bmad-plus 0.13.0 → 0.14.0

package/package.json

@@ -1,8 +1,9 @@
 {
   "$schema": "https://json.schemastore.org/package.json",
   "name": "bmad-plus",
-  "version": "0.13.0",
-  "description": "BMAD+ — Augmented AI-Driven Development Framework with multi-role agents, autopilot, and parallel execution",
+  "version": "0.14.0",
+  "description": "Project-local AI development workflows with clear roles, shared context, safe updates and coding-tool adapters",
+  "homepage": "https://bmad-plus.rochetta.fr",
   "keywords": [
     "bmad",
     "ai",
@@ -65,6 +66,10 @@
     "access": "public"
   },
   "jest": {
+    "testPathIgnorePatterns": [
+      "/node_modules/",
+      "/website/"
+    ],
     "collectCoverage": true,
     "coverageDirectory": "coverage",
     "moduleNameMapper": {

package/readme-international/README.de.md

@@ -1,6 +1,6 @@
 # 🚀 BMAD+ — Erweitertes Multi-Agent KI-Framework
 
-[![Version](https://img.shields.io/badge/version-0.13.0-blue.svg)](../CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.14.0-blue.svg)](../CHANGELOG.md)
 [![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
 [![License](https://img.shields.io/badge/license-MIT-yellow.svg)](../LICENSE)
 
@@ -15,7 +15,9 @@
 
 ## 📋 Inhaltsverzeichnis
 
-Repository-Prüfung: **709 JavaScript-Tests** (`npm test`). Die Deinstallation erhält den Projektspeicher und angepasste Dateien; für Installation oder Deinstallation ohne interaktives Terminal `--yes` verwenden.
+Repository-Prüfung: **980 JavaScript-Tests** (`npm test`). Die Deinstallation erhält den Projektspeicher und angepasste Dateien; für Installation oder Deinstallation ohne interaktives Terminal `--yes` verwenden.
+
+Version 0.14.0 vervollständigt die Dev-Studio-Workflows und ergänzt `bmad-plus studio list --json` sowie `bmad-plus studio prepare create-prd --request "Eine Offline-Aufgabenliste definieren" --json`. In einem Projekt mit installiertem Dev Studio lädt die Vorbereitung die tatsächlichen Anweisungen, Konfiguration und Eingaben für deinen KI-Assistenten; sie führt die Arbeit nicht aus. `doctor --json` prüft den installierten Ressourcengraphen. Siehe [Einstieg und Versionshinweise](https://bmad-plus.rochetta.fr/de/docs/).
 
 - [Warum BMAD+?](#-warum-bmad-)
 - [Schnellstart](#-schnellstart)
@@ -161,6 +163,7 @@ Nexus orchestriert alles automatisch mit Checkpoints für deine Genehmigung.
 | `npx bmad-plus memory status` | Statusbericht des Gedächtnisses (Projekt + globales Gehirn) |
 | `npx bmad-plus memory export` | Gehirn als portables Markdown-Archiv exportieren |
 | `npx bmad-plus doctor` | Installationsintegrität prüfen |
+| `node tools/cli/bmad-plus-cli.js doctor --json` | Quellrepository: schreibgeschützter Bericht über Inventar und Fähigkeiten (nächste Version) |
 | `npx bmad-plus update` | Agenten und Skills aktualisieren (Konfiguration bleibt erhalten) |
 | `npx bmad-plus uninstall` | BMAD+ vom aktuellen Projekt entfernen |
 | `npx bmad-plus autoconfig` | Intelligentes Bootstrap — Auto-Erkennung, Installation und Konfiguration |
@@ -169,12 +172,12 @@ Nexus orchestriert alles automatisch mit Checkpoints für deine Genehmigung.
 
 Die installierten Anweisungen bitten das LLM um eine Prüfung pro Sitzung. Das Ergebnis wird 24 Stunden zwischengespeichert; offline bleibt die veröffentlichte Version unbekannt. Automatische Updates erfordern eine ausdrückliche Richtlinie und unveränderte verwaltete Dateien.
 
-Für Installationen mit 0.12.2 oder älter einmal die neue CLI mit `npx --yes bmad-plus@0.13.0 update --yes` laden. Diese ausdrückliche Migration sichert vorhandene Dateien vor dem Ersetzen.
+Für Installationen mit 0.12.2 oder älter einmal die neue CLI mit `npx --yes bmad-plus@0.14.0 update --yes` laden. Diese ausdrückliche Migration sichert vorhandene Dateien vor dem Ersetzen.
 
 ```bash
 npx bmad-plus update-check --json
 npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.13.0"
+npx bmad-plus update-policy --mode auto --range "^0.14.0"
 npx bmad-plus update --latest --auto
 npx bmad-plus update-check --offline --json
 ```
@@ -443,7 +446,7 @@ Eine Projektidee eingeben → Nexus orchestriert die komplette Pipeline:
 **Konfigurierbare Checkpoints:**
 Konfiguriere `execution_mode` und `checkpoints` in `_bmad/config.yaml` (`discovery`, `architecture`, `story`, `delivery`).
 
-- `require_approval` (🔴) — Pause, WhatsApp-Benachrichtigung, warten
+- `require_approval` (🔴) — Kontrollpunkt in der Sitzung anzeigen und warten; externe Benachrichtigungen benötigen einen konfigurierten Kanal und eine Genehmigung.
 - `notify_only` (🟡) — Benachrichtigung, wird fortgesetzt, sofern nicht eingegriffen wird
 - `auto` (🟢) — Wird automatisch fortgesetzt
 
@@ -594,6 +597,7 @@ BMAD+/
 | **0.12.1** | 2026-07-12 | 🧩 **Portfolio-Brain** — memory-init Brain-Erkennung behoben, Monitor auf google-genai SDK migriert, Versions-Sync |
 | **0.12.2** | 2026-07-16 | 🚚 **Fähigkeiten ausgeliefert** — SEO-Toolkit in-pack ausgeliefert (funktioniert von npm), OSINT-Rechtsgrundlagen-Gate auf jedem Pfad, Monitor rebuildbar, Crawler-SSRF geschlossen, mcp-server + CLI Testabdeckung; 483 Tests |
 | **0.13.0** | 2026-09-08 | Kontrollierte Updates, geschützte Agenten, wiederherstellbare Sicherungen und Registry-basierte Installation; 709 Tests |
+| **0.14.0** | 2026-09-09 | Vollständige Dev-Studio-Workflows und Kontextvorbereitung, Diagnosen, synchronisierte npm-Dokumentation und mehrsprachige Website |
 
 Siehe [CHANGELOG.md](../CHANGELOG.md) für vollständige Details.
 

package/readme-international/README.es.md

@@ -1,6 +1,6 @@
 # 🚀 BMAD+ — Framework Multi-Agente IA Aumentado
 
-[![Version](https://img.shields.io/badge/version-0.13.0-blue.svg)](../CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.14.0-blue.svg)](../CHANGELOG.md)
 [![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
 [![License](https://img.shields.io/badge/license-MIT-yellow.svg)](../LICENSE)
 
@@ -15,7 +15,9 @@
 
 ## 📋 Tabla de contenidos
 
-Validación del repositorio: **709 tests JavaScript** (`npm test`). La desinstalación conserva la memoria del proyecto y los archivos personalizados; utiliza `--yes` para instalar o desinstalar sin un terminal interactivo.
+Validación del repositorio: **980 tests JavaScript** (`npm test`). La desinstalación conserva la memoria del proyecto y los archivos personalizados; utiliza `--yes` para instalar o desinstalar sin un terminal interactivo.
+
+La versión 0.14.0 repara la entrega completa de Dev Studio y añade `bmad-plus studio list --json` y `bmad-plus studio prepare create-prd --request "Definir una lista de tareas sin conexión" --json`. En un proyecto con Dev Studio instalado, la preparación carga instrucciones reales, configuración y entradas para tu asistente de IA; no ejecuta el trabajo. `doctor --json` verifica el grafo de recursos instalados. Consulta la [guía de inicio y las novedades](https://bmad-plus.rochetta.fr/es/docs/).
 
 - [¿Por qué BMAD+?](#-por-qué-bmad-)
 - [Inicio Rápido](#-inicio-rápido)
@@ -161,6 +163,7 @@ Nexus orquesta todo automáticamente con puntos de control (checkpoints) para tu
 | `npx bmad-plus memory status` | Informe de salud de memoria (proyecto + cerebro global) |
 | `npx bmad-plus memory export` | Exportar cerebro como archivo Markdown portable |
 | `npx bmad-plus doctor` | Verificar integridad de la instalación |
+| `node tools/cli/bmad-plus-cli.js doctor --json` | Repositorio fuente: informe de inventario y capacidades de solo lectura (próxima versión) |
 | `npx bmad-plus update` | Actualizar agentes y skills (preserva la config) |
 | `npx bmad-plus uninstall` | Eliminar BMAD+ del proyecto actual |
 | `npx bmad-plus autoconfig` | Bootstrap inteligente — detección auto, instalación y configuración |
@@ -169,12 +172,12 @@ Nexus orquesta todo automáticamente con puntos de control (checkpoints) para tu
 
 Las instrucciones instaladas piden al LLM una comprobación por sesión. El resultado se conserva durante 24 horas; sin conexión, la versión publicada permanece desconocida. Las actualizaciones automáticas requieren una política explícita y archivos administrados sin cambios locales.
 
-Para instalaciones con 0.12.2 o anterior, carga una vez el nuevo CLI con `npx --yes bmad-plus@0.13.0 update --yes`. Esta migración explícita guarda copias de seguridad antes de reemplazar los archivos antiguos.
+Para instalaciones con 0.12.2 o anterior, carga una vez el nuevo CLI con `npx --yes bmad-plus@0.14.0 update --yes`. Esta migración explícita guarda copias de seguridad antes de reemplazar los archivos antiguos.
 
 ```bash
 npx bmad-plus update-check --json
 npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.13.0"
+npx bmad-plus update-policy --mode auto --range "^0.14.0"
 npx bmad-plus update --latest --auto
 npx bmad-plus update-check --offline --json
 ```
@@ -447,7 +450,7 @@ Introduce una idea → Nexus gestionará todo:
 **Puntos de control (checkpoints) configurables:**
 Configura `execution_mode` y `checkpoints` en `_bmad/config.yaml` (`discovery`, `architecture`, `story`, `delivery`).
 
-- `require_approval` (🔴) — Pausa, notifica por WhatsApp, espera
+- `require_approval` (🔴) — Mostrar el punto de control en la sesión y esperar; las notificaciones externas requieren un canal configurado y autorización.
 - `notify_only` (🟡) — Notifica, continúa (a menos que el usuario intervenga)
 - `auto` (🟢) — Totalmente automático
 
@@ -609,6 +612,7 @@ BMAD+/
 | **0.12.1** | 2026-07-12 | 🧩 **Cerebro portfolio** — fix de detección de cerebro memory-init, monitor migrado al SDK google-genai, sincronización de versión |
 | **0.12.2** | 2026-07-16 | 🚚 **Capacidades entregadas** — toolkit SEO embarcado in-pack (funciona desde npm), gate de base legal OSINT en cada ruta, monitor reconstruible, SSRF del crawler cerrado, cobertura de tests mcp-server + CLI; 483 tests |
 | **0.13.0** | 2026-09-08 | Actualizaciones controladas, agentes protegidos, copias restaurables e instalación derivada del registro; 709 tests |
+| **0.14.0** | 2026-09-09 | Flujos completos de Dev Studio y preparación del contexto, diagnósticos, documentación npm y web multilingüe sincronizadas |
 
 Más descripciones a fondo en el archivo: [CHANGELOG.md](../CHANGELOG.md).
 

package/readme-international/README.fr.md

@@ -1,6 +1,6 @@
 # 🚀 BMAD+ — Framework Multi-Agent IA Augmenté
 
-[![Version](https://img.shields.io/badge/version-0.13.0-blue.svg)](../CHANGELOG.md)
+[![Version](https://img.shields.io/badge/version-0.14.0-blue.svg)](../CHANGELOG.md)
 [![Based on](https://img.shields.io/badge/based%20on-BMAD--METHOD-green.svg)](https://github.com/bmad-code-org/BMAD-METHOD)
 [![License](https://img.shields.io/badge/license-MIT-yellow.svg)](../LICENSE)
 
@@ -15,7 +15,9 @@
 
 ## 📋 Table des matières
 
-Validation du dépôt : **709 tests JavaScript** (`npm test`). La désinstallation conserve la mémoire du projet et les fichiers personnalisés ; utilisez `--yes` pour installer ou désinstaller sans terminal interactif.
+Validation du dépôt : **980 tests JavaScript** (`npm test`). La désinstallation conserve la mémoire du projet et les fichiers personnalisés ; utilisez `--yes` pour installer ou désinstaller sans terminal interactif.
+
+La version 0.14.0 répare la livraison complète de Dev Studio et ajoute `bmad-plus studio list --json` et `bmad-plus studio prepare create-prd --request "Définir une liste de tâches hors ligne" --json`. Dans un projet où Dev Studio est installé, la préparation charge les instructions réelles, la configuration et les entrées pour votre assistant IA ; elle n’exécute pas le travail. `doctor --json` vérifie le graphe des ressources installées. Consultez le [guide de démarrage et les nouveautés](https://bmad-plus.rochetta.fr/fr/docs/).
 
 - [Pourquoi BMAD+ ?](#-pourquoi-bmad-)
 - [Quick Start](#-quick-start)
@@ -161,6 +163,7 @@ Nexus orchestre tout automatiquement avec des checkpoints pour ton approbation.
 | `npx bmad-plus memory status` | Rapport de santé mémoire (projet + cerveau global) |
 | `npx bmad-plus memory export` | Export du cerveau en archive Markdown portable |
 | `npx bmad-plus doctor` | Vérifier l'intégrité de l'installation |
+| `node tools/cli/bmad-plus-cli.js doctor --json` | Dépôt source : rapport en lecture seule sur l'inventaire et les capacités (prochaine version) |
 | `npx bmad-plus update` | Mettre à jour agents et skills (préserve la config) |
 | `npx bmad-plus uninstall` | Supprimer BMAD+ du projet actuel |
 | `npx bmad-plus autoconfig` | Bootstrap intelligent — détection auto, installation et configuration |
@@ -169,12 +172,12 @@ Nexus orchestre tout automatiquement avec des checkpoints pour ton approbation.
 
 Les instructions installées demandent au LLM une vérification par session. Le résultat est conservé 24 heures ; hors connexion, la version publiée reste inconnue. Les mises à jour automatiques exigent une politique explicite et des fichiers gérés sans modification locale.
 
-Pour les installations en 0.12.2 ou antérieures, chargez une fois le nouveau CLI avec `npx --yes bmad-plus@0.13.0 update --yes`. Cette migration explicite sauvegarde les anciens fichiers avant leur remplacement.
+Pour les installations en 0.12.2 ou antérieures, chargez une fois le nouveau CLI avec `npx --yes bmad-plus@0.14.0 update --yes`. Cette migration explicite sauvegarde les anciens fichiers avant leur remplacement.
 
 ```bash
 npx bmad-plus update-check --json
 npx bmad-plus update --latest --yes
-npx bmad-plus update-policy --mode auto --range "^0.13.0"
+npx bmad-plus update-policy --mode auto --range "^0.14.0"
 npx bmad-plus update --latest --auto
 npx bmad-plus update-check --offline --json
 ```
@@ -447,7 +450,7 @@ Donnez une idée projet → Nexus orchestre le pipeline complet :
 **Checkpoints configurables :**
 Configurez `execution_mode` et `checkpoints` dans `_bmad/config.yaml` (`discovery`, `architecture`, `story`, `delivery`).
 
-- `require_approval` (🔴) — Pause, notification WhatsApp, attente
+- `require_approval` (🔴) — Présenter le point de contrôle dans la session et attendre ; les notifications externes nécessitent un canal configuré et une autorisation.
 - `notify_only` (🟡) — Notification, continue sauf intervention
 - `auto` (🟢) — Continue automatiquement
 
@@ -609,6 +612,7 @@ BMAD+/
 | **0.12.1** | 2026-07-12 | 🧩 **Cerveau portfolio** — fix détection de cerveau memory-init, monitor migré vers le SDK google-genai, sync version |
 | **0.12.2** | 2026-07-16 | 🚚 **Capacités livrées** — toolkit SEO embarqué in-pack (fonctionne depuis npm), gate base légale OSINT sur tout chemin, monitor reconstructible, SSRF crawler fermé, couverture de tests mcp-server + CLI ; 483 tests |
 | **0.13.0** | 2026-09-08 | Mises à jour contrôlées, agents protégés, sauvegardes restaurables et installation issue du registre ; 709 tests |
+| **0.14.0** | 2026-09-09 | Workflows Dev Studio complets et préparation du contexte, diagnostics, documentation npm et landing multilingue synchronisées |
 
 Voir [CHANGELOG.md](../CHANGELOG.md) pour le détail complet.
 

package/src/bmad-plus/agents/agent-orchestrator/SKILL.md

@@ -68,8 +68,8 @@ Focuses on: end-to-end pipeline management, agent sequencing, checkpoint managem
 Read `execution_mode` and `checkpoints` from `_bmad/config.yaml` before starting the pipeline. The checkpoint keys are `discovery`, `architecture`, `story`, and `delivery`.
 
 **Checkpoint behavior** (configurable):
-- `require_approval` (🔴 STOP): Pause and wait for user input. Notify via WhatsApp if configured.
-- `notify_only` (🟡 INFO): Send notification, continue unless user intervenes within timeout.
+- `require_approval` (🔴 STOP): Present the checkpoint in the session and wait for user input. If an external channel is configured and sending is authorized, also notify through it.
+- `notify_only` (🟡 INFO): Report progress in the session and continue. If an external channel is configured and sending is authorized, also notify through it.
 - `auto` (🟢 AUTO): Continue automatically. Log for audit trail.
 
 > 💡 **Auto-activates** when: keywords like "autopilot", "gère tout", "lance le projet", "full pipeline" are detected, or when `{execution_mode}` is set to "autopilot".
@@ -93,7 +93,7 @@ Focuses on: detecting parallelizable tasks, launching agents in parallel, confli
 - **Stop**: Detect conflicts (shared file edits) → pause conflicting agent
 - **Restart**: After conflict resolution → restart with merged context
 - **Reallocate**: Agent finishes early → assign next available task
-- **Escalate**: 3 consecutive failures → notify human via WhatsApp
+- **Escalate**: 3 consecutive failures → report the failure and evidence in the session. If an external channel is configured and sending is authorized, also notify through it.
 
 > 💡 **Auto-activates** when: multiple independent stories are queued, or when `{parallel_execution}` is enabled and batch work is detected.
 

package/src/bmad-plus/packs/pack-dev-studio/README.md

@@ -1,162 +1,154 @@
-# 🏗️ Pack Dev Studio — BMAD+
+# Dev Studio for BMAD+
 
-> Full Software Development Lifecycle powered by 6 specialized AI agents
+Dev Studio provides six specialist personas and 38 workflows for product
+discovery, planning, architecture, implementation and review. The current coding
+assistant executes the Markdown instructions with its available tools. The CLI
+can prepare their context; it does not run an autonomous development team.
 
-**Source:** Adapted from [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) v6.6.0 (47K+ ⭐)
-**Format:** BWML (BMAD+ Workflow Markup Language)
-**License:** MIT
+The public workflow IDs and persona names remain stable. The execution
+instructions are original BMAD+ adaptations. The declared BMAD-METHOD baseline
+remains v6.6.0; reviewing newer upstream ideas is separate from claiming that the
+whole upstream release has been integrated.
 
----
+## Start
 
-## Overview
+Install the pack into the intended project with the BMAD+ installer:
 
-Pack Dev Studio transforms your AI IDE into a complete software engineering team. Six specialized agents guide you through the entire development lifecycle — from brainstorming to deployment — with structured workflows, validation gates, and anti-regression guards.
-
-Unlike generic AI assistants, each agent embodies deep domain expertise with a distinct voice, methodology, and perspective, drawing on historical figures whose characteristics mirror their roles.
-
-## Agents
-
-### 📊 Miriam (מרים) — Business Analyst
-*"Like the prophetess who watched over Moses, Miriam observes patterns others miss"*
-
-Strategic analysis, market research, competitive landscape, requirements elicitation, product briefs, PRFAQ challenges. Channels Porter's strategic rigor and Minto's Pyramid Principle.
-
-### 📚 Huldah (חולדה) — Technical Writer
-*"As Huldah authenticated the Book of the Law, she authenticates your documentation"*
-
-Documentation mastery, CommonMark, DITA, OpenAPI, Mermaid diagrams, editorial review. Turns complex concepts into accessible structured docs.
-
-### 📋 Yosef (יוסף) — Product Manager
-*"Like Joseph interpreting Pharaoh's dreams, Yosef interprets user needs into actionable specs"*
-
-PRD creation/validation, feature prioritization, Jobs-to-be-Done methodology, user value first. Every "why?" tightens the net.
-
-### 🎨 Rachel (רחל) — UX Designer
-*"Rachel's empathy and devotion mirror the UX designer's commitment to the user"*
+```sh
+npx bmad-plus install --packs core,dev-studio
+```
 
-User experience design, wireframes, user flows, accessibility, empathy mapping, edge-case rigor. Paints user stories that make you feel the problem.
+Then ask the coding assistant directly:
 
-### 🏗️ Bezalel (בצלאל) — System Architect
-*"The master architect of the Tabernacle, filled with divine wisdom for design"*
+> Miriam, use product-brief to define a small issue triage tool for our support team.
 
-Architecture decisions, system design, tech stack selection, ADRs, boring technology philosophy. Measures trade-offs, not verdicts.
+> Oholiab, use investigate to reproduce the failing import described in docs/issue.md.
 
-### 💻 Oholiab (אהליאב) — Senior Engineer
-*"Bezalel's master craftsman partner — precision in every implementation"*
+The assistant reads the [pack skill](SKILL.md),
+[execution guide](shared/execution.md), selected persona and workflow. A request
+for a narrow fix does not require a complete discovery-to-sprint pipeline.
 
-TDD red-green-refactor, story implementation, code review, sprint management. Terminal-prompt precision, AC-first delivery.
+With the CLI available in the project, inspect or prepare a route:
 
-## Development Lifecycle
+```sh
+npx --no-install bmad-plus studio list --json
+npx --no-install bmad-plus studio prepare product-brief --directory . --request "Define the smallest useful issue triage tool" --json
+npx --no-install bmad-plus studio prepare validate-prd --directory . --input docs/prd.md --json
+```
 
+Use `bmad-plus` directly when it is available on your PATH. Input files must exist
+inside the selected project. Repeat `--input` to supply several explicit artifacts.
+An artifact workflow needs at least one file; request and project workflows need
+a request or a file. Missing context returns `needs-input`.
+
+Preparation is read-only. It resolves configuration, loads actual shipped
+instructions and selected input files, records their hashes and proposes a report
+path. It does not inspect an entire project, write the deliverable, run tests or
+certify that a model followed the workflow. Give the prepared contents to the
+assistant and have it perform the selected procedure.
+
+## Personas
+
+| Persona | Role | Instructions |
+| --- | --- | --- |
+| Miriam | Business analysis and research | [Analyst](categories/analysis/analyst-agent.md) |
+| Huldah | Technical documentation | [Technical writer](categories/analysis/tech-writer-agent.md) |
+| Yosef | Product requirements and priorities | [Product manager](categories/planning/pm-agent.md) |
+| Rachel | User experience and interaction | [UX designer](categories/planning/ux-designer-agent.md) |
+| Bezalel | System architecture and technical decisions | [Architect](categories/architecture/architect-agent.md) |
+| Oholiab | Implementation, debugging and verification | [Engineer](categories/implementation/dev-agent.md) |
+
+Core personas can coexist with Dev Studio. Choose the role needed for the task;
+the persona name describes instructions, not a separate running process.
+
+## Workflow catalog
+
+The [machine-readable catalog](shared/catalog.json) contains the routes and
+required resources. The [CSV index](shared/module-help.csv) provides a compact
+navigation view. Workflow IDs in text are routing suggestions, not automatic
+triggers or mandatory dependencies.
+
+| Category | Workflow | Expected result |
+| --- | --- | --- |
+| Analysis | [product-brief](categories/analysis/product-brief.md) | Product problem, audience and first useful scope |
+| Analysis | [prfaq](categories/analysis/prfaq.md) | Proposed launch narrative and questions that challenge it |
+| Analysis | [document-project](categories/analysis/document-project.md) | Documentation grounded in inspected project files |
+| Analysis | [market-research](categories/analysis/market-research.md) | Sourced market and alternative analysis |
+| Analysis | [domain-research](categories/analysis/domain-research.md) | Domain concepts, constraints and evidence gaps |
+| Analysis | [technical-research](categories/analysis/technical-research.md) | Feasibility options and a concrete next check |
+| Planning | [create-prd](categories/planning/create-prd.md) | Testable requirements and scope |
+| Planning | [prd](categories/planning/prd.md) | Selection of PRD creation, edit or validation |
+| Planning | [edit-prd](categories/planning/edit-prd.md) | Traceable requirements changes |
+| Planning | [validate-prd](categories/planning/validate-prd.md) | Evidence-based requirements findings |
+| Planning | [create-ux-design](categories/planning/create-ux-design.md) | User flows, interaction states and acceptance checks |
+| Architecture | [create-architecture](categories/architecture/create-architecture.md) | Technical decisions, boundaries and tradeoffs |
+| Architecture | [create-epics-stories](categories/architecture/create-epics-stories.md) | Deliverable increments and implementable stories |
+| Architecture | [implementation-readiness](categories/architecture/implementation-readiness.md) | Alignment gaps and readiness evidence |
+| Architecture | [generate-project-context](categories/architecture/generate-project-context.md) | Current project constraints with provenance |
+| Implementation | [sprint-planning](categories/implementation/sprint-planning.md) | Scoped work, dependencies and capacity assumptions |
+| Implementation | [create-story](categories/implementation/create-story.md) | A story with context and acceptance criteria |
+| Implementation | [dev-story](categories/implementation/dev-story.md) | Implementation and verification against a story |
+| Implementation | [code-review](categories/implementation/code-review.md) | Substantiated findings or a scoped zero-finding report |
+| Implementation | [quick-dev](categories/implementation/quick-dev.md) | A bounded change with proportionate checks |
+| Implementation | [sprint-status](categories/implementation/sprint-status.md) | Progress and blockers supported by current evidence |
+| Implementation | [retrospective](categories/implementation/retrospective.md) | Lessons and actionable process changes |
+| Implementation | [correct-course](categories/implementation/correct-course.md) | A reasoned response to a material change |
+| Implementation | [investigate](categories/implementation/investigate.md) | Hypotheses, reproduction evidence and next action |
+| Implementation | [checkpoint-preview](categories/implementation/checkpoint-preview.md) | A reviewable explanation of a change |
+| Implementation | [qa-e2e-tests](categories/implementation/qa-e2e-tests.md) | Relevant automated checks and actual run evidence |
+| Utilities | [distillator](categories/utilities/distillator.md) | A compact brief with sources and disclosed omissions |
+| Utilities | [party-mode](categories/utilities/party-mode.md) | Compared perspectives and a decision record |
+| Utilities | [brainstorming](categories/utilities/brainstorming.md) | Distinct options and a small experiment |
+| Utilities | [adversarial-review](categories/utilities/adversarial-review.md) | Supported objections, refutations and open questions |
+| Utilities | [edge-case-hunter](categories/utilities/edge-case-hunter.md) | Concrete boundary and failure scenarios |
+| Utilities | [editorial-review-prose](categories/utilities/editorial-review-prose.md) | Precise wording improvements |
+| Utilities | [editorial-review-structure](categories/utilities/editorial-review-structure.md) | A reader-oriented outline and section mapping |
+| Utilities | [advanced-elicitation](categories/utilities/advanced-elicitation.md) | Resolved uncertainties and testable requirements |
+| Utilities | [shard-doc](categories/utilities/shard-doc.md) | Linked sections with source coverage checks |
+| Utilities | [index-docs](categories/utilities/index-docs.md) | An index of inspected documents |
+| Utilities | [bmad-help](categories/utilities/bmad-help.md) | Relevant routes and a justified next step |
+| Utilities | [customize](categories/utilities/customize.md) | Verified configuration or explicit instruction changes |
+
+## Configuration and reports
+
+Configuration comes from `_bmad/config.yaml` in the selected project:
+
+```yaml
+user_name: user
+communication_language: English
+document_output_language: English
+output_folder: _bmad-output
+project_name: Example project
 ```
-Phase 1 — Analysis
-  Miriam → Brainstorm → Product Brief / PRFAQ
-  Huldah → Document existing project
 
-Phase 2 — Planning
-  Yosef  → PRD (create, edit, validate)
-  Rachel → UX Design (wireframes, user flows)
+Each missing value uses the displayed default, except `project_name`, which
+defaults to the selected directory's name. A missing file is valid. A malformed
+present file or an invalid known field is an error. Preserve unrelated settings
+when customizing. The current user request and applicable host/project instructions
+take precedence over conversation and document language preferences.
 
-Phase 3 — Architecture
-  Bezalel → Architecture → Epics & Stories → Readiness Check
+Reports default to `_bmad-output/dev-studio/WORKFLOW_ID.md`, adjusted for the
+configured output folder. Code changes stay in the actual project. Reports record
+scope, inputs, decisions, completed work, checks, unresolved questions and the next
+action. On resume, read the previous report and revalidate changed inputs. A report
+does not authorize overwriting user changes or repeating publication.
 
-Phase 4 — Implementation
-  Oholiab → Sprint Planning → [Create Story → Dev Story → Code Review] → Retrospective
+## Execution limits and migration
 
-Cross-cutting — Utilities
-  Distillator, Party Mode, Adversarial Reviews, Editorial Reviews
-```
+There is no BWML interpreter or TOML customization resolver in this pack. See the
+[BWML migration note](shared/bwml-spec.md) for the supported replacement behavior.
+Independent agent execution, browsing and command execution depend on the host.
+When one assistant explores several perspectives, it must say so. Unavailable
+checks and missing reviews remain visible.
 
-## Workflows (30+)
-
-### Analysis (8 skills)
-| Skill | Description |
-|-------|-------------|
-| `analyst-agent` | Miriam — full business analyst persona |
-| `tech-writer-agent` | Huldah — technical documentation expert |
-| `product-brief` | Guided product brief creation |
-| `prfaq` | Amazon Working Backwards PRFAQ challenge |
-| `document-project` | Analyze existing project for documentation |
-| `market-research` | Market analysis and competitive landscape |
-| `domain-research` | Industry domain deep dive |
-| `technical-research` | Technical feasibility assessment |
-
-### Planning (7 skills)
-| Skill | Description |
-|-------|-------------|
-| `pm-agent` | Yosef — product manager persona |
-| `ux-designer-agent` | Rachel — UX designer persona |
-| `create-prd` | PRD creation via coached discovery |
-| `prd` | Full PRD workflow (create/edit/validate) |
-| `edit-prd` | Update existing PRD |
-| `validate-prd` | PRD validation checklist |
-| `create-ux-design` | Guided UX design workflow |
-
-### Architecture (5 skills + 9 step files)
-| Skill | Description |
-|-------|-------------|
-| `architect-agent` | Bezalel — system architect persona |
-| `create-architecture` | 8-step architecture design workflow |
-| `create-epics-stories` | Break architecture into implementable units |
-| `implementation-readiness` | Pre-coding alignment check |
-| `generate-project-context` | LLM-optimized project context generation |
-
-### Implementation (12 skills)
-| Skill | Description |
-|-------|-------------|
-| `dev-agent` | Oholiab — senior engineer persona |
-| `sprint-planning` | Sprint plan from epics |
-| `create-story` | Prepare story with full context |
-| `dev-story` | Full TDD implementation cycle (486 lines!) |
-| `code-review` | Senior developer code review |
-| `quick-dev` | Fast track: intent → code |
-| `sprint-status` | Sprint progress report |
-| `retrospective` | Epic completion review |
-| `correct-course` | Navigate major changes |
-| `investigate` | Forensic issue investigation |
-| `checkpoint-preview` | Guided commit/PR walkthrough |
-| `qa-e2e-tests` | Automated test generation |
-
-### Utilities (12 skills)
-| Skill | Description |
-|-------|-------------|
-| `distillator` | Lossless document compression for LLM |
-| `party-mode` | Multi-agent roundtable discussion |
-| `brainstorming` | Expert-guided brainstorming facilitation |
-| `adversarial-review` | Adversarial document critique |
-| `edge-case-hunter` | Find edge cases and failure modes |
-| `editorial-review-prose` | Prose quality review |
-| `editorial-review-structure` | Document structure review |
-| `advanced-elicitation` | Deep requirement extraction |
-| `shard-doc` | Intelligent document splitting |
-| `index-docs` | Documentation index creation |
-| `bmad-help` | Contextual "what's next?" guidance |
-| `customize` | Agent customization guide |
-
-## BWML — Our Workflow DSL
-
-Pack Dev Studio uses **BWML** (BMAD+ Workflow Markup Language), a proprietary DSL that extends XML-based workflows with 12 new primitives. See `shared/bwml-spec.md` for the full specification.
-
-## File Structure
-
-```
-pack-dev-studio/
-├── dev-studio-orchestrator.md     ← Entry point
-├── upstream-sync.yaml             ← BMAD-METHOD v6.6.0 tracking
-├── README.md                      ← This file
-├── categories/
-│   ├── analysis/        (8 skills)
-│   ├── planning/        (7 skills)
-│   ├── architecture/    (5 skills + 9 steps)
-│   ├── implementation/  (12 skills + 4 code-review steps + checklist)
-│   └── utilities/       (12 skills)
-└── shared/
-    ├── bwml-spec.md                ← BWML DSL specification
-    ├── module-help.csv             ← Navigation catalog
-    └── architecture-decision-template.md
-```
+Research requires accessible sources to support current factual claims. A static
+resource check establishes that instructions were delivered; actual execution and
+model behavior need separate evidence. No workflow guarantees defect-free code or
+lossless summarization.
 
 ## Attribution
 
-Adapted from [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD) v6.6.0 by BMad Code, LLC (MIT License).
-Enhanced with BWML workflow language and specialized personas by [Laurent Rochetta](https://github.com/lrochetta/BMAD-PLUS).
+BMAD+ is maintained by Laurent Rochetta. Dev Studio's retained names and workflow
+lineage acknowledge [BMAD-METHOD](https://github.com/bmad-code-org/BMAD-METHOD)
+by BMad Code, LLC, under the MIT License. The current delivery and execution
+instructions are written for BMAD+; no upstream runtime is bundled by implication.

package/src/bmad-plus/packs/pack-dev-studio/SKILL.md

@@ -0,0 +1,49 @@
+---
+name: dev-studio
+description: Use six specialist personas and 38 Dev Studio workflows to carry out product, architecture, documentation and implementation tasks.
+---
+
+# Dev Studio
+
+Use this pack when the user requests a Dev Studio persona, a named workflow or a
+software task that benefits from its specific procedure. Read the
+[execution guide](shared/execution.md) before acting. The
+[catalog](shared/catalog.json) provides the actual agents, aliases, workflow paths,
+input kinds and required resources.
+
+## Activate
+
+1. Start from the user's actual objective and current authorization. Read relevant
+   project instructions and previous decisions. Keep the user's current language
+   preference; configuration supplies defaults when no preference is stated.
+2. Resolve the named persona or workflow through the catalog. For an unqualified
+   task use the [orchestrator](dev-studio-orchestrator.md) to choose the smallest
+   useful route. Use bmad-help for a roster or a next-step recommendation.
+3. Read the selected workflow, its persona and declared resources. Check the
+   inputs against the content actually supplied. A filename alone is not evidence
+   of a complete brief, a valid PRD or a reproduced defect.
+4. Execute the workflow's procedure with real host tools. Record actual outcomes
+   and unavailable checks. Independent agents require host support; sequential
+   perspectives by one assistant must be labeled accurately.
+5. Deliver the requested artifact with verification evidence and remaining work.
+   Preserve existing reports and user changes. On resume, compare input hashes
+   and project state, invalidate affected decisions and continue incomplete work.
+
+## Optional context preparation
+
+With the CLI already available, use:
+
+```sh
+npx --no-install bmad-plus studio list --json
+npx --no-install bmad-plus studio prepare product-brief --directory . --request "Define a small issue triage tool" --json
+```
+
+For artifact workflows, provide an existing project-relative file through
+`--input`; repeat the flag for additional artifacts. The CLI reports missing
+inputs and returns a read-only bundle with actual text, hashes, resolved
+configuration and a proposed report path. It neither executes the workflow nor
+certifies model behavior. The host must still perform the work.
+
+See the [README](README.md) for all 38 routes and configuration examples.
+The [BWML migration note](shared/bwml-spec.md) explains the replacement for earlier
+XML and TOML assumptions.