutes) | default: 10interval: Poll interval in minutes | default: 10squad watch --interval {n} in your terminal.name: Plugin name to search for | default: (browse all)plugin: Plugin owner/repo (e.g., owner/plugin-name)name: Plugin name to removemodel: Model name (e.g., gpt-4o, claude-sonnet-4.5, o3)agent: Agent name (must match name in team.md)model: Model name (e.g., gpt-4o, claude-sonnet-4.5)scope: Clear default or a specific agent? | choices: {default model, specific agent} | default: default modelagent: Agent name (only if scope = specific agent)olderThan: Archive decisions older than how many days? | default: 30member: Which team member's history to summarize?| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 12,363 | 8,286 | -33% | 1 | 1 | 0% | 1,810 | 3,007 | +66% | 0 | 0 | — |
case-02 | fail→fail | 3,922 | 19,938 | +408% | 1 | 1 | 0% | 524 | 3,507 | +569% | 0 | 0 | — |
case-03 | fail→fail | 6,017 | 7,059 | +17% | 1 | 1 | 0% | 780 | 3,686 | +373% | 0 | 0 | — |
case-04 | fail→pass | 14,799 | 6,967 | -53% | 1 | 1 | 0% | 2,155 | 3,947 | +83% | 0 | 0 | — |
case-05 | fail→pass | 8,266 | 3,884 | -53% | 1 | 1 | 0% | 1,219 | 3,145 | +158% | 0 | 0 | — |
case-06 | fail→pass | 8,237 | 4,096 | -50% | 1 | 1 | 0% | 1,117 | 3,245 | +191% | 0 | 0 | — |
case-07 | pass→pass | 9,106 | 4,510 | -50% | 1 | 1 | 0% | 1,277 | 3,314 | +160% | 0 | 0 | — |
case-08 | pass→pass | 22,310 | 3,719 | -83% | 1 | 1 | 0% | 1,042 | 3,124 | +200% | 0 | 0 | — |
case-09 | fail→fail | 9,210 | 3,316 | -64% | 1 | 1 | 0% | 1,409 | 3,059 | +117% | 0 | 0 | — |
case-10 | pass→pass | 6,755 | 2,494 | -63% | 1 | 1 | 0% | 992 | 2,887 | +191% | 0 | 0 | — |
case-11 | fail→pass | 10,694 | 3,390 | -68% | 1 | 1 | 0% | 1,342 | 2,929 | +118% | 0 | 0 | — |
case-12 | pass→pass | 13,643 | 5,049 | -63% | 1 | 1 | 0% | 2,007 | 3,263 | +63% | 0 | 0 | — |
case-13 | fail→fail | 11,493 | 2,967 | -74% | 1 | 1 | 0% | 1,841 | 2,953 | +60% | 0 | 0 | — |
case-14 | fail→pass | 7,883 | 3,832 | -51% | 1 | 1 | 0% | 1,080 | 3,111 | +188% | 0 | 0 | — |
case-15 | pass→fail | 19,210 | 3,005 | -84% | 1 | 1 | 0% | 1,012 | 3,009 | +197% | 0 | 0 | — |
case-16 | fail→fail | 10,130 | 6,534 | -35% | 1 | 1 | 0% | 1,325 | 3,676 | +177% | 0 | 0 | — |
case-17 | pass→fail | 5,829 | 5,024 | -14% | 1 | 1 | 0% | 855 | 3,153 | +269% | 0 | 0 | — |
case-18 | fail→pass | 8,081 | 3,959 | -51% | 1 | 1 | 0% | 1,167 | 3,250 | +178% | 0 | 0 | — |
case-19 | pass→pass | 11,884 | 3,380 | -72% | 1 | 1 | 0% | 1,393 | 2,926 | +110% | 0 | 0 | — |
case-20 | pass→pass | 9,374 | 2,546 | -73% | 1 | 1 | 0% | 1,165 | 2,922 | +151% | 0 | 0 | — |
case-21 | pass→pass | 4,182 | 4,675 | +12% | 1 | 1 | 0% | 450 | 3,292 | +632% | 0 | 0 | — |
case-22 | pass→pass | 9,629 | 19,297 | +100% | 1 | 1 | 0% | 1,721 | 3,791 | +120% | 0 | 0 | — |
case-23 | pass→pass | 5,535 | 6,050 | +9% | 1 | 1 | 0% | 854 | 3,421 | +301% | 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 21 counted toward the lift figure. The other 2 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 +17 percentage points is the difference between those two pass rates over the 21 comparable cases. 4 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.