Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer. Triggers on team-review.
.claude/skills/catlog22-team-review/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -13% | 0% |
> Agent timeout: spawn_agent 异步执行且无内置超时 — 除明确短任务外一律 spawn_agent 后立即 wait_agent({ timeout_ms: 3600000 })(上限 1 小时)阻塞等待,绝不依赖 30000 默认值;timed_out: true 且 Agent 未完成时再次 wait_agent 续等,不丢弃。批量场景使用 spawn_agents_on_csv({ max_runtime_seconds: 3600, ... })。
<required_reading> @~/.maestro/workflows/run-mode-lite.md </required_reading>
Orchestrate multi-agent code review: scanner -> reviewer -> fixer. Toolchain + LLM scan, deep analysis with root cause enrichment, and automated fix with rollback-on-failure.
spawn_agent({ task_name: "team_review", message: "Execute skill team-review, args: task description" })
|
SKILL.md (this file) = Router
|
+--------------+--------------+
| |
no --role flag --role <name>
| |
Coordinator Worker
roles/coordinator/role.md roles/<name>/role.md
|
+-- analyze -> dispatch -> spawn workers -> STOP
|
+-------+-------+-------+
v v v
[scan] [review] [fix]
team-worker agents, each loads roles/<role>/role.md| Role | Path | Prefix | Inner Loop | |------|------|--------|------------| | coordinator | roles/coordinator/role.md | — | — | | scanner | roles/scanner/role.md | SCAN- | false | | reviewer | [roles/reviewer/role.md](roles/reviewer/role.md) | REV- | false | | fixer | roles/fixer/role.md | FIX- | true |
Parse $ARGUMENTS:
--role <name> -> Read roles/<name>/role.md, execute Phase 2-4--role -> @roles/coordinator/role.md, execute entry routerRV{run_dir}/work/team/reviewmaestro delegate --mode analysis (read-only), maestro delegate --mode write (modifications)mcp__maestro__team_msg(session_id=<run-id>, ...)Coordinator spawns workers using this template:
spawn_agent({
subagent_type: "team-worker",
description: "Spawn <role> worker",
team_name: "review",
name: "<role>",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: <skill_root>/roles/<role>/role.md
session: {run_dir}/work/team
session_id: <run-id>
team_name: review
requirement: <task-description>
inner_loop: <true|false>
## Progress Milestones
session_id: <run-id>
Report progress via team_msg at natural phase boundaries (context loaded -> core work done -> verification).
Report blockers immediately via team_msg type="blocker".
Report completion via team_msg type="task_complete" after final send_message.
Read role_spec file (@<skill_root>/roles/<role>/role.md) to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role Phase 2-4 -> built-in Phase 5 (report).`
})| Command | Action | |---------|--------| | check / status | View pipeline status graph | | resume / continue | Advance to next step | | --full | Enable scan + review + fix pipeline | | --fix | Fix-only mode (skip scan/review) | | -q / --quick | Quick scan only | | --dimensions=sec,cor,prf,mnt | Custom dimensions | | -y / --yes | Skip confirmations |
When pipeline completes, coordinator presents:
request_user_input({
questions: [{
question: "Review pipeline complete. What would you like to do?",
header: "Completion",
multiSelect: false,
options: [
{ label: "Archive & Clean (Recommended)", description: "Archive session, clean up team" },
{ label: "Keep Active", description: "Keep session for follow-up work" },
{ label: "Export Results", description: "Export deliverables to target directory" }
]
}]
}){run_dir}/
├── outputs/
│ ├── scan/ # Scanner output
│ ├── review/ # Reviewer output
│ └── fix/ # Fixer output
├── report.md # Human-readable synthesis + handoff
└── work/team/ # Team coordination (non-artifact)
├── .msg/messages.jsonl # Team message bus
├── .msg/meta.json # Message-bus state + cross-role state
└── wisdom/ # Cross-task knowledge| Scenario | Resolution | |----------|------------| | Unknown --role value | Error with available role list | | Role not found | Error with expected path (roles/<name>/role.md) | | CLI tool fails | Worker fallback to direct implementation | | Scanner finds 0 findings | Report clean, skip review + fix | | User declines fix | Delete FIX tasks, complete with review-only results | | Fast-advance conflict | Coordinator reconciles on next callback | | Completion action fails | Default to Keep Active |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-06 | fail→pass | 10,411 | 2,723 | -74% | 1 | 1 | 0% | 1,725 | 1,976 | +15% | 0 | 0 | — |
case-01 | fail→fail | 7,612 | 7,299 | -4% | 1 | 1 | 0% | 893 | 2,303 | +158% | 0 | 0 | — |
case-02 | fail→fail | 19,444 | 10,028 | -48% | 1 | 1 | 0% | 2,736 | 2,859 | +4% | 0 | 0 | — |
case-03 | fail→pass | 13,501 | 6,796 | -50% | 1 | 1 | 0% | 2,145 | 2,734 | +27% | 0 | 0 | — |
case-04 | fail→pass | 24,182 | 3,273 | -86% | 1 | 1 | 0% | 1,816 | 2,079 | +14% | 0 | 0 | — |
case-05 | fail→fail | 8,395 | 13,090 | +56% | 1 | 1 | 0% | 1,378 | 3,448 | +150% | 0 | 0 | — |
case-07 | fail→pass | 7,961 | 2,208 | -72% | 1 | 1 | 0% | 1,322 | 1,883 | +42% | 0 | 0 | — |
case-08 | fail→pass | 13,358 | 1,818 | -86% | 1 | 1 | 0% | 2,038 | 1,771 | -13% | 0 | 0 | — |
case-09 | fail→pass | 7,113 | 2,055 | -71% | 1 | 1 | 0% | 1,103 | 1,823 | +65% | 0 | 0 | — |
case-10 | pass→fail | 6,201 | 7,454 | +20% | 1 | 1 | 0% | 867 | 2,038 | +135% | 0 | 0 | — |
case-11 | fail→fail | 19,092 | 5,493 | -71% | 1 | 1 | 0% | 2,775 | 1,804 | -35% | 0 | 0 | — |
case-12 | fail→fail | 5,819 | 26,411 | +354% | 1 | 1 | 0% | 976 | 1,996 | +105% | 0 | 0 | — |
case-13 | pass→fail | 12,600 | 22,357 | +77% | 1 | 1 | 0% | 2,169 | 1,929 | -11% | 0 | 0 | — |
case-14 | fail→pass | 8,552 | 4,410 | -48% | 1 | 1 | 0% | 1,357 | 2,159 | +59% | 0 | 0 | — |
case-15 | fail→pass | 8,358 | 4,157 | -50% | 1 | 1 | 0% | 1,440 | 2,177 | +51% | 0 | 0 | — |
case-16 | fail→pass | 10,516 | 2,672 | -75% | 1 | 1 | 0% | 1,636 | 1,855 | +13% | 0 | 0 | — |
case-17 | pass→pass | 11,509 | 1,734 | -85% | 1 | 1 | 0% | 1,731 | 1,836 | +6% | 0 | 0 | — |
case-18 | fail→pass | 12,048 | 1,524 | -87% | 1 | 1 | 0% | 1,994 | 1,748 | -12% | 0 | 0 | — |
case-19 | fail→pass | 7,203 | 2,839 | -61% | 1 | 1 | 0% | 1,072 | 2,091 | +95% | 0 | 0 | — |
case-20 | pass→fail | 15,372 | 5,254 | -66% | 1 | 1 | 0% | 3,261 | 1,833 | -44% | 0 | 0 | — |
case-21 | pass→fail | 9,136 | 6,719 | -26% | 1 | 1 | 0% | 1,002 | 1,787 | +78% | 0 | 0 | — |
case-22 | pass→pass | 11,634 | 12,583 | +8% | 1 | 1 | 0% | 2,390 | 3,251 | +36% | 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 15 counted toward the lift figure. The other 7 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 +32 percentage points is the difference between those two pass rates over the 15 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +27% |
Other measured skills in the registry, with their headline benchmark lift.