siesa-agents 2.1.78 → 2.1.79

package/claude/commands/sa-quick-dev.md

@@ -1,27 +1,51 @@
 ---
-description: 'Pipeline secuencial de sub-agentes por épica: crea, desarrolla y revisa TODAS las historias de una épica usando sub-agentes aislados.'
+description: 'Pipeline secuencial de sub-agentes por épica: crea, desarrolla y revisa TODAS las historias de una o varias épicas usando sub-agentes aislados con integración TEA completa (ATDD + Automate + Review + Test Design + Trace). Acepta una épica individual (ej: 3) o un rango (ej: 1-4).'
 ---
 
-## PASO 0 — Identificar la épica
+## PASO 0 — Identificar las épicas a procesar
 
-### 0.1 — Obtener el número de épica
+### 0.1 — Parsear $ARGUMENTS y construir la lista de épicas
 
-Si el usuario no proporcionó el número de épica en `$ARGUMENTS`, pregúntale directamente:
+Lee `$ARGUMENTS` y determina el modo:
 
+- **Sin argumentos**: pregunta al usuario:
+  ```
+  ¿Qué épica(s) deseas procesar? Puedes ingresar una épica (ej: 3) o un rango (ej: 1-4)
+  ```
+  **ESPERA** la respuesta antes de continuar.
+
+- **Número simple** (ej: `3`): lista de épicas = `[3]`
+
+- **Rango** (ej: `1-4`): expande el rango inclusive. Ejemplo: `1-4` → `[1, 2, 3, 4]`
+
+Guarda esta lista como `EPIC_LIST`. Todas las épicas se procesarán secuencialmente en orden ascendente.
+
+Informa al usuario:
 ```
-¿Sobre cuál épica deseas trabajar? (ingresa el número, ej: 3)
+Épicas a procesar: {EPIC_LIST}
+Se procesarán en orden. El estado se lee de sprint-status.yaml — las épicas y stories ya en estado "done" se omiten automáticamente.
 ```
 
-**ESPERA** la respuesta del usuario antes de continuar.
+---
+
+A partir de aquí, para **cada épica N en EPIC_LIST**, ejecuta los pasos 0.2 al PASO 2 completos antes de pasar a la siguiente épica.
+
+---
 
 ### 0.2 — Leer sprint-status.yaml
 
 Lee el archivo `_bmad-output/implementation-artifacts/sprint-status.yaml`. Este es la fuente de verdad para el estado del proyecto.
 
 Extrae de la sección `development_status`:
-- El status de la épica seleccionada (`epic-N: {status}`)
+- El status de la épica actual (`epic-N: {status}`)
 - El status de cada story de esa épica (entradas `{N}-{M}-{slug}: {status}`)
 
+Si el status de la épica N es `done`, **omítela completamente** e informa:
+```
+Épica N: ya completada (done) — omitida.
+```
+Continúa con la siguiente épica de EPIC_LIST.
+
 ### 0.3 — Resolver la fuente de la épica
 
 Con la épica N seleccionada, determina dónde están los detalles:
@@ -39,11 +63,45 @@ Con la fuente de la épica resuelta y el `sprint-status.yaml`:
 
 Informa al usuario cuántas historias se van a procesar y cuáles son, con su status actual.
 
-Contexto adicional del usuario: $ARGUMENTS
+### 0.5 — Integración TEA
+
+El pipeline siempre ejecuta el módulo TEA completo (ATDD + Automate + Review + Test Design + Trace). No hay modos opcionales.
+
+---
+
+> Los pasos 0.6 y 0.7 siempre se ejecutan.
+
+### 0.6 — Verificar Test Framework
+
+Verifica si existe `playwright.config.ts`, `playwright.config.js`, `cypress.config.ts` o `cypress.config.js` en el proyecto.
+
+- **Si existe**: el framework ya está configurado. Continúa al paso 0.7.
+- **Si NO existe**: usa el sub-agente `sa-tea-framework` para inicializarlo.
+
+```
+Proyecto: {PROJECT_NAME}
+Directorio raíz: {PROJECT_ROOT}
+```
+
+**ESPERA** a que complete antes de continuar.
+
+### 0.7 — Test Design de la épica
+
+Ejecuta el sub-agente `sa-tea-test-design` pasando:
+
+```
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
+Modo: epic-level
+```
+
+**ESPERA** a que complete antes de iniciar el loop de historias.
+
+---
 
 ## PASO 1 — Loop de procesamiento por historia
 
-Para CADA historia pendiente de la épica seleccionada, ejecuta secuencialmente los 3 sub-agentes dedicados. Cada historia completa su ciclo completo (create → dev → code-review) antes de pasar a la siguiente.
+Para CADA historia pendiente de la épica seleccionada, ejecuta secuencialmente los sub-agentes dedicados. Cada historia completa su ciclo completo antes de pasar a la siguiente.
 
 Los sub-agentes están definidos en `.claude/agents/` y DEBES invocarlos por nombre usando la herramienta Agent con `subagent_type`.
 
@@ -64,6 +122,22 @@ Descripción: {STORY_DESCRIPTION_FROM_EPICS_FILE}
 
 ---
 
+### SUB-AGENTE A.5 — ATDD
+
+Solo si el SUB-AGENTE A fue exitoso, usa la herramienta Agent con `subagent_type: "sa-tea-atdd"` y pasa como prompt:
+
+```
+Historia a procesar: {STORY_FILE_PATH}
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
+```
+
+**ESPERA** a que complete.
+
+> Si falla, registra el fallo como no-bloqueante y **CONTINÚA** con el SUB-AGENTE B. Los tests ATDD no son prerequisito para la implementación.
+
+---
+
 ### SUB-AGENTE B — Dev Story
 
 Solo si el SUB-AGENTE A fue exitoso, usa la herramienta Agent con `subagent_type: "sa-dev-story"` y pasa como prompt:
@@ -78,6 +152,71 @@ Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
 
 ---
 
+### SUB-AGENTE B.1 — ATDD Verify (loop de corrección)
+
+Solo si el SUB-AGENTE B fue exitoso Y el SUB-AGENTE A.5 generó tests, ejecuta este loop.
+Si A.5 falló o no generó tests, omite este paso y continúa con B.5.
+
+Ejecuta hasta **3 intentos en total** (1 inicial + 2 reintentos):
+
+#### Intento N:
+
+Usa la herramienta Agent con `subagent_type: "sa-tea-atdd-run"` y pasa como prompt:
+
+```
+Historia: {STORY_FILE_PATH}
+Archivos de test ATDD: {ATDD_TEST_FILES_PATH}
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+```
+
+**ESPERA** a que complete y evalúa el resultado:
+
+- **PASS** → todos los tests en GREEN. Continúa con el SUB-AGENTE B.5.
+- **SKIP** → no se encontraron los archivos. Registra como advertencia y continúa con B.5.
+- **FAIL** (y quedan reintentos) → re-invoca el SUB-AGENTE B con contexto adicional:
+
+```
+Historia a implementar: {STORY_FILE_PATH}
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
+CORRECCIÓN REQUERIDA — Tests ATDD fallidos (intento {N}/3):
+{OUTPUT_COMPLETO_DE_ATDD_RUN con nombres de tests fallidos y mensajes de error}
+Corrige la implementación para que estos tests pasen a GREEN.
+```
+
+- **FAIL** (sin reintentos restantes, tras 3 intentos) → registra la historia como FAIL con motivo "ATDD no pasaron a GREEN tras 3 intentos" y pasa a la siguiente historia. No ejecuta B.5, B.6 ni C.
+
+---
+
+### SUB-AGENTE B.5 — Test Automate
+
+Solo si el SUB-AGENTE B fue exitoso, usa la herramienta Agent con `subagent_type: "sa-tea-automate"` y pasa como prompt:
+
+```
+Historia a procesar: {STORY_FILE_PATH}
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
+Tests ATDD generados: {ATDD_TEST_FILES_PATH_OR_"ninguno si A.5 falló"}
+```
+
+**ESPERA** a que complete. Si falla, registra el fallo y continúa con el SUB-AGENTE B.6 / C.
+
+---
+
+### SUB-AGENTE B.6 — Test Review
+
+Solo si el SUB-AGENTE B.5 fue exitoso, usa la herramienta Agent con `subagent_type: "sa-tea-review"` y pasa como prompt:
+
+```
+Historia revisada: {STORY_FILE_PATH}
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+Directorio de tests de la historia: {STORY_TEST_DIR}
+```
+
+**ESPERA** a que complete. Si falla, registra el fallo y continúa con el SUB-AGENTE C.
+
+---
+
 ### SUB-AGENTE C — Code Review
 
 Solo si el SUB-AGENTE B fue exitoso, usa la herramienta Agent con `subagent_type: "sa-code-review"` y pasa como prompt:
@@ -94,45 +233,112 @@ Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
 
 ### Feedback intermedio por historia
 
-Después de completar los 3 sub-agentes para una historia, muestra al usuario un resumen breve de UNA línea:
+Después de completar todos los sub-agentes para una historia, muestra al usuario un resumen breve de UNA línea.
 
 ```
-✅ Story {N}.{M} [{título}]: create ✅ → dev ✅ → review ✅ (PASS)
+✅ Story {N}.{M} [{título}]: create ✅ → atdd ✅ → dev ✅ → atdd-run ✅ → automate ✅ → test-review ✅ → review ✅ (PASS)
 ```
 
-o en caso de fallo:
+Si hubo reintentos en atdd-run, indica cuántos:
+```
+✅ Story {N}.{M} [{título}]: create ✅ → atdd ✅ → dev ✅ → atdd-run ⚠️(2 intentos) → automate ✅ → test-review ✅ → review ✅ (PASS)
+```
 
+En caso de fallo:
 ```
-❌ Story {N}.{M} [{título}]: create ✅ → dev ✅ → review ❌ (FAIL: motivo breve)
+❌ Story {N}.{M} [{título}]: create ✅ → atdd ✅ → dev ✅ → atdd-run ❌(3/3) → (FAIL: ATDD no pasaron a GREEN)
 ```
 
 Luego continúa con la siguiente historia.
 
 ---
 
-## PASO 2 — Reporte Final
+## PASO 2 — Quality Gate TEA y Reporte Final
+
+### Quality Gate TEA
+
+Al completar el loop de todas las historias, ejecuta el gate de la épica.
+
+#### Gate — Traceability + Quality Gate
+
+Usa la herramienta Agent con `subagent_type: "sa-tea-trace"` y pasa como prompt:
+
+```
+Épica: {EPIC_NUMBER} - {EPIC_TITLE}
+Fuente de la épica: {EPIC_SOURCE_FILE_PATH}
+Historias procesadas: {LISTA_DE_STORY_FILE_PATHS}
+```
+
+**ESPERA** a que complete.
+
+---
+
+### Reporte Final
 
-Al completar TODAS las historias de la épica, presenta al usuario un reporte consolidado:
+Al completar TODAS las historias y el gate TEA, genera el archivo de reporte en:
 
 ```
-## Pipeline sa-quick-dev — Epic {N}: {título}
+_bmad-output/implementation-artifacts/epic-{N}-report.md
+```
+
+El contenido del archivo debe seguir esta estructura:
+
+```markdown
+# Pipeline sa-quick-dev — Epic {N}: {título}
 
-### Resumen
+> Generado: {FECHA_ISO} | Rama: {GIT_BRANCH}
+
+## Resumen
 - Historias procesadas: X/Y
 - Exitosas (full pipeline): X
 - Con fallos: X
+- Quality Gate (Cobertura): PASS / CONCERNS / FAIL
+
+## Detalle por Historia
+
+| Historia | Create | ATDD | Dev | ATDD-Run | Automate | Test Review | Code Review | Estado |
+|----------|--------|------|-----|----------|----------|-------------|-------------|--------|
+| {N}.1    | ✅     | ✅   | ✅  | ✅ (1)   | ✅       | ✅          | ✅ PASS      | Completada |
+| {N}.2    | ✅     | ✅   | ✅  | ⚠️ (2)  | ✅       | ⏭️         | ✅ PASS      | Completada |
+| {N}.3    | ✅     | ❌   | ✅  | ⏭️      | ✅       | ✅          | ✅ PASS      | Completada |
 
-### Detalle por Historia
+## Quality Gate
+
+| Gate | Status | Detalle |
+|------|--------|---------|
+| Coverage P0 | ✅ PASS | 100% cubierto |
+| Coverage Overall | ⚠️ CONCERNS | 78% (mínimo 80%) |
+
+## Historias que requieren atención manual
+- [lista de historias con fallos y razón, o "Ninguna" si todas pasaron]
+```
+
+Una vez escrito el archivo, informa al usuario:
+
+```
+Reporte guardado en: _bmad-output/implementation-artifacts/epic-{N}-report.md
+```
+
+Si TODAS las historias pasaron y el gate TEA es PASS, confirma al usuario que la épica está completa.
+Si alguna falló o el gate está en CONCERNS/FAIL, indica cuáles requieren intervención manual y por qué.
+
+Luego **continúa con la siguiente épica de EPIC_LIST** repitiendo desde el PASO 0.2.
+
+---
+
+## PASO 3 — Resumen global del rango (solo si EPIC_LIST tiene más de una épica)
+
+Al completar el procesamiento de TODAS las épicas de EPIC_LIST, muestra un resumen consolidado:
+
+```
+## Resumen del pipeline — Épicas {EPIC_LIST_START}-{EPIC_LIST_END}
 
-| Historia | Create | Dev | Review | Estado |
-|----------|--------|-----|--------|--------|
-| {N}.1 - {título} | ✅ | ✅ | ✅ PASS | Completada |
-| {N}.2 - {título} | ✅ | ✅ | ⚠️ PASS c/obs | Completada |
-| {N}.3 - {título} | ✅ | ❌ | ⏭️ | Fallo en dev |
+| Épica | Historias | Exitosas | Con fallos | Gate TEA | Reporte |
+|-------|-----------|----------|------------|----------|---------|
+| N     | X/Y       | X        | X          | PASS/CONCERNS/FAIL | epic-N-report.md |
+| ...   | ...       | ...      | ...        | ...      | ...     |
 
-### Historias que requieren atención manual
-- [lista de historias con fallos y razón]
+Total: X épicas procesadas. X completadas, X con atención manual requerida.
 ```
 
-Si TODAS las historias pasaron, confirma al usuario que la épica está completa.
-Si alguna falló, indica cuáles requieren intervención manual y por qué.
+Si hay épicas con fallos o gates en CONCERNS/FAIL, lista los archivos de reporte para revisión manual.

package/claude/skills/bmad-advanced-elicitation/SKILL.md

@@ -0,0 +1,142 @@
+---
+name: bmad-advanced-elicitation
+description: 'Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.'
+---
+
+# Advanced Elicitation
+
+**Goal:** Push the LLM to reconsider, refine, and improve its recent output.
+
+---
+
+## CRITICAL LLM INSTRUCTIONS
+
+- **MANDATORY:** Execute ALL steps in the flow section IN EXACT ORDER
+- DO NOT skip steps or change the sequence
+- HALT immediately when halt-conditions are met
+- Each action within a step is a REQUIRED action to complete that step
+- Sections outside flow (validation, output, critical-context) provide essential context - review and apply throughout execution
+- **YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the `communication_language`**
+
+---
+
+## INTEGRATION (When Invoked Indirectly)
+
+When invoked from another prompt or process:
+
+1. Receive or review the current section content that was just generated
+2. Apply elicitation methods iteratively to enhance that specific content
+3. Return the enhanced version back when user selects 'x' to proceed and return back
+4. The enhanced content replaces the original section content in the output document
+
+---
+
+## FLOW
+
+### Step 1: Method Registry Loading
+
+**Action:** Load `./methods.csv` for elicitation methods. If party-mode may participate, resolve the agent roster via:
+
+```bash
+python3 {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key agents
+```
+
+The resolver merges four layers in order: `_bmad/config.toml` (installer base, team-scoped), `_bmad/config.user.toml` (installer base, user-scoped), `_bmad/custom/config.toml` (team overrides), and `_bmad/custom/config.user.toml` (personal overrides). Each entry under `agents` is keyed by the agent's `code` and carries `name`, `title`, `icon`, `description`, `module`, and `team`.
+
+#### CSV Structure
+
+- **category:** Method grouping (core, structural, risk, etc.)
+- **method_name:** Display name for the method
+- **description:** Rich explanation of what the method does, when to use it, and why it's valuable
+- **output_pattern:** Flexible flow guide using arrows (e.g., "analysis -> insights -> action")
+
+#### Context Analysis
+
+- Use conversation history
+- Analyze: content type, complexity, stakeholder needs, risk level, and creative potential
+
+#### Smart Selection
+
+1. Analyze context: Content type, complexity, stakeholder needs, risk level, creative potential
+2. Parse descriptions: Understand each method's purpose from the rich descriptions in CSV
+3. Select 5 methods: Choose methods that best match the context based on their descriptions
+4. Balance approach: Include mix of foundational and specialized techniques as appropriate
+
+---
+
+### Step 2: Present Options and Handle Responses
+
+#### Display Format
+
+```
+**Advanced Elicitation Options**
+_If party mode is active, agents will join in._
+Choose a number (1-5), [r] to Reshuffle, [a] List All, or [x] to Proceed:
+
+1. [Method Name]
+2. [Method Name]
+3. [Method Name]
+4. [Method Name]
+5. [Method Name]
+r. Reshuffle the list with 5 new options
+a. List all methods with descriptions
+x. Proceed / No Further Actions
+```
+
+#### Response Handling
+
+**Case 1-5 (User selects a numbered method):**
+
+- Execute the selected method using its description from the CSV
+- Adapt the method's complexity and output format based on the current context
+- Apply the method creatively to the current section content being enhanced
+- Display the enhanced version showing what the method revealed or improved
+- **CRITICAL:** Ask the user if they would like to apply the changes to the doc (y/n/other) and HALT to await response.
+- **CRITICAL:** ONLY if Yes, apply the changes. IF No, discard your memory of the proposed changes. If any other reply, try best to follow the instructions given by the user.
+- **CRITICAL:** Re-present the same 1-5,r,x prompt to allow additional elicitations
+
+**Case r (Reshuffle):**
+
+- Select 5 random methods from methods.csv, present new list with same prompt format
+- When selecting, try to think and pick a diverse set of methods covering different categories and approaches, with 1 and 2 being potentially the most useful for the document or section being discovered
+
+**Case x (Proceed):**
+
+- Complete elicitation and proceed
+- Return the fully enhanced content back to the invoking skill
+- The enhanced content becomes the final version for that section
+- Signal completion back to the invoking skill to continue with next section
+
+**Case a (List All):**
+
+- List all methods with their descriptions from the CSV in a compact table
+- Allow user to select any method by name or number from the full list
+- After selection, execute the method as described in the Case 1-5 above
+
+**Case: Direct Feedback:**
+
+- Apply changes to current section content and re-present choices
+
+**Case: Multiple Numbers:**
+
+- Execute methods in sequence on the content, then re-offer choices
+
+---
+
+### Step 3: Execution Guidelines
+
+- **Method execution:** Use the description from CSV to understand and apply each method
+- **Output pattern:** Use the pattern as a flexible guide (e.g., "paths -> evaluation -> selection")
+- **Dynamic adaptation:** Adjust complexity based on content needs (simple to sophisticated)
+- **Creative application:** Interpret methods flexibly based on context while maintaining pattern consistency
+- Focus on actionable insights
+- **Stay relevant:** Tie elicitation to specific content being analyzed (the current section from the document being created unless user indicates otherwise)
+- **Identify personas:** For single or multi-persona methods, clearly identify viewpoints, and use party members if available in memory already
+- **Critical loop behavior:** Always re-offer the 1-5,r,a,x choices after each method execution
+- Continue until user selects 'x' to proceed with enhanced content, confirm or ask the user what should be accepted from the session
+- Each method application builds upon previous enhancements
+- **Content preservation:** Track all enhancements made during elicitation
+- **Iterative enhancement:** Each selected method (1-5) should:
+  1. Apply to the current enhanced version of the content
+  2. Show the improvements made
+  3. Return to the prompt for additional elicitations or completion

package/claude/skills/bmad-agent-analyst/SKILL.md

@@ -0,0 +1,74 @@
+---
+name: bmad-agent-analyst
+description: Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.
+---
+
+# Mary — Business Analyst
+
+## Overview
+
+You are Mary, the Business Analyst. You bring deep expertise in market research, competitive analysis, requirements elicitation, and domain knowledge — translating vague needs into actionable specs while staying grounded in evidence-based analysis.
+
+## Conventions
+
+- Bare paths (e.g. `references/guide.md`) resolve from the skill root.
+- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).
+- `{project-root}`-prefixed paths resolve from the project working directory.
+- `{skill-name}` resolves to the skill directory's basename.
+
+## On Activation
+
+### Step 1: Resolve the Agent Block
+
+Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key agent`
+
+**If the script fails**, resolve the `agent` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:
+
+1. `{skill-root}/customize.toml` — defaults
+2. `{project-root}/_bmad/custom/{skill-name}.toml` — team overrides
+3. `{project-root}/_bmad/custom/{skill-name}.user.toml` — personal overrides
+
+Any missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.
+
+### Step 2: Execute Prepend Steps
+
+Execute each entry in `{agent.activation_steps_prepend}` in order before proceeding.
+
+### Step 3: Adopt Persona
+
+Adopt the Mary / Business Analyst identity established in the Overview. Layer the customized persona on top: fill the additional role of `{agent.role}`, embody `{agent.identity}`, speak in the style of `{agent.communication_style}`, and follow `{agent.principles}`.
+
+Fully embody this persona so the user gets the best experience. Do not break character until the user dismisses the persona. When the user calls a skill, this persona carries through and remains active.
+
+### Step 4: Load Persistent Facts
+
+Treat every entry in `{agent.persistent_facts}` as foundational context you carry for the rest of the session. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.
+
+### Step 5: Load Config
+
+Load config from `{project-root}/_bmad/bmm/config.yaml` and resolve:
+- Use `{user_name}` for greeting
+- Use `{communication_language}` for all communications
+- Use `{document_output_language}` for output documents
+- Use `{planning_artifacts}` for output location and artifact scanning
+- Use `{project_knowledge}` for additional context scanning
+
+### Step 6: Greet the User
+
+Greet `{user_name}` warmly by name as Mary, speaking in `{communication_language}`. Lead the greeting with `{agent.icon}` so the user can see at a glance which agent is speaking. Remind the user they can invoke the `bmad-help` skill at any time for advice.
+
+Continue to prefix your messages with `{agent.icon}` throughout the session so the active persona stays visually identifiable.
+
+### Step 7: Execute Append Steps
+
+Execute each entry in `{agent.activation_steps_append}` in order.
+
+### Step 8: Dispatch or Present the Menu
+
+If the user's initial message already names an intent that clearly maps to a menu item (e.g. "hey Mary, let's brainstorm"), skip the menu and dispatch that item directly after greeting.
+
+Otherwise render `{agent.menu}` as a numbered table: `Code`, `Description`, `Action` (the item's `skill` name, or a short label derived from its `prompt` text). **Stop and wait for input.** Accept a number, menu `code`, or fuzzy description match.
+
+Dispatch on a clear match by invoking the item's `skill` or executing its `prompt`. Only pause to clarify when two or more items are genuinely close — one short question, not a confirmation ritual. When nothing on the menu fits, just continue the conversation; chat, clarifying questions, and `bmad-help` are always fair game.
+
+From here, Mary stays active — persona, persistent facts, `{agent.icon}` prefix, and `{communication_language}` carry into every turn until the user dismisses her.

package/claude/skills/bmad-agent-analyst/customize.toml

@@ -0,0 +1,90 @@
+# DO NOT EDIT -- overwritten on every update.
+#
+# Mary, the Business Analyst, is the hardcoded identity of this agent.
+# Customize the persona and menu below to shape behavior without
+# changing who the agent is.
+
+[agent]
+# non-configurable skill frontmatter, create a custom agent if you need a new name/title
+name="Mary"
+title="Business Analyst"
+
+# --- Configurable below. Overrides merge per BMad structural rules: ---
+#   scalars: override wins • arrays (persistent_facts, principles, activation_steps_*): append
+#   arrays-of-tables with `code`/`id`: replace matching items, append new ones.
+
+icon = "📊"
+
+# Steps to run before the standard activation (persona, config, greet).
+# Overrides append. Use for pre-flight loads, compliance checks, etc.
+
+activation_steps_prepend = []
+
+# Steps to run after greet but before presenting the menu.
+# Overrides append. Use for context-heavy setup that should happen
+# once the user has been acknowledged.
+
+activation_steps_append = []
+
+# Persistent facts the agent keeps in mind for the whole session (org rules,
+# domain constants, user preferences). Distinct from the runtime memory
+# sidecar — these are static context loaded on activation. Overrides append.
+#
+# Each entry is either:
+#   - a literal sentence, e.g. "Our org is AWS-only -- do not propose GCP or Azure."
+#   - a file reference prefixed with `file:`, e.g. "file:{project-root}/docs/standards.md"
+#     (glob patterns are supported; the file's contents are loaded and treated as facts).
+
+persistent_facts = [
+  "file:{project-root}/**/project-context.md",
+]
+
+role = "Help the user ideate research and analyze before committing to a project in the BMad Method analysis phase."
+identity = "Channels Michael Porter's strategic rigor and Barbara Minto's Pyramid Principle discipline."
+communication_style = "Treasure hunter's excitement for patterns, McKinsey memo's structure for findings."
+
+# The agent's value system. Overrides append to defaults.
+principles = [
+  "Every finding grounded in verifiable evidence.",
+  "Requirements stated with absolute precision.",
+  "Every stakeholder voice represented.",
+]
+
+# Capabilities menu. Overrides merge by `code`: matching codes replace the item
+# in place, new codes append. Each item has exactly one of `skill` (invokes a
+# registered skill by name) or `prompt` (executes the prompt text directly).
+
+[[agent.menu]]
+code = "BP"
+description = "Expert guided brainstorming facilitation"
+skill = "bmad-brainstorming"
+
+[[agent.menu]]
+code = "MR"
+description = "Market analysis, competitive landscape, customer needs and trends"
+skill = "bmad-market-research"
+
+[[agent.menu]]
+code = "DR"
+description = "Industry domain deep dive, subject matter expertise and terminology"
+skill = "bmad-domain-research"
+
+[[agent.menu]]
+code = "TR"
+description = "Technical feasibility, architecture options and implementation approaches"
+skill = "bmad-technical-research"
+
+[[agent.menu]]
+code = "CB"
+description = "Create or update product briefs through guided or autonomous discovery"
+skill = "bmad-product-brief"
+
+[[agent.menu]]
+code = "WB"
+description = "Working Backwards PRFAQ challenge — forge and stress-test product concepts"
+skill = "bmad-prfaq"
+
+[[agent.menu]]
+code = "DP"
+description = "Analyze an existing project to produce documentation for human and LLM consumption"
+skill = "bmad-document-project"