siesa-agents 2.1.78 → 2.1.79

package/claude/skills/bmad-validate-prd/steps-v/step-v-13-report-complete.md

@@ -0,0 +1,230 @@
+---
+# File references (ONLY variables used in this step)
+validationReportPath: '{validation_report_path}'
+prdFile: '{prd_file_path}'
+---
+
+# Step 13: Validation Report Complete
+
+## STEP GOAL:
+
+Finalize validation report, summarize all findings from steps 1-12, present summary to user conversationally, and offer actionable next steps.
+
+## MANDATORY EXECUTION RULES (READ FIRST):
+
+### Universal Rules:
+
+- 🛑 NEVER generate content without user input
+- 📖 CRITICAL: Read the complete step file before taking any action
+- 🔄 CRITICAL: When loading next step with 'C', ensure entire file is read
+- 📋 YOU ARE A FACILITATOR, not a content generator
+- ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}`
+- ✅ YOU MUST ALWAYS WRITE all artifact and document content in `{document_output_language}`
+
+### Role Reinforcement:
+
+- ✅ You are a Validation Architect and Quality Assurance Specialist
+- ✅ If you already have been given communication or persona patterns, continue to use those while playing this new role
+- ✅ We engage in collaborative dialogue, not command-response
+- ✅ You bring synthesis and summary expertise
+- ✅ This is the FINAL step - requires user interaction
+
+### Step-Specific Rules:
+
+- 🎯 Focus ONLY on summarizing findings and presenting options
+- 🚫 FORBIDDEN to perform additional validation
+- 💬 Approach: Conversational summary with clear next steps
+- 🚪 This is the final step - no next step after this
+
+## EXECUTION PROTOCOLS:
+
+- 🎯 Load complete validation report
+- 🎯 Summarize all findings from steps 1-12
+- 🎯 Update report frontmatter with final status
+- 💬 Present summary to user conversationally
+- 💬 Offer menu options for next actions
+- 🚫 FORBIDDEN to proceed without user selection
+
+## CONTEXT BOUNDARIES:
+
+- Available context: Complete validation report with findings from all validation steps
+- Focus: Summary and presentation only (no new validation)
+- Limits: Don't add new findings, just synthesize existing
+- Dependencies: Steps 1-12 completed - all validation checks done
+
+## MANDATORY SEQUENCE
+
+**CRITICAL:** Follow this sequence exactly. Do not skip, reorder, or improvise unless user explicitly requests a change.
+
+### 1. Load Complete Validation Report
+
+Read the entire validation report from {validationReportPath}
+
+Extract all findings from:
+- Format Detection (Step 2)
+- Parity Analysis (Step 2B, if applicable)
+- Information Density (Step 3)
+- Product Brief Coverage (Step 4)
+- Measurability (Step 5)
+- Traceability (Step 6)
+- Implementation Leakage (Step 7)
+- Domain Compliance (Step 8)
+- Project-Type Compliance (Step 9)
+- SMART Requirements (Step 10)
+- Holistic Quality (Step 11)
+- Completeness (Step 12)
+
+### 2. Update Report Frontmatter with Final Status
+
+Update validation report frontmatter:
+
+```yaml
+---
+validationTarget: '{prd_path}'
+validationDate: '{current_date}'
+inputDocuments: [list of documents]
+validationStepsCompleted: ['step-v-01-discovery', 'step-v-02-format-detection', 'step-v-03-density-validation', 'step-v-04-brief-coverage-validation', 'step-v-05-measurability-validation', 'step-v-06-traceability-validation', 'step-v-07-implementation-leakage-validation', 'step-v-08-domain-compliance-validation', 'step-v-09-project-type-validation', 'step-v-10-smart-validation', 'step-v-11-holistic-quality-validation', 'step-v-12-completeness-validation']
+validationStatus: COMPLETE
+holisticQualityRating: '{rating from step 11}'
+overallStatus: '{Pass/Warning/Critical based on all findings}'
+---
+```
+
+### 3. Create Summary of Findings
+
+**Overall Status:**
+- Determine from all validation findings
+- **Pass:** All critical checks pass, minor warnings acceptable
+- **Warning:** Some issues found but PRD is usable
+- **Critical:** Major issues that prevent PRD from being fit for purpose
+
+**Quick Results Table:**
+- Format: [classification]
+- Information Density: [severity]
+- Measurability: [severity]
+- Traceability: [severity]
+- Implementation Leakage: [severity]
+- Domain Compliance: [status]
+- Project-Type Compliance: [compliance score]
+- SMART Quality: [percentage]
+- Holistic Quality: [rating/5]
+- Completeness: [percentage]
+
+**Critical Issues:** List from all validation steps
+**Warnings:** List from all validation steps
+**Strengths:** List positives from all validation steps
+
+**Holistic Quality Rating:** From step 11
+**Top 3 Improvements:** From step 11
+
+**Recommendation:** Based on overall status
+
+### 4. Present Summary to User Conversationally
+
+Display:
+
+"**✓ PRD Validation Complete**
+
+**Overall Status:** {Pass/Warning/Critical}
+
+**Quick Results:**
+{Present quick results table with key findings}
+
+**Critical Issues:** {count or "None"}
+{If any, list briefly}
+
+**Warnings:** {count or "None"}
+{If any, list briefly}
+
+**Strengths:**
+{List key strengths}
+
+**Holistic Quality:** {rating}/5 - {label}
+
+**Top 3 Improvements:**
+1. {Improvement 1}
+2. {Improvement 2}
+3. {Improvement 3}
+
+**Recommendation:**
+{Based on overall status:
+- Pass: "PRD is in good shape. Address minor improvements to make it great."
+- Warning: "PRD is usable but has issues that should be addressed. Review warnings and improve where needed."
+- Critical: "PRD has significant issues that should be fixed before use. Focus on critical issues above."}
+
+**What would you like to do next?**"
+
+### 5. Present MENU OPTIONS
+
+Display:
+
+**[R] Review Detailed Findings** - Walk through validation report section by section
+**[E] Use Edit Workflow** - Use validation report with Edit workflow for systematic improvements
+**[F] Fix Simpler Items** - Immediate fixes for simple issues (anti-patterns, leakage, missing headers)
+**[X] Exit** - Exit and Suggest Next Steps.
+
+#### EXECUTION RULES:
+
+- ALWAYS halt and wait for user input after presenting menu
+- Only proceed based on user selection
+
+#### Menu Handling Logic:
+
+- **IF R (Review Detailed Findings):**
+  - Walk through validation report section by section
+  - Present findings from each validation step
+  - Allow user to ask questions
+  - After review, return to menu
+
+- **IF E (Use Edit Workflow):**
+  - Explain: "The Edit workflow can use this validation report to systematically address issues. Edit mode will guide you through discovering what to edit, reviewing the PRD, and applying targeted improvements."
+  - Offer: "Would you like to launch Edit mode now? It will help you fix validation findings systematically."
+  - If yes: Invoke the `bmad-edit-prd` skill, passing the validation report path as context
+  - If no: Return to menu
+
+- **IF F (Fix Simpler Items):**
+  - Offer immediate fixes for:
+    - Template variables (fill in with appropriate content)
+    - Conversational filler (remove wordy phrases)
+    - Implementation leakage (remove technology names from FRs/NFRs)
+    - Missing section headers (add ## headers)
+  - Ask: "Which simple fixes would you like me to make?"
+  - If user specifies fixes, make them and update validation report
+  - Return to menu
+
+- **IF X (Exit):**
+  - Display: "**Validation Report Saved:** {validationReportPath}"
+  - Display: "**Summary:** {overall status} - {recommendation}"
+  - PRD Validation complete. Invoke the `bmad-help` skill.
+  - Run: `python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.
+
+- **IF Any other:** Help user, then redisplay menu
+
+---
+
+## 🚨 SYSTEM SUCCESS/FAILURE METRICS
+
+### ✅ SUCCESS:
+
+- Complete validation report loaded successfully
+- All findings from steps 1-12 summarized
+- Report frontmatter updated with final status
+- Overall status determined correctly (Pass/Warning/Critical)
+- Quick results table presented
+- Critical issues, warnings, and strengths listed
+- Holistic quality rating included
+- Top 3 improvements presented
+- Clear recommendation provided
+- Menu options presented with clear explanations
+- User can review findings, get help, or exit
+
+### ❌ SYSTEM FAILURE:
+
+- Not loading complete validation report
+- Missing summary of findings
+- Not updating report frontmatter
+- Not determining overall status
+- Missing menu options
+- Unclear next steps
+
+**Master Rule:** User needs clear summary and actionable next steps. Edit workflow is best for complex issues; immediate fixes available for simpler ones.

package/claude/skills/sa-check-implementation-readiness/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-check-implementation-readiness
+description: 'Custom Siesa extension of bmad-check-implementation-readiness. Injects project-specific context via workflow_ext.md before delegating to the base skill. Use when the user says "check implementation readiness".'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: 
+
+1. FIRST, LOAD and READ the FULL contents of the custom extension file at: `_siesa-agents/bmm/workflows/3-solutioning/check-implementation-readiness/workflow_ext.md ` — This contains mandatory pre-workflow context injection rules. Execute its steps BEFORE proceeding.
+
+2. LOAD the FULL @.claude/skills/bmad-check-implementation-readiness/SKILL.md, READ its entire contents and follow its directions exactly!

package/claude/skills/sa-code-review/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-code-review
+description: 'Custom perform an ADVERSARIAL Senior Developer code review that finds 3-10 specific problems in every story. Challenges everything: code quality, test coverage, architecture compliance, security, performance. NEVER accepts `looks good` - must find minimum issues and can auto-fix with user approval.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS 
+
+1. FIRST: LOAD and READ the FULL `@_siesa-agents/bmm/workflows/4-implementation/code-review/workflow_ext.md` — This contains mandatory context injection rules. Apply them throughout the workflow execution.
+
+2. Always LOAD the FULL `@_siesa-agents/bmm/workflows/4-implementation/code-review/workflow.md`. Follow all instructions in the task file exactly as written.

package/claude/skills/sa-correct-course/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-correct-course
+description: 'Custom Siesa extension of bmad-correct-course. Loads company-specific workflow standards before delegating to the base skill. Use when the user says "correct course" or "propose sprint change"'
+---
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS - while staying in character as the current agent persona you may have loaded:
+
+
+1. ALWAYS Load and read the workflow extension from `@{project-root}/_siesa-agents/bmm/workflows/4-implementation/correct-course/workflow_ext.md` to understand the Company Standards Context.
+
+2. Follow the instructions in `.claude/skills/bmad-correct-course/SKILL.md`

package/claude/skills/sa-create-architecture/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-create-architecture
+description: 'Customization of Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design"'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: 
+
+1. FIRST, LOAD and READ the FULL contents of the custom extension file at: `_siesa-agents/bmm/workflows/3-solutioning/create-architecture/workflow_ext.md ` — This contains mandatory pre-workflow context injection rules. Execute its steps BEFORE proceeding.
+
+2. Follow the instructions in `.claude/skills/bmad-create-architecture/SKILL.md`

package/claude/skills/sa-create-epics-and-stories/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-create-epics-and-stories
+description: 'Custom SIESA extension of bmad-create-epics-and-stories. Injects context from _siesa-agents workflow extension before delegating to the base skill. Use when the user says "create the epics and stories list".'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: 
+
+1. FIRST, LOAD and READ the FULL contents of the custom extension file at: `_siesa-agents/bmm/workflows/3-solutioning/create-epics-and-stories/workflow_ext.md` — This contains mandatory pre-workflow context injection rules. Execute its steps BEFORE proceeding.
+
+2. Follow the instructions in `.claude/skills/bmad-create-epics-and-stories/SKILL.md`

package/claude/skills/sa-create-prd/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-create-prd
+description: 'SIESA custom version of bmad-create-prd. Creates a comprehensive PRD through collaborative step-by-step discovery, extended with SIESA-specific prerequisites (feature list sharding, workflow extensions). Use instead of bmad-create-prd when working on SIESA projects.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND IN THIS EXACT ORDER:
+
+1. FIRST, LOAD and READ the FULL contents of the custom extension file at: `_siesa-agents/bmm/workflows/2-plan-workflows/prd/workflow_ext.md`. You MUST assimilate these pre-requisites (especially asking for the feature list for sharding) before doing anything else.
+
+2. LOAD the FULL @.claude/skills/bmad-create-prd/SKILL.md, READ its entire contents and follow its directions exactly!

package/claude/skills/sa-create-story/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-create-story
+description: 'SIESA-specific story creation workflow. Analyzes epics, architecture, and project context to generate implementation-ready user stories following SIESA standards. Use when the user says "create the next story" or "create story [identifier]"'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS 
+
+1. FIRST: LOAD and READ the FULL `@_siesa-agents/bmm/workflows/4-implementation/create-story/workflow_ext.md` — This contains mandatory context injection rules. Apply them throughout the workflow execution.
+
+2. Always LOAD the FULL `@_siesa-agents/bmm/workflows/4-implementation/create-story/workflow.md`. Follow all instructions in the task file exactly as written.

package/claude/skills/sa-create-user-guide/SKILL.md

@@ -0,0 +1,6 @@
+---
+name: sa-create-user-guide
+description: 'Genera guías de usuario comprehensivas en español e inglés desde épicas y PRDs, con diagramas Mermaid y trazabilidad completa'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL @_siesa-agents/bmm/workflows/5-documentation/create-user-guide/workflow.md, READ its entire contents and follow its directions exactly!

package/claude/skills/sa-create-ux-design/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-create-ux-design
+description: 'Custom extension of bmad-create-ux-design: Plan UX patterns and design specifications with Siesa-specific customizations. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX"'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: 
+
+1. FIRST, LOAD and READ the FULL contents of the custom extension file at: `_siesa-agents/bmm/workflows/2-plan-workflows/create-ux-design/workflow_ext.md ` — This contains mandatory pre-workflow context injection rules. Execute its steps BEFORE proceeding.
+
+2. Follow the instructions in `.claude/skills/bmad-create-ux-design/SKILL.md`

package/claude/skills/sa-dev-story/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-dev-story
+description: "Executes the SIESA dev-story workflow: branches, injects shared-artifact context, implements tasks, writes tests, and marks the story ready for review."
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS 
+
+1. FIRST: LOAD and READ the FULL `@_siesa-agents/bmm/workflows/4-implementation/dev-story/workflow_ext.md` — This contains mandatory context injection rules. Apply them throughout the workflow execution.
+
+2. Always LOAD the FULL `@_siesa-agents/bmm/workflows/4-implementation/dev-story/workflow.md`. Follow all instructions in the task file exactly as written.

package/claude/skills/sa-generate-project-context/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-generate-project-context
+description: 'Custom version of bmad-generate-project-context. Extends the base skill by injecting additional context rules from _siesa-agents before delegating execution to the standard workflow. Use when the user says "generate project context" or "create project context"'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS:
+
+1. FIRST: LOAD and READ the FULL @_siesa-agents/bmm/workflows/generate-project-context/workflow_ext.md — This contains mandatory context injection rules and an interactive menu. Apply them BEFORE proceeding.
+
+2. Follow the instructions in @.claude/skills/bmad-generate-project-context/Skill.md

package/claude/skills/sa-product-brief/SKILL.md

@@ -0,0 +1,11 @@
+---
+name: sa-product-brief
+description: "SIESA custom version of bmad-product-brief. Creates or updates product briefs through guided or autonomous discovery, injecting SIESA-specific extension context (workflow_ext.md) before executing the base workflow. Use this instead of bmad-product-brief when working on SIESA projects."
+model: claude-sonnet-4-6
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: 
+
+1. FIRST, LOAD and READ the FULL contents of the custom extension file at: `_siesa-agents/bmm/workflows/1-analysis/create-product-brief/workflow_ext.md ` — This contains mandatory pre-workflow context injection rules. Execute its steps BEFORE proceeding.
+
+2. LOAD the FULL @.claude/skills/bmad-product-brief/SKILL.md, READ its entire contents and follow its directions exactly!

package/claude/skills/sa-quality-process/SKILL.md

@@ -0,0 +1,6 @@
+---
+name: sa-quality-process
+description: 'QA Quality Process — Phase 1 Planning or Phase 2 Design (QA Test Plan & Strategy). Asks at startup which phase to execute.'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: LOAD the FULL @_siesa-agents/bmm/workflows/3-solutioning/quality-process/workflow.md, READ its entire contents and follow its directions exactly!

package/claude/skills/sa-shard-doc/SKILL.md

@@ -0,0 +1,8 @@
+---
+name: 'sa-shard-doc'
+description: 'Custom skill to splits large markdown documents into smaller, organized files based on level 2 (default) sections'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THIS COMMAND: 
+
+Read the entire task file at: `{project-root}/_siesa-agents/core/tasks/shard-doc.md`.Follow all instructions in the task file exactly as written.

package/claude/skills/sa-sprint-planning/SKILL.md

@@ -0,0 +1,10 @@
+---
+name: sa-sprint-planning
+description: 'Custom Siesa extension of bmad-sprint-planning. Injects mandatory Siesa-specific context via workflow_ext.md before delegating to the base bmad-sprint-planning skill. Use when the user says "run sprint planning" or "generate sprint plan".'
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS 
+
+1. FIRST: LOAD and READ the FULL `@_siesa-agents/bmm/workflows/4-implementation/sprint-planning/workflow_ext.md` — This contains mandatory context injection rules. Apply them throughout the workflow execution.
+
+2. Always LOAD the FULL `@.claude/skills/bmad-sprint-planning/SKILL.md`.Follow all instructions in the task file exactly as written.

package/claude/skills/sa-sprint-status/SKILL.md

@@ -0,0 +1,9 @@
+---
+name: sa-sprint-status
+description: 'Custom extension of bmad-sprint-status that injects Siesa-specific context before delegating to the base workflow. Use when the user says "check sprint status" or "show sprint status"'
+---
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS 
+
+1. FIRST: LOAD and READ the FULL `@_siesa-agents/bmm/workflows/4-implementation/sprint-status/workflow_ext.md` — This contains mandatory context injection rules. Apply them throughout the workflow execution.
+
+2. Always LOAD the FULL `@.claude/skills/bmad-sprint-status/SKILL.md`.Follow all instructions in the task file exactly as written.

package/claude/skills/sa-workflow-init/SKILL.md

@@ -0,0 +1,181 @@
+---
+name: sa-workflow-init
+description: Initialize a new BMM project by determining level, type, and creating workflow path
+---
+
+IT IS CRITICAL THAT YOU FOLLOW THESE STEPS IN EXACT ORDER. NEVER skip a step. Execute ALL steps in the exact numerical order listed.
+
+## EXECUTION RULES
+
+- Read all referenced files COMPLETELY — never use offset or limit
+- After every **template-output** section: save the content to file (Write tool the first time, Edit tool on subsequent saves), show it to the user, then ask: `[a] Advanced Elicitation  [c] Continue  [y] YOLO rest of workflow` — wait for response before proceeding
+- **#yolo mode**: if the user activates it, skip all per-step confirmations and produce all remaining output automatically, simulating an expert user
+- Communicate with the user in `{communication_language}` throughout the entire workflow
+
+---
+
+## PHASE 0 — PRE-EXECUTION (BEFORE ANY STEP)
+
+### 0.1 Resolve config
+
+Load `{project-root}/_bmad/bmm/config.yaml` and resolve these variables:
+
+| Variable | Source |
+|---|---|
+| `{output_folder}` | config.yaml → output_folder |
+| `{planning_artifacts}` | config.yaml → planning_artifacts |
+| `{implementation_artifacts}` | config.yaml → implementation_artifacts |
+| `{user_name}` | config.yaml → user_name |
+| `{project_name}` | config.yaml → project_name |
+| `{communication_language}` | config.yaml → communication_language |
+| `{document_output_language}` | config.yaml → document_output_language |
+| `{user_skill_level}` | config.yaml → user_skill_level |
+
+### 0.2 Create Phase 1 discovery branch (MANDATORY — DO NOT SKIP)
+
+Before executing any workflow step, run the Phase 1 branch script:
+
+```bash
+node _siesa-agents/scripts/phases/phase1.js
+```
+
+- If the `discovery` branch already exists, the script will report it — continue normally.
+- If created successfully, confirm to the user.
+
+Output to the user:
+> `✅ Phase 1 (discovery) branch ready. Proceeding with workflow-init...`
+
+**DO NOT proceed to Step 1 until this is fully executed.**
+
+---
+
+## STEP 1 — Clone Siesa base repositories
+
+Before running any command, resolve `{project-root}` to the **actual absolute path** of the current working directory. Never pass the literal string `{project-root}` to the shell. Each `git clone` must run as an independent Bash tool call using the full absolute path.
+
+Use **AskUserQuestion** to present:
+
+> "To complete the project setup, I can clone the Siesa base repositories into the `apps/` folder. What would you like to clone?"
+>
+> **[1] Frontend + Backend** — Clone both base repositories.
+> **[2] Backend only** — Clone `BaseBackend` only.
+> **[3] Skip** — Do not clone any repository.
+
+---
+
+### Option [1] — Frontend + Backend
+
+Ensure `apps/` exists:
+```bash
+mkdir -p <resolved-project-root>/apps
+```
+
+**Copy architecture base file** (as-is, do not modify contents):
+```
+_siesa-agents/resources/architecture/architecture-both.md
+  → {planning_artifacts}/architecture.md
+```
+Create destination directory if it does not exist. Confirm the file exists at destination.
+
+**Copy UX/UI specification file** (as-is, do not modify contents):
+```
+_siesa-agents/resources/ux-ui/ux-design-specification.md
+  → {planning_artifacts}/ux-design-specification.md
+```
+Create destination directory if it does not exist. Confirm the file exists at destination.
+
+**Clone repositories** (only if target directory does NOT already exist):
+```bash
+git clone https://github.com/SiesaTeams/BaseFrontend.git <resolved-project-root>/apps/Frontend
+git clone https://github.com/SiesaTeams/BaseBackend.git <resolved-project-root>/apps/Backend
+```
+
+---
+
+### Option [2] — Backend only
+
+Ensure `apps/` exists:
+```bash
+mkdir -p <resolved-project-root>/apps
+```
+
+**Copy architecture base file** (as-is, do not modify contents):
+```
+_siesa-agents/resources/architecture/architecture-single-backend.md
+  → {planning_artifacts}/architecture.md
+```
+Create destination directory if it does not exist. Confirm the file exists at destination.
+
+**Clone repository** (only if target directory does NOT already exist):
+```bash
+git clone https://github.com/SiesaTeams/BaseBackend.git <resolved-project-root>/apps/Backend
+```
+
+---
+
+### Option [3] — Skip
+
+Do not execute any command. Proceed to the Final Phase.
+
+---
+
+### Pre-clone existence check
+
+Before each `git clone`, verify whether the target directory already exists:
+
+- If `apps/Frontend` exists → do NOT clone; inform:
+  > `⚠️ apps/Frontend already exists. Skipping Frontend clone.`
+- If `apps/Backend` exists → do NOT clone; inform:
+  > `⚠️ apps/Backend already exists. Skipping Backend clone.`
+
+Continue with the remaining repo if only one was skipped.
+
+### Error handling
+
+If a `git clone` fails: show the exact error output, then ask:
+> `❌ Could not clone {repo-name}. Would you like to retry? (y/n)`
+
+- If "y" → retry once.
+- If "n" or second failure → skip that repo and continue.
+
+### Confirmation output
+
+```
+✅ Base repositories cloned into: <resolved-project-root>/apps/
+
+  Frontend  →  apps/Frontend   (https://github.com/SiesaTeams/BaseFrontend.git)
+  Backend   →  apps/Backend    (https://github.com/SiesaTeams/BaseBackend.git)
+
+Project structure is ready. Happy building! 🚀
+```
+
+Adapt the message if only one repo was cloned or if any were skipped.
+
+---
+
+## PHASE FINAL — Commit Phase 1 changes (MANDATORY LAST ACTION)
+
+After all workflow steps complete (including Step 1), inspect changes and commit.
+
+**1. Inspect repository state:**
+```bash
+git status --short
+git diff --stat
+```
+
+**2. Build commit message** using format:
+`[Phase 1 - Discovery] <brief description of what was produced>`
+
+Example: `[Phase 1 - Discovery] initialize project structure and clone base repositories`
+
+Write the message in the same language used throughout the conversation.
+
+**3. Commit via phase script:**
+```bash
+node _siesa-agents/scripts/phases/phase1.js --commit "<generated commit message>"
+```
+
+**4. Confirm to the user:**
+> `✅ Project initialization changes committed to Phase 1 (discovery) branch.`
+
+**This is the LAST action of the workflow. Do not execute any further steps after this commit.**

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "siesa-agents",
-  "version": "2.1.78",
+  "version": "2.1.79",
   "description": "Paquete para instalar y configurar agentes SIESA en tu proyecto",
   "main": "index.js",
   "bin": {