Interactive project bootstrapper that populates planning docs and AI understanding docs based on conversational discovery with the user.
Guide a structured conversation with the user to understand their project, then populate .docs/planning/ and .ai-ingest-docs/ with project-specific content.
Present a structured summary back to the user:
## Here's what I understand about your project:
**Project:** [name]
**Purpose:** [one-liner]
**Target Users:** [who]
**Key Features:** [bullet list]
**Tech Stack:** [what you gathered]
**Scope:** [MVP / production / prototype / etc.]
Be honest about what you're unsure of. Don't pad with assumptions.
Ask 3–7 questions to fill gaps. Good question categories:
Don't ask all of these — pick the ones that matter for this specific project.
.ai-ingest-docs/project-goals-understanding.mdWrite this file FIRST. Structure:
# Project Goals Understanding
> Auto-generated by the repo-setup-agent based on conversational discovery.
> Last updated: [YYYY-MM-DD]
## Project Identity
- **Name:** [project name]
- **One-liner:** [single sentence description]
- **Repository:** [repo path or URL if known]
## Core Purpose
[2-3 paragraphs on what this project does and why it exists]
## Target Users
[Who uses this, their needs, their technical level]
## Key Features & Capabilities
[Bullet list of the main things this project does]
## Tech Stack & Architecture
[Languages, frameworks, databases, infrastructure]
## Scope & Constraints
- **In scope:** [what this project will do]
- **Out of scope:** [what it explicitly won't do]
- **Constraints:** [budget, timeline, team size, technical limitations]
## Key Decisions Made
[Architecture choices, tech stack rationale, trade-offs accepted]
## Open Questions & Assumptions
[Things the AI assumed or that still need user input]
Read each existing file in .docs/planning/ to understand its current structure, then overwrite with project-specific content. Always populate:
| File | Content |
|---|---|
overview.md | Product vision, scope, functional emphasis, product posture |
prd.md | Full PRD: summary, problem, users, objectives, features, requirements |
technical-specification.md | Architecture, tech stack choices, data flow, infrastructure |
user-stories.md | User stories with acceptance criteria grouped by feature area |
milestones.md | Phased delivery plan with deliverables per phase |
risks-and-decisions.md | Risk log, mitigation strategies, key architecture decisions |
README.md | Updated index of all planning docs including any new ones |
Only write these if they're relevant to the project:
| File | When to write |
|---|---|
auth-and-subscriptions.md | Project has user accounts, auth, or billing |
deployment-and-hosting.md | Deployment strategy is known or important |
project-structure-spec.md | Project has a meaningful folder/file schema |
sync-strategy.md | Multi-device or cloud sync is in play |
Evaluate whether the project needs docs beyond the standard set. Create any that would meaningfully help planning and execution. There is no fixed list — use judgment based on the project.
When creating a new doc:
my-new-doc.md# Title headerREADME.md indexAfter writing all files, present a summary:
## Repo Setup Complete
### AI Understanding
- `.ai-ingest-docs/project-goals-understanding.md` — [created/updated]
### Planning Docs Written
- `.docs/planning/overview.md` — [created/updated]
- `.docs/planning/prd.md` — [created/updated]
- [... list all files ...]
### New Docs Created
- `.docs/planning/api-design.md` — [why it was needed]
- [... any additional files ...]
### Files Skipped (not relevant)
- `auth-and-subscriptions.md` — project has no auth
- [... any skipped files ...]
[TBD — needs input] sparingly and only for genuinely unknown details..docs/planning/ and .ai-ingest-docs/ unless explicitly asked.