Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Unified team skill for issue resolution. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team issue".
.claude/skills/catlog22-team-issue/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 25% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -15% | 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 issue resolution pipeline: explore context -> plan solution -> review (optional) -> marshal queue -> implement. Supports Quick, Full, and Batch pipelines with review-fix cycle.
spawn_agent({ task_name: "team_issue", message: "Execute skill team-issue, args: <issue-ids> [--mode=<mode>]" })
|
SKILL.md (this file) = Router
|
+--------------+--------------+
| |
no --role flag --role <name>
| |
Coordinator Worker
roles/coordinator/role.md roles/<name>/role.md
|
+-- clarify -> dispatch -> spawn workers -> STOP
|
+-------+-------+-------+-------+
v v v v v
[explor] [plann] [review] [integ] [imple]| Role | Path | Prefix | Inner Loop | |------|------|--------|------------| | coordinator | roles/coordinator/role.md | — | — | | explorer | roles/explorer/role.md | EXPLORE- | false | | planner | [roles/planner/role.md](roles/planner/role.md) | SOLVE- | false | | reviewer | roles/reviewer/role.md | AUDIT- | false | | integrator | [roles/integrator/role.md](roles/integrator/role.md) | MARSHAL- | false | | implementer | roles/implementer/role.md | BUILD- | false |
.workflow/codebase/ARCHITECTURE.md exists, read for module boundariesmaestro load --type spec --category coding — load coding constraints as shared contextmaestro load --type spec --category debug — load debug constraints as shared contextmaestro search "issue resolution fix" --json — top 5 entries as prior contextParse $ARGUMENTS:
--role <name> → Read roles/<name>/role.md, execute Phase 2-4--role → @roles/coordinator/role.md, execute entry routerTISL{run_dir}/work/team/issuemaestro 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: "issue",
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: issue
requirement: <task-description>
inner_loop: 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).`
})Parallel spawn (Batch mode, N explorer or M implementer instances):
spawn_agent({
subagent_type: "team-worker",
name: "<role>-<N>",
team_name: "issue",
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: issue
requirement: <task-description>
agent_name: <role>-<N>
inner_loop: 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, owner=<role>-<N>) -> role Phase 2-4 -> built-in Phase 5 (report).`
})| Command | Action | |---------|--------| | check / status | View execution status graph, no advancement | | resume / continue | Check worker states, advance next step |
{run_dir}/work/team/
├── team-session.json # Session metadata + pipeline + fix_cycles
├── task-analysis.json # Coordinator analyze output
├── .msg/
│ ├── messages.jsonl # Message bus log
│ └── meta.json # Session state + cross-role state
├── wisdom/ # Cross-task knowledge
│ ├── learnings.md
│ ├── decisions.md
│ ├── conventions.md
│ └── issues.md
├── explorations/ # Explorer output
│ └── context-<issueId>.json
├── {run_dir}/outputs/solutions/ # Planner output
│ └── solution-<issueId>.json
├── {run_dir}/outputs/audits/ # Reviewer output
│ └── audit-report.json
├── {run_dir}/outputs/queue/ # Integrator output
└── {run_dir}/outputs/builds/ # Implementer output| Scenario | Resolution | |----------|------------| | Unknown command | Error with available command list | | Role not found | Error with role registry | | CLI tool fails | Worker fallback to direct implementation | | Fast-advance conflict | Coordinator reconciles on next callback | | Completion action fails | Default to Keep Active | | Review rejection exceeds 2 rounds | Force convergence to integrator | | No issues found for given IDs | Coordinator reports error to user | | Deferred BUILD count unknown | Defer to MARSHAL callback |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→fail | 2,442 | 5,789 | +137% | 1 | 1 | 0% | 199 | 2,192 | +1002% | 0 | 0 | — |
case-20 | pass→pass | 8,080 | 10,700 | +32% | 1 | 1 | 0% | 1,616 | 3,850 | +138% | 0 | 0 | — |
case-01 | fail→fail | 4,377 | 6,199 | +42% | 1 | 1 | 0% | 266 | 2,303 | +766% | 0 | 0 | — |
case-03 | fail→fail | 13,564 | 15,363 | +13% | 1 | 1 | 0% | 1,363 | 2,171 | +59% | 0 | 0 | — |
case-04 | fail→fail | 6,397 | 6,890 | +8% | 1 | 1 | 0% | 954 | 2,145 | +125% | 0 | 0 | — |
case-05 | fail→fail | 5,904 | 13,415 | +127% | 1 | 1 | 0% | 885 | 2,721 | +207% | 0 | 0 | — |
case-06 | pass→fail | 12,233 | 7,726 | -37% | 1 | 1 | 0% | 2,191 | 2,416 | +10% | 0 | 0 | — |
case-07 | fail→pass | 12,227 | 3,775 | -69% | 1 | 1 | 0% | 2,006 | 2,538 | +27% | 0 | 0 | — |
case-08 | fail→fail | 5,190 | 7,326 | +41% | 1 | 1 | 0% | 824 | 2,240 | +172% | 0 | 0 | — |
case-09 | fail→pass | 8,760 | 1,935 | -78% | 1 | 1 | 0% | 1,488 | 2,121 | +43% | 0 | 0 | — |
case-10 | fail→pass | 11,273 | 1,904 | -83% | 1 | 1 | 0% | 1,701 | 2,130 | +25% | 0 | 0 | — |
case-11 | fail→pass | 9,380 | 2,190 | -77% | 1 | 1 | 0% | 1,413 | 2,128 | +51% | 0 | 0 | — |
case-12 | fail→pass | 21,575 | 5,247 | -76% | 1 | 1 | 0% | 3,216 | 2,738 | -15% | 0 | 0 | — |
case-13 | pass→pass | 10,365 | 2,175 | -79% | 1 | 1 | 0% | 1,570 | 2,177 | +39% | 0 | 0 | — |
case-14 | pass→pass | 6,815 | 2,223 | -67% | 1 | 1 | 0% | 1,067 | 2,134 | +100% | 0 | 0 | — |
case-15 | fail→pass | 11,150 | 1,658 | -85% | 1 | 1 | 0% | 1,770 | 2,081 | +18% | 0 | 0 | — |
case-16 | fail→pass | 8,199 | 3,815 | -53% | 1 | 1 | 0% | 1,251 | 2,318 | +85% | 0 | 0 | — |
case-17 | fail→pass | 13,636 | 5,045 | -63% | 1 | 1 | 0% | 2,351 | 2,552 | +9% | 0 | 0 | — |
case-18 | fail→fail | 10,671 | 2,666 | -75% | 1 | 1 | 0% | 1,602 | 2,236 | +40% | 0 | 0 | — |
case-19 | fail→pass | 10,932 | 2,171 | -80% | 1 | 1 | 0% | 1,765 | 2,188 | +24% | 0 | 0 | — |
case-21 | pass→fail | 4,782 | 5,130 | +7% | 1 | 1 | 0% | 909 | 2,006 | +121% | 0 | 0 | — |
case-22 | pass→pass | 5,969 | 3,967 | -34% | 1 | 1 | 0% | 1,155 | 2,594 | +125% | 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 14 counted toward the lift figure. The other 8 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 14 comparable cases. 2 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 | +57% |
Other measured skills in the registry, with their headline benchmark lift.