一键导入
maestro-init
Initialize project with auto state detection
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Initialize project with auto state detection
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Default interactive entry for development intents — score intent + project state, recommend one atomic step, execute after confirmation. Multi-step intents: stepwise, user-confirmed manual-engine chain, or hand off to /maestro. Never auto-orchestrates
Adaptive lifecycle orchestrator — compose, dispatch ralph-executor agent, evaluate decision, loop
Auto-route intent to optimal command chain — default multi-step closed-loop orchestration; for stepwise interactive execution use /maestro-next
ACO swarm intelligence with modular Workflow composition and adversarial decision gates. Coordinator drives iteration loop; 4 composable Workflow scripts handle exploration, scoring, convergence, and synthesis — each with built-in adversarial patterns.
Unified team skill for architecture optimization. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team arch-opt".
Unified team skill for brainstorming team. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team brainstorm".
| name | maestro-init |
| description | Initialize project with auto state detection |
| argument-hint | [-y] [--from <source>] [--from-brainstorm SESSION-ID] |
| allowed-tools | ["AskUserQuestion","Bash","Glob","Grep","Read","Write","teammate"] |
| session-mode | bootstrap |
<deferred_reading>
Flags:
| Flag | Effect | Default |
|---|---|---|
-y / --yes | Automatic mode. After config questions, runs research without further interaction. Expects idea document via @ reference. | false |
--from <source> | Load upstream context package (brainstorm:ID, @file, or path). Consumes context-package.json to pre-fill project vision, goals, constraints, and terminology. Skips interactive questioning. Alias: --from-brainstorm | — |
Load project state if exists:
Check for .workflow/state.json -- loads context if project already initialized.
Output boundary: ALL file writes MUST target .workflow/ (project.md, state.json, config.json, specs/) only. NEVER modify source code or files outside .workflow/.
<interview_protocol> Follows @~/.maestro/workflows/interview-mechanics.md standard.
Interaction mode: convergent menu-driven Decision tree (strict order): project type (greenfield / existing codebase onboarding) → tech stack detection and confirmation → directory structure preferences → initial configuration (specs categories, wiki bootstrap) Scope guard: only init decisions; do not prejudge roadmap structure or plan scope Writeback target: project.md (project description) + config.json (settings) + state.json (initial state) Additional skip conditions: --from source (upstream context pre-fills decisions) Exit condition: all configuration questions settled → proceed to workflow execution </interview_protocol>
GATE 1: Pre-flight → Interview
.workflow/ existence check completed.--from source validated (if provided)..workflow/) unresolved.GATE 2: Interview → Research
.workflow/ directory created with initial structure.GATE 3: Research → Completion
.workflow/specs/ initialized..workflow/ already exists — if so, load state and warn (E002 for greenfield conflicts)--from source is accessible if providedFollow '~/.maestro/workflows/init.md' completely.
REQUIRED_ARTIFACTS = [
".workflow/project.md", // Core Value, Requirements, Key Decisions
".workflow/state.json", // artifacts[], initialized to idle state
".workflow/config.json" // Workflow configuration
]
If any artifact is missing: DO NOT report completion. Write the missing file first.
### Standalone report=== WORKFLOW INITIALIZED ===
Project: {project_name}
State: .workflow/state.json (active)
Created:
.workflow/project.md
.workflow/state.json
.workflow/config.json
.workflow/specs/
End the step by calling the CLI (no text block output):
maestro run complete --session {session_id} --verdict {VERDICT} [--evidence {path}]
(run-id 可省略 — 自动解析当前 running 步)
Verdicts:
--note--reason| Condition | Suggestion |
|---|---|
| Roadmap needed (default light) | step roadmap (maestro run prepare --platform pi roadmap + maestro run create roadmap --session YYYYMMDD-roadmap-{topic} --intent "{goal}") |
| Full spec package | step blueprint (maestro run prepare --platform pi blueprint + maestro run create blueprint --session YYYYMMDD-blueprint-{topic} --intent "{goal}") |
| Explore ideas first | step brainstorm (maestro run prepare --platform pi brainstorm + maestro run create brainstorm --session YYYYMMDD-brainstorm-{topic} --intent "{goal}") |
| View project dashboard | /manage status |
| Quick ad-hoc task | step quick (maestro run prepare --platform pi quick + maestro run create quick --session YYYYMMDD-quick-{topic} --intent "{goal}") |
<error_codes>
| Code | Severity | Condition | Recovery |
|---|---|---|---|
| E001 | error | No arguments provided when -y requires @ reference | Check arguments format, re-run with correct input |
| E002 | error | .workflow/ already exists for greenfield init | Check .workflow/ directory state, resolve conflicts |
| E003 | error | Context source not found (--from / --from-brainstorm) | Check arguments format, re-run with correct input |
| W001 | warning | Research agent failed, continuing with partial results | Retry research or proceed with partial results |
| </error_codes> |
<success_criteria>
.workflow/project.md created with Core Value, Requirements (Validated/Active/Out of Scope), Key Decisions.workflow/state.json created with artifacts[] array, initialized to idle state.workflow/config.json created with workflow / execution / git / gates / codebase / guard / collab / specInjection / dashboard segments.workflow/specs/ initialized with convention files