maestro-init

SkillDev tools

Initialize project with auto state detection

Use maestro-init in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add maestro-init and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the maestro-init skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

maestro-initStart free

What this skill tells your AI

The instructions your AI receives, as published by catlog22/maestro-flow in .codex/skills/maestro-init/SKILL.md and read by Ahel’s review.

<bootstrap_mode> This skill initializes protected project state before a Session exists. It MUST NOT call maestro run create; bootstrap files remain owned by their protected stores. </bootstrap_mode>

<deferred_reading>

  • project.md — read when generating project description
  • state.json — read when creating initial state
  • config.json — read when creating workflow configuration </deferred_reading>

Flags:

FlagEffectDefault
-y / --yesAutomatic 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>

Phase Gates (MANDATORY, BLOCKING)

GATE 1: Pre-flight → Interview

  • REQUIRED: .workflow/ existence check completed.
  • REQUIRED: --from source validated (if provided).
  • BLOCKED if: E002 (greenfield conflict with existing .workflow/) unresolved.

GATE 2: Interview → Research

  • REQUIRED: All interview decisions recorded in project.md and config.json.
  • REQUIRED: .workflow/ directory created with initial structure.
  • BLOCKED if: interview decisions not yet written to files.

GATE 3: Research → Completion

  • REQUIRED: All 3 required artifacts exist (project.md, state.json, config.json).
  • REQUIRED: .workflow/specs/ initialized.
  • BLOCKED if: any artifact missing — write it before reporting completion.

Pre-flight

  1. Check if .workflow/ already exists — if so, load state and warn (E002 for greenfield conflicts)
  2. Validate --from source is accessible if provided

Follow '~/.maestro/workflows/init.md' completely.

Artifact Verification (before completion)

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.

=== WORKFLOW INITIALIZED ===
Project: {project_name}
State:   .workflow/state.json (active)

Created:
  .workflow/project.md
  .workflow/state.json
  .workflow/config.json
  .workflow/specs/

Ralph-invoked completion

End the step through the v3 Run lifecycle (no text block output):

maestro run complete {run_id} --session {session_id} --actor {actor_id} --expected-orchestration-revision {orchestration_revision} --expected-run-revision {run_revision} --verdict {VERDICT} [--summary "<summary>"] --advance --json

(run-id 由 birth packet 提供 — 自动解析当前 running 步)

Verdicts (v3 surface):

  • done — Normal completion
  • done_with_concerns — Completed with concerns; pass --summary and put concerns in report.md frontmatter
  • needs-retry / blocked — apply the exact structured continuation using fully fenced run transition or run cancel; retry only through a later fenced run next after Runtime reports the step pending

Next-step routing

ConditionSuggestion
Roadmap needed (default light)route step roadmap through /maestro-next or the canonical receipt-chained session open -> session chain insert --command roadmap --arg "<goal>" -> run next flow

Note: roadmap step is responsible for creating state.json.sessions[] entries and setting the first active_session_id. | Full spec package | route step blueprint through /maestro-next or the canonical receipt-chained self-start flow | | Explore ideas first | route step brainstorm through /maestro-next or the canonical receipt-chained self-start flow | | Quick ad-hoc task | /maestro-companion "{goal}" |

<error_codes>

CodeSeverityConditionRecovery
E001errorNo arguments provided when -y requires @ referenceCheck arguments format, re-run with correct input
E002error.workflow/ already exists (greenfield init)Use --from to import existing state, or remove .workflow/ to start fresh
E003errorContext source not found (--from / --from-brainstorm)Check arguments format, re-run with correct input
E004errorTemplate file missing in ~/.maestro/templates/Run maestro-update to restore templates
E005warning.workflow/ already exists (existing codebase onboarding)Merge with existing state or overwrite; user chooses via request_user_input
W001warningResearch agent failed, continuing with partial resultsRetry 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 and empty sessions[] 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
  • All interview decisions written to project.md / config.json before proceeding
  • Research completed (if enabled) — parallel agents spawned with results merged
  • Next-step routing displayed in completion report </success_criteria>

Signals

GitHub stars
560
Forks
68
Last commit
Sep 2026
Advanced
Item type
skill
Key
maestro-init
Source
github.com/catlog22/maestro-flow