maestro
免费Intent-to-chain planner over the canonical Session/Run lifecycle
中文简介正在准备中。当前显示原文说明。
Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on "Team Coordinate ".
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
<required_reading> @~/.maestro/workflows/run-mode-lite.md </required_reading>
Universal team coordination skill: analyze task -> generate role-specs -> dispatch -> execute -> deliver. Only the coordinator is built-in. All worker roles are dynamically generated as lightweight role-spec files and spawned via the team-worker agent.
+---------------------------------------------------+
| Skill(skill="team-coordinate") |
| args="task description" |
+-------------------+-------------------------------+
|
Orchestration Mode (auto -> coordinator)
|
Coordinator (built-in)
Phase 0-5 orchestration
|
+-------+-------+-------+-------+
v v v v v
[team-worker agents, each loaded with a dynamic role-spec]
(roles generated at runtime from task analysis)
CLI Tools (callable by any worker):
maestro delegate --mode analysis - analysis and exploration
maestro delegate --mode write - code generation and modification
| Constant | Value |
|---|---|
| Session prefix | TC |
| Session path | {run_dir}/work/team/ |
| Worker agent | team-worker |
| Message bus | mcp__maestro__team_msg(session_id=<run-id>, ...) |
| CLI analysis | maestro delegate --mode analysis |
| CLI write | maestro delegate --mode write |
| Max roles | 5 |
This skill is coordinator-only. Workers do NOT invoke this skill -- they are spawned as team-worker agents directly.
Parse $ARGUMENTS. No --role needed -- always routes to coordinator.
Only coordinator is statically registered. All other roles are dynamic, stored as role-specs in session.
| Role | File | Type |
|---|---|---|
| coordinator | roles/coordinator/role.md | built-in orchestrator |
| (dynamic) | {run_dir}/work/team/role-specs/<role-name>.md | runtime-generated role-spec |
Workers can use CLI tools for analysis and code operations:
| Tool | Purpose |
|---|---|
| maestro delegate --mode analysis | Analysis, exploration, pattern discovery |
| maestro delegate --mode write | Code generation, modification, refactoring |
Always route to coordinator. Coordinator reads roles/coordinator/role.md and executes its phases.
User just provides task description.
Invocation: Skill(skill="team-coordinate", args="task description")
Lifecycle:
User provides task description
-> coordinator Phase 1: task analysis (detect capabilities, build dependency graph)
-> coordinator Phase 2: generate role-specs + initialize session
-> coordinator Phase 3: create task chain from dependency graph
-> coordinator Phase 4: spawn first batch workers (background) -> STOP
-> Worker executes -> SendMessage callback -> coordinator advances next step
-> Loop until pipeline complete -> Phase 5 report + completion action
User Commands (wake paused coordinator):
| Command | Action |
|---|---|
check / status | Output execution status graph, no advancement |
resume / continue | Check worker states, advance next step |
revise <TASK-ID> [feedback] | Revise specific task with optional feedback |
feedback <text> | Inject feedback into active pipeline |
improve [dimension] | Auto-improve weakest quality dimension |
When coordinator spawns workers, use team-worker agent with role-spec path:
Agent({
subagent_type: "team-worker",
description: "Spawn <role> worker",
team_name: <team-name>,
name: "<role>",
run_in_background: true,
prompt: `## Role Assignment
role: <role>
role_spec: {run_dir}/work/team/role-specs/<role>.md
session: {run_dir}/work/team
session_id: <run-id>
team_name: <team-name>
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 SendMessage.
Read role_spec file to load Phase 2-4 domain instructions.
Execute built-in Phase 1 (task discovery) -> role-spec Phase 2-4 -> built-in Phase 5 (report).`
})
Inner Loop roles (role has 2+ serial same-prefix tasks): Set inner_loop: true. The team-worker agent handles the loop internally.
Single-task roles: Set inner_loop: false.
When pipeline completes (all tasks done), coordinator presents an interactive choice:
AskUserQuestion({
questions: [{
question: "Team 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, then clean" }
]
}]
})
| Choice | Steps |
|---|---|
| Archive & Clean | Update session status="completed" -> TeamDelete -> output final summary with artifact paths |
| Keep Active | Update session status="paused" -> output: "Resume with: Skill(skill='team-coordinate', args='resume')" |
| Export Results | AskUserQuestion(target path) -> copy artifacts to target -> Archive & Clean |
| Spec | Purpose |
|---|---|
| specs/pipelines.md | Dynamic pipeline model, task naming, dependency graph |
| specs/role-spec-template.md | Template for dynamic role-spec generation |
| specs/quality-gates.md | Quality thresholds and scoring dimensions |
| specs/knowledge-transfer.md | Context transfer protocols between roles |
{run_dir}/
+-- outputs/ # Formal worker deliverables
| +-- <artifact>.md
+-- evidence/discussions/ # Inline discuss records
| +-- <round>.md
+-- report.md # Human-readable synthesis + handoff
+-- work/team/ # Team coordination (non-artifact)
+-- team-session.json # Session state + dynamic role registry
+-- task-analysis.json # Phase 1 output: capabilities, dependency graph
+-- role-specs/ # Dynamic role-spec definitions (generated Phase 2)
| +-- <role-1>.md # Lightweight: frontmatter + Phase 2-4 only
| +-- <role-2>.md
+-- .msg/ # Team message bus + state
| +-- messages.jsonl # Message log
| +-- meta.json # Session metadata + cross-role state
+-- wisdom/ # Cross-task knowledge
| +-- learnings.md
| +-- decisions.md
| +-- issues.md
+-- explorations/ # Shared explore cache
+-- cache-index.json
+-- explore-<angle>.json
{
"session_id": "TC-<slug>-<date>",
"task_description": "<original user input>",
"status": "active | paused | completed",
"team_name": "<team-name>",
"roles": [
{
"name": "<role-name>",
"prefix": "<PREFIX>",
"responsibility_type": "<type>",
"inner_loop": false,
"role_spec": "role-specs/<role-name>.md"
}
],
"pipeline": {
"dependency_graph": {},
"tasks_total": 0,
"tasks_completed": 0
},
"active_workers": [],
"completed_tasks": [],
"completion_action": "interactive",
"created_at": "<timestamp>"
}
Coordinator supports resume / continue for interrupted sessions:
{run_dir}/work/team/team-session.json for active/paused sessions| Scenario | Resolution |
|---|---|
| Unknown command | Error with available command list |
| Dynamic role-spec not found | Error, coordinator may need to regenerate |
| Command file not found | Fallback to inline execution |
| CLI tool fails | Worker proceeds with direct implementation, logs warning |
| Explore cache corrupt | Clear cache, re-explore |
| Fast-advance spawns wrong task | Coordinator reconciles on next callback |
| capability_gap reported | Coordinator generates new role-spec via handleAdapt |
| Completion action fails | Default to Keep Active, log warning |
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Intent-to-chain planner over the canonical Session/Run lifecycle
中文简介正在准备中。当前显示原文说明。
Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks.
中文简介正在准备中。当前显示原文说明。
Create or sync session worktree for parallel dev
中文简介正在准备中。当前显示原文说明。
Manage editing boundary restrictions
中文简介正在准备中。当前显示原文说明。
Maestro Flow 命令帮助系统。搜索命令、浏览技能、工作流推荐、新手引导。Triggers on "maestro-help", "帮助", "命令", "怎么用", "skill", "workflow", "maestro 怎么用".
中文简介正在准备中。当前显示原文说明。
Use when designing, reviewing, refining, fixing, or codifying frontend UI with Maestro's self-contained Impeccable core
中文简介正在准备中。当前显示原文说明。