JaviMontano

Redacta agradecimientos post-proceso diferenciados por persona, evidencia de interaccion, voz de marca y lint offline contra FOMO, hustle, servilismo y promesas no verificables.

Optimiza CV y carta de presentacion para ATS, rol objetivo y voz de marca con lint offline de keywords, secciones, longitud, contacto y tono.

Cosecha aprendizajes, valida evidencia y produce un cierre de conversacion reproducible con handoff, riesgos y plan de actualizaciones durables.

Orchestrates JM-ADK Alfa repository maintenance in fixed safety phases: bootstrap, repo sync audit, local state preservation, isolated branch planning, selective import or consolidation planning, cleanup planning, validation gates, and closeout blockers.

Validates plugin directory layout against the official Claude Code plugin spec. Triggers: validate structure, check layout, directory audit, plugin skeleton check.

Validates frontmatter and body structure of all skills, agents, and commands in a plugin. Triggers: validate components, check frontmatter, component audit, skill validation.

Use when the user asks to "scan for secrets", "detect credentials", "sanitize sensitive data", "check for exposed passwords", "run security gate G0", or mentions secret detection, credential scanning, security gate G0, sensitive data masking, API key exposure, token detection.

Audit and improve repository structure: naming consistency, directory patterns, file organization, staleness detection. Auto-organization per Constitution XVIII. [EXPLICIT] Trigger: "repo organization", "structure audit", "naming consistency", "directory cleanup", "auto-organize"

This skill should be used when the user asks to "create a Sofka HTML document", "generate a branded report", "build an executive deliverable", "upgrade HTML to brand standards", "fix broken Sofka styles", "convert markdown to HTML", "batch convert deliverables to HTML", or mentions Sofka HTML, entregable, brand deliverable, Design System v5, Dark Authority, or any combination of Sofka + document/report/summary/analysis/roadmap. Also use when batch-upgrading existing HTML files to Sofka brand compliance, even if the user does not explicitly say "brand". Triggers on: convert to HTML, branded HTML, DS v5, markdown to HTML pipeline, Mermaid diagrams in HTML.

WCAG 2.1/2.2 compliance assessment — a11y testing strategy, remediation priorities, inclusive design. Use when the user asks to "audit accessibility", "assess WCAG compliance", "evaluate a11y", "review inclusive design", or mentions screen readers, ARIA, color contrast, keyboard navigation.

Adoption strategy design producing communication plan, training roadmap, resistance management tactics, and reinforcement mechanisms. Use when the user asks to "design adoption strategy", "plan change adoption", "communication plan", "training needs analysis", "resistance management", "adoption roadmap", "change communication", or mentions "post-implementation adoption", "user onboarding strategy", "technology adoption plan".

Use when the user asks to "assess agile maturity", "evaluate agile practices", "run agile readiness check", "benchmark Scrum adoption", or "audit agile capabilities". Activates when a stakeholder needs to measure agile adoption level, evaluate Scrum maturity, diagnose agile anti-patterns, compare agile readiness across teams, or baseline agile capability before a transformation initiative.

Audits existing AI system architectures against best practices — structural integrity, AI quality attributes, pattern adherence, anti-pattern detection, security compliance, and technical debt inventory. This skill should be used when the user asks to "audit AI architecture", "review ML system quality", "assess AI technical debt", "evaluate AI compliance", "detect AI anti-patterns", "review AI security posture", or mentions AI architecture review, AI system assessment, AI quality audit, drift monitoring audit, or AI governance review.

Guides implementation of AI system architectures — technology selection, pipeline implementation, model serving setup, monitoring deployment, and CI/CD automation. This skill should be used when the user asks to "implement AI architecture", "build ML pipeline", "set up model serving", "deploy AI system", "implement MLOps", "configure drift monitoring", "set up feature store", or mentions AI implementation plan, ML infrastructure setup, model deployment guide, RAG implementation, or agent framework setup.

AI Center services discovery — AI readiness assessment using MetodologIA AI SCALE methodology, use case portfolio prioritization, data readiness evaluation, model inventory, AI governance assessment, infrastructure evaluation, MetodologIA AI product integration, and AI adoption roadmap. Use when the user asks to "assess AI readiness", "evaluate AI maturity", "AI discovery", "AI use case prioritization", "MLOps assessment", "AI governance evaluation", "AI adoption roadmap", "AI strategy assessment", "evaluate AI infrastructure", "AI product fit", or mentions "AI SCALE", "responsible AI", "AI pilots", "ML pipeline", "AI Center of Excellence", "LLM adoption", "generative AI strategy".

Concept of Operations (CONOPS) for AI systems — system vision, stakeholder mapping, AI-human interaction spectrum, business value assessment, success metrics, and operational modes. This skill should be used when the user asks to "define the AI operational concept", "map AI stakeholders", "design AI-human interaction levels", "assess AI business value", "define AI success metrics", "plan AI operational modes", or mentions CONOPS, IEEE 1362, AI autonomy levels, AI value matrix, or AI system vision.

Create or update a CONSTITUTION.md that defines project governance — establishes coding standards, quality gates, TDD policy, review requirements, and non-negotiable development principles with versioned amendment tracking. Use when defining project rules, setting up coding standards, establishing quality gates, configuring TDD requirements, or creating non-negotiable development principles.

Create a feature specification from a natural language description — generates user stories with Given/When/Then scenarios, functional requirements (FR-XXX), success criteria, and a quality checklist. Use when starting a new feature, writing a PRD, defining user stories, capturing acceptance criteria, or documenting requirements for a product idea.

Generate Gherkin .feature files from requirements before implementation — produces executable BDD scenarios with traceability tags, computes assertion integrity hashes, and locks acceptance criteria for test-driven development. Use when writing tests first, doing TDD, creating test cases from a spec, locking acceptance criteria, or setting up red-green-refactor with hash-verified assertions.

Validate cross-artifact consistency — checks that every spec requirement traces to tasks, plan tech stack matches task file paths, and constitution principles are satisfied across all artifacts. Use when running a consistency check, verifying requirements traceability, detecting conflicts between design docs, or auditing alignment before implementation begins.

Generate a technical design document from a feature spec — selects frameworks, defines data models, produces API contracts, and creates a dependency-ordered implementation strategy. Use when planning how to build a feature, writing a technical design doc, choosing libraries, defining database schemas, or setting up Tessl tiles for runtime library knowledge.

Generate quality checklists that validate requirements completeness, clarity, and consistency — produces scored checklist items linked to specific spec sections (FR-XXX, SC-XXX). Use when reviewing a spec for gaps, doing a requirements review, verifying PRD quality, auditing user stories and acceptance criteria, or gating before implementation.

Generate dependency-ordered task breakdown from plan and specification. Use when breaking features into implementable tasks, planning sprints, or creating work items with parallel markers.

Execute the implementation plan by coding each task from tasks.md — writes source files, runs tests, verifies assertion integrity, and validates output against constitutional principles. Use when ready to build the feature, start coding, develop from the task list, or resume a partially completed implementation.

Create and replicate brand-ready MetodologIA HTML for webpages, web apps, and playbooks, respecting UX/UI guidelines and brand rules. Use when generating, scaffolding, replicating, extending, or reviewing MetodologIA-branded HTML/CSS documents or pages. Enforces the brand: no prices (Cotizacion tras Discovery), no 'gratis'/'sin compromiso', brand pun 'EstrategIA' with IA in gold, Poppins headings + Montserrat body, light-default web palette (neoswiss-v5) and dark-first rich palette for playbooks, trilingual ES/EN/PT, SVG icons (no emoji, no Tailwind), and WCAG AA. Includes a scaffolder (scaffold.py), a contract-driven brand+UX validator (brand_check.py) with stable rule IDs, a knowledge graph (contracts.json), a regression harness, and auditor agents. Triggers: build/replicate a MetodologIA page, landing, web app, dashboard, playbook, runbook, proposal, or branded document; check/audit brand compliance.

Add or maintain the trilingual ℹ info-icon modal system on a single metodologia.info page. Use when the user asks to add info-icons, info modals, glossary tooltips, or "explain-the-concept" affordances to a page, or to migrate a page's inline modal engine to the shared js/info-icons.js module. Drives one page at a time: inventory → trilingual glossary → dialog markup + shared engine → wire cards → verify (vitest + DOM-assert) → PR.

Writes testable acceptance criteria in Given/When/Then format, covering happy paths, edge cases, and error scenarios. Trigger: "acceptance criteria", "given when then", "write AC", "define done", "user story criteria".

Implement WCAG 2.1 AA / 2.2 accessibility: semantic HTML audit, ARIA implementation, keyboard navigation, screen reader testing, color contrast. Use when user asks to "implement accessibility", "fix a11y issues", "make WCAG compliant", or "audit for accessibility".

Produces Architecture Decision Records following the Nygard/MADR template with full context, consequences, and traceability. Trigger: "generate ADR", "document decision", "architecture decision record", "record this decision".

dbt-style transformations, dimensional data modeling, testing strategies, and documentation generation for analytics platforms. Trigger: "analytics engineering", "dbt", "data modeling", "dimensional model", "star schema", "data marts".

REST, GraphQL, and gRPC API governance, versioning strategy, rate limiting, and developer experience design. Trigger: "API architecture", "API design", "REST", "GraphQL", "gRPC", "API governance", "developer experience".

Contract-first API design producing OpenAPI specs, GraphQL schemas, or protobuf definitions with versioning strategy. Trigger: "design API", "OpenAPI spec", "GraphQL schema", "protobuf definition", "API contract".

Use when the user asks to "test a hypothesis", "validate assumptions through delivery", "run experiment-driven project", "design build-measure-learn cycles", "validate project assumptions", or mentions hypothesis-driven delivery, HDD, validated learning, experiment design, build-measure-learn. Triggers on: converts assumptions into testable hypotheses, designs minimum viable experiments, facilitates pivot-or-persevere decisions, documents validated learning, ranks hypotheses by risk and impact.

Use when the user asks to "plan change management", "implement ADKAR", "manage organizational change", "plan adoption", "design resistance management", or mentions OCM, organizational change management, ADKAR, change readiness, adoption planning. Triggers on: designs ADKAR-based change interventions, assesses change readiness, creates communication campaigns, builds training plans, manages resistance through structured interventions, measures adoption KPIs.

Use when the user asks to "plan staff augmentation", "source external resources", "plan contractor onboarding", "design nearshore team integration", "manage vendor staffing", or mentions staff augmentation, contractor sourcing, augmentation needs, external staffing, nearshore/offshore, resource augmentation strategy.

Use when the user asks to "plan capacity", "forecast resource demand", "analyze resource availability", "match supply to demand", or "model resource scenarios". Activates when a stakeholder needs to analyze resource supply vs demand, identify capacity gaps, detect over-allocations, build time-phased capacity models, or plan proactive hiring and cross-training decisions before bottlenecks impact delivery.

Análisis horizontal de estados financieros (P&L, Balance General, Flujo de Caja, notas/anexos) con comparación YoY de 2 períodos. Genera informes ejecutivos estandarizados para Junta Directiva y C-Level con variaciones absolutas, relativas, drivers de cambio, alertas y recomendaciones estratégicas. Usa esta skill SIEMPRE que el usuario mencione análisis horizontal, comparar estados financieros, variación año contra año, YoY, análisis de tendencias financieras, comparación de períodos, evolución financiera, cambios interanuales, delta financiero, o adjunte cualquier estado financiero y pida análisis comparativo. Trigger: análisis horizontal, comparar estados financieros, YoY, variación interanual, evolución financiera, delta financiero, comparar períodos.

Use when the user asks to "analyze project inputs", "process documents", "extract requirements", "review project brief", "parse RFP content", or mentions input processing, document analysis, requirement extraction, project brief analysis. Triggers on: analyzes project input documents, extracts structured requirements from briefs, detects contradictions in source documents, normalizes project inputs for planning, produces input completeness scorecard.

Use when the user asks to "set up change control", "evaluate change requests", "manage scope changes", "establish CCB governance", or "process a change request". Activates when a stakeholder needs to establish a change control process, create change request templates, define CCB composition and decision criteria, evaluate change impact on scope/schedule/cost, or track change request trends across the project.

Use when the user asks to "define governance", "create governance model", "set up escalation paths", "design authority matrix", "establish decision framework", or mentions project governance, steering committee, decision framework, authority levels, escalation matrix. Triggers on: builds a governance charter, designs escalation paths, defines decision-making authority, creates steering committee structure, maps authority levels.

SDD Phase 0 — Define governance principles, coding standards, quality gates, and TDD policy. Enhanced: validates context.json, updates pipeline state, suggests workspace creation.

SDD Phase 1 — User Specs from natural language. FR-NNN, SC-NNN, acceptance scenarios. Enhanced: bug-fix intent detection, semantic diff on re-run, workspace RAG capture.

SDD Phase 2 — Technical Specs: architecture, data model, API contracts, technology decisions. Enhanced: Tessl tile discovery, context validation, schema enforcement.

SDD Phase 3 — BDD Analysis quality checklists. [GATE G1] Enhanced: mandatory gate enforcement, FR→plan alignment check.

SDD Phase 4 — Gherkin BDD test specs with cryptographic assertion hashing. Enhanced: SHA-256 hash generation, traceability tag validation, assertion integrity.

SDD Phase 5 — Dependency-ordered task breakdown with parallel markers and story labels.

SDD Phase 6 — Cross-artifact consistency validation, traceability FR→TS→Tasks. Enhanced: knowledge graph rebuild, orphan detection, health scoring.

SDD Phase 7 — Iterative TDD implementation with BDD verification chain. [GATE G2] Enhanced: mandatory gate, step coverage verification, assertion integrity, feature immutability.

Add or improve DUA (Diseno Universal de Aprendizaje) adaptations in educational content to meet the 2+ adaptations per activity requirement across 3 principles. Trigger on: adaptaciones DUA, universal design, mejorar accesibilidad, inclusion educativa, necesidades especiales, add adaptations.

Amplify a human author's draft to Scriba quality standards — add curriculum traceability, DUA adaptations, taxonomic annotations, and style corrections while preserving 100% of original content. Trigger on: amplificar borrador, amplify draft, mejorar borrador, enriquecer draft, version 1, draft humano, author draft, delegar version 1.

Audit cross-unit consistency for progressive complexity, terminological coherence, and sequential logic across multiple editorial units. Trigger on: auditoria consistencia, cross-unit audit, contradicciones terminologicas, progresion complejidad, coherencia editorial. Detects terminology contradictions, validates Bloom/Marzano progression curves, and classifies inconsistencies by severity. Essential for multi-unit textbook coherence and Gate G3 compliance.

Auto-calibrate Scriba session by detecting available documents, calculating priming level (COLD/WARM/HOT/DEEP), and restoring session state. Trigger on: calibrar, calibration, session state, detectar documentos, priming level, entorno, environment check.

Auto-generate RAG priming files from client documents (PDFs, HTMLs, Word files). Reads each document, extracts key knowledge, and creates structured priming files with evidence tags. Trigger on: priming, auto-prime, procesar documentos, generar RAG, extract knowledge, documentos del cliente.

Improve existing teacher guide by incorporating pedagogical review feedback, enhancing DUA adaptations, and updating rubrics. Trigger on: mejorar guia, evolucionar guia docente, actualizar DUA, enhance guide, update rubrics. Categorizes feedback into DUA/rubric/planning/methodology dimensions, applies changes preserving indicator coverage, enforces 2+ DUA adaptations per activity, and refines rubric descriptors. Prevents pedagogical regression during guide revision cycles.

Improve existing editorial unit by incorporating review feedback while preserving curriculum traceability and pedagogical structure. Trigger on: mejorar unidad, incorporar feedback, evolucionar contenido, revisar unidad, enhance unit. Categorizes feedback, applies corrections in priority order, tracks every change, and re-validates against acceptance criteria. Prevents traceability loss during revision cycles. Essential for iterative editorial quality improvement.

Export editorial content to branded Word document (.docx) using python-docx. Generates texto alumno and guia docente as separate files ready for layout team. Trigger on: exportar docx, export word, generar word, documento word, maquetacion, docx, enviar a diagramacion.

Create or update a CONSTITUTION.md that defines project governance — establishes coding standards, quality gates, TDD policy, review requirements, and non-negotiable development principles with versioned amendment tracking. Use when defining project rules, setting up coding standards, establishing quality gates, configuring TDD requirements, or creating non-negotiable development principles.

Create a feature specification from a natural language description — generates user stories with Given/When/Then scenarios, functional requirements (FR-XXX), success criteria, and a quality checklist. Use when starting a new feature, writing a PRD, defining user stories, capturing acceptance criteria, or documenting requirements for a product idea.

Generate a technical design document from a feature spec — selects frameworks, defines data models, produces API contracts, and creates a dependency-ordered implementation strategy. Use when planning how to build a feature, writing a technical design doc, choosing libraries, defining database schemas, or setting up Tessl tiles for runtime library knowledge.

Generate quality checklists that validate requirements completeness, clarity, and consistency — produces scored checklist items linked to specific spec sections (FR-XXX, SC-XXX). Use when reviewing a spec for gaps, doing a requirements review, verifying PRD quality, auditing user stories and acceptance criteria, or gating before implementation.

Generate Gherkin .feature files from requirements before implementation — produces executable BDD scenarios with traceability tags, computes assertion integrity hashes, and locks acceptance criteria for test-driven development. Use when writing tests first, doing TDD, creating test cases from a spec, locking acceptance criteria, or setting up red-green-refactor with hash-verified assertions.

Generate dependency-ordered task breakdown from plan and specification. Use when breaking features into implementable tasks, planning sprints, or creating work items with parallel markers.

Validate cross-artifact consistency — checks that every spec requirement traces to tasks, plan tech stack matches task file paths, and constitution principles are satisfied across all artifacts. Use when running a consistency check, verifying requirements traceability, detecting conflicts between design docs, or auditing alignment before implementation begins.

Execute the implementation plan by coding each task from tasks.md — writes source files, runs tests, verifies assertion integrity, and validates output against constitutional principles. Use when ready to build the feature, start coding, develop from the task list, or resume a partially completed implementation.

Create or update a CONSTITUTION.md that defines project governance — establishes coding standards, quality gates, TDD policy, review requirements, and non-negotiable development principles with versioned amendment tracking. Use when defining project rules, setting up coding standards, establishing quality gates, configuring TDD requirements, or creating non-negotiable development principles.

Create a feature specification from a natural language description — generates user stories with Given/When/Then scenarios, functional requirements (FR-XXX), success criteria, and a quality checklist. Use when starting a new feature, writing a PRD, defining user stories, capturing acceptance criteria, or documenting requirements for a product idea.

Generate a technical design document from a feature spec — selects frameworks, defines data models, produces API contracts, and creates a dependency-ordered implementation strategy. Use when planning how to build a feature, writing a technical design doc, choosing libraries, defining database schemas, or setting up Tessl tiles for runtime library knowledge.

Generate quality checklists that validate requirements completeness, clarity, and consistency — produces scored checklist items linked to specific spec sections (FR-XXX, SC-XXX). Use when reviewing a spec for gaps, doing a requirements review, verifying PRD quality, auditing user stories and acceptance criteria, or gating before implementation.

Generate Gherkin .feature files from requirements before implementation — produces executable BDD scenarios with traceability tags, computes assertion integrity hashes, and locks acceptance criteria for test-driven development. Use when writing tests first, doing TDD, creating test cases from a spec, locking acceptance criteria, or setting up red-green-refactor with hash-verified assertions.

Generate dependency-ordered task breakdown from plan and specification. Use when breaking features into implementable tasks, planning sprints, or creating work items with parallel markers.

Validate cross-artifact consistency — checks that every spec requirement traces to tasks, plan tech stack matches task file paths, and constitution principles are satisfied across all artifacts. Use when running a consistency check, verifying requirements traceability, detecting conflicts between design docs, or auditing alignment before implementation begins.

Execute the implementation plan by coding each task from tasks.md — writes source files, runs tests, verifies assertion integrity, and validates output against constitutional principles. Use when ready to build the feature, start coding, develop from the task list, or resume a partially completed implementation.

Operate the JM Labs local admin dashboard and its repair surface. Use whenever the task mentions `dashboard.html`, `admin-app`, `dashboard-doctor.sh`, `dashboard-repair.sh`, the local mini app server, task admin views, filesystem inspection, or safe MCP/config visibility.

Audit parity between the JM Labs core contracts and the live Claude Desktop or Codex environment. Use whenever MCPs, plugins, connectors, local overlays, NotebookLM, Tessl, admin dashboard health, task orchestration scripts, or readiness claims are involved, especially before declaring the workspace healthy.

Curate durable `rag-memory-*` files for JM Labs tasks. Use whenever an input, attachment, ephemeral note, conversation snippet, or admin repair step must be preserved so the workspace can recover context even if the original artifact disappears.

Govern the JM Labs persistent task filesystem and intake workflow. Use whenever the task mentions `workspaces/tasks`, `tasklog.md`, `rag-memory-*`, task intake, task close, task resume, ambiguous inputs, session-state orchestration, or the rule that every new work input must be recoverable from disk.

Govern changes to the JM Labs Claude Desktop workspace ecosystem. Use whenever a task touches bootstrap, refresh, sync, export, local overlays, repo-local skills or agents, `workspaces/tasks`, generated `tasklog.md`, task intake flows, or when you need to decide whether an artifact belongs in the core, the workspace instance, or ignored local state.

MetodologIA commercial proposal engine — bilingual (ES+EN), multi-format, brand-resolved. Activate whenever the user mentions: proposal, quote, offer, budget for a client, pitch, commercial presentation, "design a service", "handle this request", "adapt for this client", "innovate a service", "white-label for partner", "co-brand with X", "new service variant", or any document intended to sell or scope a MetodologIA service. Operates in THREE MODES: — STANDARD: existing catalog service, derive correct version per audience/segment — INNOVATION: new service or variant designed from canonical building blocks — CATALOG EDIT: add/modify a service or condition without generating a proposal Default output: 10 files per proposal (HTML·DOCX·XLSX·PPTX·MD × ES+EN + verification report). Branding resolved at runtime: own | cobrand | whitelabel. Language: follows user's conversation language; scaffolding is English.

MetodologIA commercial proposal engine — bilingual (ES+EN), multi-format, brand-resolved. Activate whenever the user mentions: proposal, quote, offer, budget for a client, pitch, commercial presentation, "design a service", "handle this request", "adapt for this client", "innovate a service", "white-label for partner", "co-brand with X", "new service variant", or any document intended to sell or scope a MetodologIA service. Operates in THREE MODES: — STANDARD: existing catalog service, derive correct version per audience/segment — INNOVATION: new service or variant designed from canonical building blocks — CATALOG EDIT: add/modify a service or condition without generating a proposal Default output: 10 files per proposal (HTML·DOCX·XLSX·PPTX·MD × ES+EN + verification report). Branding resolved at runtime: own | cobrand | whitelabel. Language: follows user's conversation language; scaffolding is English.

Motor de propuestas comerciales MetodologIA — universal (Claude Desktop, Claude Code, Cowork). ACTIVAR cuando el usuario mencione: propuesta, cotización, oferta, presupuesto para cliente, armar pitch, presentación comercial, servicio nuevo, variante de servicio, "diseñar algo a medida", "innovar un servicio", "adaptar para este cliente", "atender este requerimiento", o cualquier solicitud de documento comercial o creación de servicio. Opera en DOS MODOS: — MODO ESTÁNDAR: propuesta basada en servicios existentes del catálogo — MODO INNOVACIÓN: diseño de servicio nuevo o variante a medida, partiendo del catálogo como base Por DEFAULT genera paquete bilingüe completo ES+EN en todos los formatos simultáneamente: HTML · DOCX · XLSX (pricing) · PPTX · Markdown Incluye verificación legal y de marca antes de toda entrega. Nunca compromete lo que no está en el canónico. Nunca sobre-expone legalmente. Siempre atractivo, siempre vendedor, siempre dentro del marco.

This skill should be used when the user asks to "generar canonico", "derivar documento", "verificar catalogo", "proponer servicio", "auditar texto comercial", "crear version ejecutiva/comercial/inexperto", "revisar precios", "verificar brand safety", "generar servicio a medida", "innovar servicio", "verificar compromisos legales", or mentions any document of the MetodologIA service catalog (canonicos, derivadas, guias, anexos). Orchestrates ALL operations on the MetodologIA service catalog: creation, derivation, verification, innovation, legal/commercial safety review, and brand compliance. Use this skill whenever the user references MetodologIA services, catalog documents, pricing, editorial guidelines, service proposals, or any combination thereof — even if they don't say "catalogo" explicitly.

MetodologIA commercial proposal engine — bilingual (ES+EN), multi-format, brand-resolved. Activate whenever the user mentions: proposal, quote, offer, budget for a client, pitch, commercial presentation, "design a service", "handle this request", "adapt for this client", "innovate a service", "white-label for partner", "co-brand with X", "new service variant", or any document intended to sell or scope a MetodologIA service. Operates in THREE MODES: — STANDARD: existing catalog service, derive correct version per audience/segment — INNOVATION: new service or variant designed from canonical building blocks — CATALOG EDIT: add/modify a service or condition without generating a proposal Default output: 10 files per proposal (HTML·DOCX·XLSX·PPTX·MD × ES+EN + verification report). Branding resolved at runtime: own | cobrand | whitelabel. Language: follows user's conversation language; scaffolding is English.

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"

Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD"

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Validate a PRD against standards. Use when the user says "validate this PRD" or "run PRD validation"