@edupia-tutor/spec-driven-docs 0.14.0

package/commands/setup-ai-first.tmpl

@@ -0,0 +1,358 @@
+# /setup-ai-first — Initialize Spec-Driven Docs in a Project
+
+Walk the user through a one-time setup that creates all required directories, installs CLAUDE.md, and verifies the environment.
+
+## Gate
+{{include:steps/gate.md}}
+
+*Note: For this command — **skip Gate Steps 1, 2, and 3** (there is no input file and no project context yet). Only run Step 0-B (model check). The project root is the **current working directory**. Proceed directly to the Precondition Check below.*
+
+---
+
+## Precondition Check
+
+Check if already set up:
+- If `CLAUDE.md` **and** `.agent/project-context.yaml` both exist → ask: "This project is already initialized. Re-run setup to regenerate config files? (Y/N)"
+  - N → stop
+  - Y → continue (existing files will be preserved — each step will offer merge/skip)
+- If only `specs/` exists or only partial setup detected → continue normally (safe to re-run)
+
+## Step 0.5 — Project Type
+
+Ask the user:
+
+```
+What type of project is this?
+  1. Single-service  — one codebase, one platform (standard setup)
+  2. Umbrella repo   — this repo contains multiple service submodules (microservices / multi-app)
+  3. PO Spec repo    — docs only, no runnable code (PRD + design-spec only)
+```
+
+Store the answer as `project_type`. Default to `1` if user does not answer.
+
+Based on answer:
+
+**project_type = 1 (Single-service):** Continue standard setup below.
+
+**project_type = 2 (Umbrella):** Ask two follow-up questions:
+- "Path to spec submodule (e.g. `free-trial-specs`)? Press Enter to skip."
+- "List services as `domain:module` pairs, comma-separated
+  (e.g. `user:java-spring,order:java-spring`). Press Enter to skip."
+
+Then:
+- Skip creating any `specs/` artifacts (all specs — PRD, BDD, tech-docs, design-spec — live in the spec submodule under the feature-package layout `specs/{domain}/{prd-slug}/`)
+- Create only: `.trace/`, `.agent/review/` at umbrella level
+  *(Unless user explicitly asks to create the full structure)*
+- Generate `.agent/project-context.yaml` in umbrella mode with the services and spec_source provided
+- Skip creating `CLAUDE.md` (umbrella has no single tech stack)
+- After setup, remind: "Open each service submodule separately in Claude Code to install the framework there if needed."
+
+**project_type = 3 (PO Spec repo):**
+- Create base dirs: `specs/product-definition/`, `specs/domain-knowledge/`, `feedback/`, `.agent/review/`
+- Per-feature artifacts (`specs/{domain}/{prd-slug}/{prd.md, bdd/, tech-docs/, design-spec/}`) are created on demand by the generate commands — do NOT pre-create them
+- Skip: `.trace/` (per-service, lives beside code in each service submodule)
+- Generate minimal `CLAUDE.md` with only §1 (project overview) and §7 (git conventions)
+- Ask the user: **"List your business domains (e.g. auth, payment, loyalty):"** — store as domain list for `project-context.yaml` and remind PO these names must be used consistently as `@trace.domain` in every PRD
+- Inform:
+  - Commands for PO repo: `/define-product`, `/generate-prd`, `/review-context`, `/generate-design-spec`
+  - **Critical for dev team handoff:** Every PRD must have `@trace.domain: {domain}` in its frontmatter. Dev team uses this to route generated BDD/code to the correct service submodule. Inconsistent domain names will break routing.
+  - Recommended PRD frontmatter:
+    ```
+    @trace.domain: {domain}    ← must match a key in dev team's services config
+    @trace.id: {TICKET-ID}
+    @trace.status: draft | approved
+    ```
+
+## Step 1 — Create Directory Structure
+
+Create these directories (skip if they exist):
+
+```
+{project-root}/
+├── specs/
+│   ├── product-definition/   ← Output of /define-product
+│   └── domain-knowledge/     ← business dictionary & domain context
+├── .trace/                   ← .trace/{domain}/{prd-slug}/{UC-ID}.tsv
+└── .agent/
+    └── review/
+```
+
+**Feature-package layout** — per-feature spec artifacts are NOT pre-created. Each generate
+command creates its own folder on demand under `specs/{domain}/{prd-slug}/`:
+
+```
+specs/{domain}/{prd-slug}/
+├── prd.md                    ← /generate-prd
+├── bdd/                      ← /generate-bdd (.feature files)
+├── tech-docs/                ← /generate-tech-docs
+└── design-spec/              ← /generate-design-spec (FE/App platforms only)
+```
+
+*Which base dirs to create varies by `project_type` set in Step 0.5:*
+
+| project_type | Create | Skip |
+|---|---|---|
+| **1 — Single-service** | Base structure above (`specs/product-definition/`, `specs/domain-knowledge/`, `.trace/`, `.agent/review/`) | per-feature folders (created on demand) |
+| **2 — Umbrella** | `.trace/` + `.agent/review/` only (at umbrella root) | Everything else — **all specs live in the spec submodule (`spec_source`)** under `specs/{domain}/{prd-slug}/`; service submodules hold only **code + `.trace/`** |
+| **3 — PO Spec repo** | `specs/product-definition/`, `specs/domain-knowledge/`, **`feedback/`**, `.agent/review/` (per-feature `specs/{domain}/{prd-slug}/` folders created on demand) | `.trace/` (per-service, lives beside code in each service submodule) |
+
+## Step 2 — Create CLAUDE.md
+
+*Skip this step entirely if `project_type = 2` (Umbrella) — umbrella has no single tech stack.*
+*For `project_type = 3` (PO Spec repo) — create a minimal CLAUDE.md with only §1 (project overview) and §7 (git conventions). Skip §2–§6.*
+
+Check if `CLAUDE.md` exists:
+- Yes → ask "Merge template or skip?"
+- No → create from the template below
+
+After creating, instruct: "Open CLAUDE.md and fill in the `{{PLACEHOLDER}}` values with your project information."
+
+### CLAUDE.md Template
+
+```
+# §1. Project Overview
+Project: {{PROJECT_NAME}}
+Language: {{LANGUAGE}}
+Framework: {{FRAMEWORK}}
+Build: {{BUILD_COMMAND}}
+Test: {{TEST_COMMAND}}
+Domains: {{COMMA_SEPARATED_DOMAINS}}
+
+# §2. Architecture
+layers: "{{LAYER_STACK}}"
+# Example: Controller → Facade → Service → Repository
+rules:
+  - "Controllers must not contain business logic"
+  - "Services own transaction boundaries"
+
+# §3. Coding Standards
+naming:
+  classes: "{{NAMING_CONVENTION}}"
+  methods: "{{METHOD_CONVENTION}}"
+response_wrapper: "{{WRAPPER}}"
+forbidden:
+  - "Magic numbers"
+  - "Debug print statements"
+
+# §4. Traceability
+# Every controller method must be tagged:
+# @trace.implements={UC-ID}-{SC-ID}
+# @trace.source=specs/{domain}/{prd-slug}/bdd/{UC-ID}.feature  ← adjust if specs_dir differs in .agent/project-context.yaml
+# Tests must be tagged:
+# @trace.verifies={UC-ID}
+
+# §5. Error Handling
+not_found: "{{NOT_FOUND_EXCEPTION}}"
+http_codes: { get: 200, create: 201, not_found: 404, validation: 400 }
+
+# §6. Build & Test
+build_command: "{{BUILD_COMMAND}}"
+test_command: "{{TEST_COMMAND}}"
+run_command: "{{RUN_COMMAND}}"
+
+# §7. Git Conventions
+branch_feature: "feature/{{TICKET_PREFIX}}-{N}-{slug}"
+commit_feature: "feat({{TICKET_PREFIX}}-{N}): {description}"
+```
+
+## Step 3 — Create project-context.yaml
+
+*For `project_type = 2` (Umbrella):*
+- *If `.agent/project-context.yaml` was already generated by `--init --umbrella` → open it and verify/edit the `services` section (domain keys, paths, modules). Skip template copy below.*
+- *If not yet generated → ask: "Spec submodule path?" and "Services (domain:module pairs)?" then generate umbrella config (see Step 0.5 for format).*
+
+Create `.agent/project-context.yaml` using `.agent/templates/project-context.yaml` as the source template.
+
+Copy the template and instruct: "Open `.agent/project-context.yaml` and fill in all `{{PLACEHOLDER}}` values. The `paths` section is pre-configured with sensible defaults — adjust if your project uses different directory names."
+
+## Step 4 — Create business-dictionary.md
+
+*Skip Steps 4 and 5 if `project_type = 2` (Umbrella) — business dictionary and core entities live in the spec submodule and are managed by the PO team. Dev team reads them from `{spec_source}/specs/domain-knowledge/`.*
+
+
+Create `specs/domain-knowledge/business-dictionary.md` if it does not exist:
+
+```markdown
+# Business Dictionary — {{PROJECT_NAME}}
+
+> Canonical terminology for this project. All PRDs, BDD specs, and code must follow these terms.
+> Managed by: PO / SA team.
+
+## Canonical Terms
+
+| Canonical Term | Description / Context |
+|----------------|----------------------|
+| {Term}         | {Short description, usage scope} |
+
+## Banned Terms
+
+| ❌ Do NOT use | ✅ Use instead    | Reason |
+|---------------|-------------------|--------|
+| {banned}      | {canonical}       | {why}  |
+
+## Status / Enum Registry
+
+| Entity | Field   | Allowed Values     |
+|--------|---------|--------------------|
+| {Entity} | status | {value1, value2} |
+```
+
+Instruct: "Open `specs/domain-knowledge/business-dictionary.md` and add your project terminology. This file will be read by all commands to enforce consistent naming."
+
+## Step 5 — Create core-entities.md
+
+Create `specs/domain-knowledge/core-entities.md` if it does not exist:
+
+```markdown
+# Core Entities — {{PROJECT_NAME}}
+
+> Machine-readable entity glossary for AI-assisted development.
+> Loaded by all commands so AI knows your domain model without reading source code.
+> Managed by: Tech Lead / Architect.
+>
+> HOW TO USE:
+> - Add one `## Entity: {Name}` section per domain entity (aggregate root, value object, etc.)
+> - Keep field descriptions concise — this is a REFERENCE, not API docs
+> - Update this file whenever you add/rename fields or change business invariants
+
+---
+
+## Entity: {EntityName}
+
+**Purpose**: {1-2 sentences — what this entity represents and why it exists in the domain}
+**Domain**: {domain}
+**Storage**: {e.g., `orders` table in PostgreSQL | `orders` collection in MongoDB}
+**Owner service**: {service/module that owns this entity}
+
+| Field        | Type    | Nullable | Description                         |
+|--------------|---------|----------|-------------------------------------|
+| id           | UUID    | No       | Primary key                         |
+| {field_name} | {type}  | Yes/No   | {short description}                 |
+| status       | Enum    | No       | See Status Registry in business-dictionary.md |
+
+**Business invariants:**
+- {Rule 1: e.g., "status can only transition: PENDING → ACTIVE → CLOSED"}
+- {Rule 2: e.g., "total must equal sum of line items"}
+
+**Relationships:**
+- `{EntityA}` 1:N `{EntityB}` — {one sentence description}
+- `{EntityA}` N:N `{EntityC}` via `{junction_table}` — {description}
+
+---
+
+## Entity: {AnotherEntity}
+
+*(Add more entities following the same pattern above)*
+```
+
+Instruct: "Open `specs/domain-knowledge/core-entities.md` and define your key domain entities. Start with aggregate roots. This file is loaded by every AI command — good definitions here save significant back-and-forth during code generation."
+
+## Step 6 — Install VS Code Extension (Recommended)
+
+Recommend the user install the **Spec Driven Docs Tools** VS Code extension — it provides Review Board + Living Documentation panels that integrate with this workflow.
+
+```bash
+code --install-extension SpecDrivenDocsTools.spec-driven-docs-tool
+```
+
+Or: VS Code → `Ctrl+Shift+P` → **"Extensions: Install from Marketplace"** → search **Spec Driven Docs Tools**.
+
+**What it does:**
+- 📋 **Review Board** — visual UI to review findings from `/refine-prd`, `/review-context`, `/review-tech-docs`
+- 📊 **Living Documentation** — traceability dashboard driven by `.trace/*.tsv`
+
+## Step 7 — Verify
+
+Checklist varies by `project_type`:
+
+**project_type = 1 (Single-service):**
+- [ ] `specs/` exists
+- [ ] `specs/product-definition/` exists
+- [ ] `specs/domain-knowledge/` exists
+- [ ] `.trace/` exists
+  *(per-feature `specs/{domain}/{prd-slug}/` folders are created on demand — not checked here)*
+- [ ] `.agent/project-context.yaml` exists
+- [ ] `CLAUDE.md` exists
+- [ ] `specs/domain-knowledge/business-dictionary.md` exists
+- [ ] `specs/domain-knowledge/core-entities.md` exists
+
+**project_type = 2 (Umbrella):**
+- [ ] `.agent/project-context.yaml` exists with `setup.mode: umbrella`
+- [ ] `services` section has at least one entry with correct domain keys
+- [ ] `spec_source` path exists (e.g., `my-project-specs/` directory is present)
+- [ ] `.agent/review/` exists
+- [ ] Spec submodule initialized: `git submodule status` shows no `-` prefix
+
+**project_type = 3 (PO Spec repo):**
+- [ ] `specs/product-definition/` exists
+- [ ] `specs/domain-knowledge/` exists
+- [ ] `feedback/` exists
+  *(per-feature `specs/{domain}/{prd-slug}/` folders are created on demand — not checked here)*
+- [ ] `.agent/review/` exists
+- [ ] `.agent/project-context.yaml` exists
+- [ ] `CLAUDE.md` exists (minimal)
+- [ ] `specs/domain-knowledge/business-dictionary.md` exists
+- [ ] `specs/domain-knowledge/core-entities.md` exists
+
+## Output
+
+{{include:steps/report-footer.md}}
+
+```
+/setup-ai-first Complete ✅
+```
+
+Output varies by `project_type`:
+
+**Single-service:**
+```
+Next:
+  1. Fill CLAUDE.md (replace {{PLACEHOLDER}} values)
+  2. Fill .agent/project-context.yaml
+  3. Fill specs/domain-knowledge/business-dictionary.md
+  4. Fill specs/domain-knowledge/core-entities.md
+  5. git add and commit those 4 files
+  6. Install VS Code extension:
+     code --install-extension SpecDrivenDocsTools.spec-driven-docs-tool
+  7. /define-product to start your first feature
+```
+
+**Umbrella:**
+```
+Next:
+  1. Review .agent/project-context.yaml:
+     - Update services[].path to match actual submodule directory names
+     - Update services domain keys to match @trace.domain in your PRD files
+     - Confirm spec_source path is correct
+
+  2. Run /sync — one command that handles everything else:
+     /sync
+     → git pull + submodule init + spec submodule update
+     → Auto-create .agent/project-context.yaml for each service submodule
+       (detects module from pom.xml / go.mod / package.json / pubspec.yaml etc.)
+     → Sync Living Docs panel
+     → Refresh spec-manifest.yaml
+
+  3. Start generating:
+     /generate-bdd {spec_source}/specs/{domain}/{prd-slug}/prd.md
+```
+
+**PO Spec repo:**
+```
+Next:
+  1. Fill .agent/project-context.yaml:
+     - domains: [list all business domains — these become @trace.domain values in PRDs]
+     - project.name, project.description
+  2. Fill specs/domain-knowledge/business-dictionary.md  ← canonical terms
+  3. Fill specs/domain-knowledge/core-entities.md        ← entity glossary
+  4. git add and commit those files
+  5. Install VS Code extension:
+     code --install-extension SpecDrivenDocsTools.spec-driven-docs-tool
+  6. /define-product to start your first feature
+
+⚠️  Dev team handoff reminder:
+  - Each PRD must have @trace.domain matching one of your domains list
+  - When dev team sets up their umbrella repo, they map these domain names
+    to service submodule paths in their project-context.yaml services section
+  - Share domain names with dev team before they configure their umbrellas
+```