nicolas-codemate/bootstrap-project

Bootstrap Project - Modular Orchestrator

<context> This skill runs a structured CPO+CTO interview flow to establish the foundations of a project. It orchestrates two specialized agents (product-strategist and tech-architect) through modular step files.

The skill does NOT modify /express-need. It stands alone. /express-need and bootstrap-project can be used independently; bootstrap-project does not call /express-need.

Four modes:

• bootstrap (default): 4 phases (vision, architecture, roadmap, save) + optional ticket creation across 7 steps
• continue (auto-detected): when state file exists, detects progress and resumes at the next incomplete step
• tickets: jump directly to ticket creation (step 07) — requires bootstrap to be complete
• review: re-validate existing foundational documents, 3 review steps

Each step lives in its own file and declares its next transition. This orchestrator parses arguments, selects the entry point, loads the first step, tracks state, and follows transitions until STOP.

State Tracking

Progress is tracked in ./docs/project/.bootstrap-state.json:

{
  "version": 1,
  "started": "2026-04-07",
  "updated": "2026-04-07T15:51:00",
  "last_completed": "save",
  "steps_done": ["receive-and-check", "vision-phase", "architecture-phase", "roadmap-phase", "save"]
}

This file is updated after each step completes. It enables:

• Resuming interrupted workflows (/bootstrap-project without args)
• Knowing exactly where we are at any point
• Resetting from scratch (delete the state file + docs) </context>

Input

Arguments passed from command: $ARGUMENTS

Step 1: Parse Arguments and Detect Mode

<instructions> Parse `$ARGUMENTS`:

• If the first token is review (case-insensitive) → REVIEW mode
  • Entry point: review/R1-read-existing.md
• If the first token is tickets (case-insensitive) → TICKETS mode
  • Verify ./docs/project/.bootstrap-state.json exists AND all 5 core docs exist
  • If not: display error "Le bootstrap n'est pas terminé. Lance d'abord /bootstrap-project pour générer les documents de projet." → STOP
  • If yes: entry point: steps/07-create-tickets.md (skip steps 01-06)
  • Load all doc variables from existing files before entering step 07
• If $ARGUMENTS is empty AND ./docs/project/.bootstrap-state.json exists → CONTINUE mode
  • Read the state file to determine last_completed
  • Entry point: the step AFTER last_completed (see state-to-step mapping below)
  • Load all existing doc variables from files before entering the step
• Otherwise → BOOTSTRAP mode
  • Remaining $ARGUMENTS is the raw idea, or empty
  • Entry point: steps/01-receive-and-check.md

Store the raw idea (if any) as raw_idea for use by the first step.

Get today's date in ISO format via Bash: date +%Y-%m-%d. Store as today_date.

State-to-Step Mapping (for continue mode)

| last_completed | Next step | What to load | |---|---|---| | receive-and-check | steps/02-vision-phase.md | raw_idea from state or vision.md sources | | vision-phase | steps/03-architecture-phase.md | vision.md | | architecture-phase | steps/04-roadmap-phase.md | vision.md, architecture.md, constraints.md | | roadmap-phase | steps/05-save.md | all in-memory content (rare — save usually follows immediately) | | save | steps/06-next-steps.md | all docs from files | | next-steps | steps/07-create-tickets.md | all docs from files | | create-tickets | STOP (workflow complete) | suggest /bootstrap-project review |

Loading Doc Variables From Files

When resuming (continue or tickets mode), read each existing doc file, strip the YAML frontmatter (everything between the opening --- and closing ---), and store the remaining content as the corresponding variable:

• ./docs/project/vision.md → vision_content
• ./docs/project/architecture.md → architecture_content
• ./docs/project/constraints.md → constraints_content
• ./docs/project/roadmap.md → roadmap_content
• ./docs/project/mvp-features.md → mvp_features_content

Only load files that exist. Display: Reprise à l'étape : {step_name} </instructions>

Step 2: Load Entry Step

<instructions> Read the entry step file from `${CLAUDE_SKILL_DIR}`: - BOOTSTRAP mode: `${CLAUDE_SKILL_DIR}/steps/01-receive-and-check.md` - CONTINUE mode: the step file determined by state-to-step mapping - TICKETS mode: `${CLAUDE_SKILL_DIR}/steps/07-create-tickets.md` - REVIEW mode: `${CLAUDE_SKILL_DIR}/review/R1-read-existing.md`

Execute the step's instructions. </instructions>

Step 3: Follow Transitions

<workflow> After each step completes:

1. Update state file: record the completed step name and timestamp

   python3 -c "
   import json, datetime, os
   f = './docs/project/.bootstrap-state.json'
   os.makedirs(os.path.dirname(f), exist_ok=True)
   try:
       state = json.load(open(f))
   except (FileNotFoundError, json.JSONDecodeError):
       state = {'version': 1, 'started': '$(date +%Y-%m-%d)', 'steps_done': []}
   state['last_completed'] = '{step_name}'
   if '{step_name}' not in state['steps_done']:
       state['steps_done'].append('{step_name}')
   state['updated'] = datetime.datetime.now().isoformat(timespec='seconds')
   json.dump(state, open(f, 'w'), indent=2)
   print('State updated: {step_name}')
   "
   

   Replace {step_name} with the name field from the step's frontmatter.

2. Read the step file's next field from frontmatter

3. Resolve the next step file:

   • For bootstrap steps: ${CLAUDE_SKILL_DIR}/steps/{NN}-{next-name}.md (find by frontmatter name field)
   • For review steps: ${CLAUDE_SKILL_DIR}/review/R{N}-{next-name}.md
   • If next is STOP: end workflow

4. Load the next step file and execute

5. Repeat until STOP

Do not skip transitions. Each step file explicitly declares what comes next in its frontmatter — follow the chain until STOP, and update the state file between steps. </workflow>

Step Files Reference

Bootstrap Mode (default)

| Order | File | Name | Description | |-------|------|------|-------------| | 01 | steps/01-receive-and-check.md | receive-and-check | Receive raw idea, check for existing docs, handle conflicts | | 02 | steps/02-vision-phase.md | vision-phase | Product vision scout + interview + synthesis (product-strategist) | | 03 | steps/03-architecture-phase.md | architecture-phase | Architecture scout + interview + synthesis (tech-architect) | | 04 | steps/04-roadmap-phase.md | roadmap-phase | MVP interview + roadmap synthesis (product-strategist) | | 05 | steps/05-save.md | save | Write 5 files to ./docs/project/ with dated frontmatter | | 06 | steps/06-next-steps.md | next-steps | Display guidance, propose ticket creation | | 07 | steps/07-create-tickets.md | create-tickets | Break MVP features into atomic tickets and create them |

Review Mode

| Order | File | Name | Description | |-------|------|------|-------------| | R1 | review/R1-read-existing.md | review-read-existing | Read existing foundational docs, parse hypotheses and decisions | | R2 | review/R2-review-loop.md | review-loop | Ask user to re-validate each hypothesis, decision, and MVP feature | | R3 | review/R3-update-files.md | review-update-files | Append Review Log, update last_reviewed date, flag invalidated items |

References

• ${CLAUDE_SKILL_DIR}/references/file-formats.md — frontmatter templates and expected file structures
• ${CLAUDE_SKILL_DIR}/references/scout-parsing.md — how to parse scout agent outputs into AskUserQuestion calls
• ~/.claude/agents/references/cross-cutting-concerns.md — shared trigger table used by both agents

Language

All user communication in French. Technical content (file paths, command outputs, stack names, constraint text) in English.

NOW

<instructions> 1. Parse the arguments provided 2. Determine mode (bootstrap, continue, tickets, or review) 3. If continue/tickets: read state file, load existing doc variables 4. Load the entry step file 5. Follow transitions until STOP, updating state after each step </instructions>

Begin workflow for: $ARGUMENTS