create-sdd-project 0.11.1 → 0.12.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (4) hide show
  1. package/README.md +9 -7
  2. package/package.json +1 -1
  3. package/template/.claude/skills/development-workflow/SKILL.md +3 -2
  4. package/template/.gemini/skills/development-workflow/SKILL.md +3 -2
package/README.md CHANGED
@@ -307,23 +307,25 @@ SDD DevFlow combines three proven practices:
307
307
 
308
308
  | Command | What it does |
309
309
  |---------|-------------|
310
- | `/review-spec` | Reviews feature specs using external AI models before planning — catches requirement gaps, ambiguity, and architectural inconsistencies |
311
- | `/review-plan` | Sends Implementation Plan to external AI models (Codex CLI, Gemini CLI) for independent critique |
310
+ | `/review-spec` | Cross-model spec review — runs automatically after self-review when external CLIs are available; catches requirement gaps, ambiguity, and architectural inconsistencies |
311
+ | `/review-plan` | Cross-model plan review — runs automatically after plan self-review when external CLIs are available; catches implementation blind spots |
312
312
  | `/context-prompt` | Generates a context recovery prompt after `/compact` with Workflow Recovery to prevent checkpoint skipping |
313
313
  | `/review-project` | Comprehensive project-level review using up to 3 AI models in parallel — 6 domains, audit context, consolidated report with action plan |
314
314
 
315
315
  ### Spec & Plan Quality
316
316
 
317
- Every Standard/Complex feature spec goes through a **built-in self-review** (Step 0.4) where the agent critically re-reads its own spec checking for completeness, edge cases, API contract clarity, and architectural consistency. For additional confidence, the optional `/review-spec` command sends the spec plus project context (`key_facts.md`, `decisions.md`) to external AI models for independent critique — catching requirement-level blind spots before any planning begins.
317
+ Every Standard/Complex feature spec goes through a **built-in self-review** (Step 0.4) where the agent critically re-reads its own spec checking for completeness, edge cases, API contract clarity, and architectural consistency. Then `/review-spec` **automatically** sends the spec plus project context (`key_facts.md`, `decisions.md`) to external AI models for independent critique — catching requirement-level blind spots before any planning begins.
318
318
 
319
- Every plan then goes through its own **built-in self-review** (Step 2.4) followed by the optional `/review-plan` command for external critique — catching implementation-level blind spots that same-model review misses.
319
+ Every plan then goes through its own **built-in self-review** (Step 2.4) followed by **automatic** `/review-plan` for external critique — catching implementation-level blind spots that same-model review misses.
320
+
321
+ Cross-model reviews only trigger when at least one external CLI is available (Gemini CLI, Codex CLI). If no CLIs are detected, the step is skipped — the self-review is sufficient.
320
322
 
321
323
  ### Workflow (Steps 0–6)
322
324
 
323
325
  ```
324
- 0. SPEC → spec-creator drafts + self-review → Spec Approval
325
- 1. SETUP → Branch, ticket, product tracker → Ticket Approval
326
- 2. PLAN → Planner creates plan + self-review → Plan Approval
326
+ 0. SPEC → spec-creator drafts + self-review + cross-model review → Spec Approval
327
+ 1. SETUP → Branch, ticket, product tracker → Ticket Approval
328
+ 2. PLAN → Planner creates plan + self-review + cross-model review → Plan Approval
327
329
  3. IMPLEMENT → Developer agent, TDD
328
330
  4. FINALIZE → Tests/lint/build, validator → Commit Approval
329
331
  5. REVIEW → PR, code review, QA → Merge Approval
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "create-sdd-project",
3
- "version": "0.11.1",
3
+ "version": "0.12.0",
4
4
  "description": "Create a new SDD DevFlow project with AI-assisted development workflow",
5
5
  "bin": {
6
6
  "create-sdd-project": "bin/cli.js"
package/template/.claude/skills/development-workflow/SKILL.md CHANGED
@@ -71,7 +71,7 @@ Ask user to classify complexity before starting. See `references/complexity-guid
71
71
  2. Agent updates global spec files (`api-spec.yaml`, `ui-components.md`) and Zod schemas in `shared/src/schemas/` if applicable
72
72
  3. Agent writes spec summary into the ticket's `## Spec` section
73
73
  4. **Spec Self-Review:** Re-read the spec critically. Are requirements complete? Edge cases covered? API contract well-defined? Acceptance criteria testable? Does the spec conflict with existing architecture (`key_facts.md`, `decisions.md`)? Update the spec with any fixes found before proceeding.
74
- 5. **Optional:** Run `/review-spec` for external model review (recommended for Standard/Complex)
74
+ 5. **Cross-Model Spec Review:** Run `/review-spec`. If at least one external CLI is available (`gemini`, `codex`), this provides independent validation from other models. If no external CLIs are detected, skip this step (the self-review above is sufficient).
75
75
 
76
76
  **→ CHECKPOINT: Spec Approval** — Update tracker (Active Session + Features table): step `0/6 (Spec)`
77
77
 
@@ -108,7 +108,8 @@ See `references/branching-strategy.md` for details.
108
108
  - Dependencies between steps that force a different order?
109
109
  - Over-engineering or unnecessary abstractions?
110
110
  Update the plan with any fixes found before proceeding.
111
- 5. Update tracker: step `2/6 (Plan)` (Active Session + Features table)
111
+ 5. **Cross-Model Plan Review:** Run `/review-plan`. If at least one external CLI is available (`gemini`, `codex`), this provides independent validation from other models. If no external CLIs are detected, skip this step (the self-review above is sufficient).
112
+ 6. Update tracker: step `2/6 (Plan)` (Active Session + Features table)
112
113
 
113
114
  **→ CHECKPOINT: Plan Approval**
114
115
 
package/template/.gemini/skills/development-workflow/SKILL.md CHANGED
@@ -71,7 +71,7 @@ Ask user to classify complexity before starting. See `references/complexity-guid
71
71
  2. Update global spec files (`api-spec.yaml`, `ui-components.md`) and Zod schemas in `shared/src/schemas/` if applicable
72
72
  3. Write spec summary into the ticket's `## Spec` section
73
73
  4. **Spec Self-Review:** Re-read the spec critically. Are requirements complete? Edge cases covered? API contract well-defined? Acceptance criteria testable? Does the spec conflict with existing architecture (`key_facts.md`, `decisions.md`)? Update the spec with any fixes found before proceeding.
74
- 5. **Optional:** Run `/review-spec` for external model review (recommended for Standard/Complex)
74
+ 5. **Cross-Model Spec Review:** Run `/review-spec`. If at least one external CLI is available (`claude`, `codex`), this provides independent validation from other models. If no external CLIs are detected, skip this step (the self-review above is sufficient).
75
75
 
76
76
  **→ CHECKPOINT: Spec Approval** — Update tracker (Active Session + Features table): step `0/6 (Spec)`
77
77
 
@@ -108,7 +108,8 @@ See `references/branching-strategy.md` for details.
108
108
  - Dependencies between steps that force a different order?
109
109
  - Over-engineering or unnecessary abstractions?
110
110
  Update the plan with any fixes found before proceeding.
111
- 5. Update tracker: step `2/6 (Plan)` (Active Session + Features table)
111
+ 5. **Cross-Model Plan Review:** Run `/review-plan`. If at least one external CLI is available (`claude`, `codex`), this provides independent validation from other models. If no external CLIs are detected, skip this step (the self-review above is sufficient).
112
+ 6. Update tracker: step `2/6 (Plan)` (Active Session + Features table)
112
113
 
113
114
  **→ CHECKPOINT: Plan Approval**
114
115