arkaos 4.7.0 → 4.8.0

package/departments/ecom/skills/cro-optimize/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: ecom/cro-optimize
 description: >
-  Conversion Rate Optimization using CXL's ResearchXL framework.
-  6-phase research process before testing anything.
+  Conversion Rate Optimization using CXL's ResearchXL framework — 6 research
+  phases (heuristic, technical, analytics, heatmaps, surveys, user testing)
+  before any test, PIE/ICE prioritization, delivering research findings plus a
+  prioritized test backlog and hypotheses for the top 3 tests. TRIGGER:
+  "otimiza a conversão da loja", "a loja não converte", "CRO", "improve store
+  conversion", "porque é que ninguém compra", "/ecom cro <page>". SKIP:
+  optimizing a standalone landing page or funnel step -> landing/optimize-page
+  (page-level persuasion, not store-wide research); measuring funnel metrics
+  without optimizing -> ecom/analytics (measurement, not experimentation).
 allowed-tools: [Read, Write, Edit, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/customer-journey/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: ecom/customer-journey
 description: >
-  Customer journey mapping: discovery, consideration, purchase, delivery, loyalty.
+  Maps the e-commerce customer journey across discovery, consideration,
+  purchase, delivery, and loyalty stages, producing a journey map with
+  touchpoints, pain points, and optimization opportunities per stage. TRIGGER:
+  "jornada do cliente", "mapeia a experiência do cliente", "customer journey
+  map", "touchpoints da loja", "/ecom journey <segment>". SKIP: scoring
+  customers by purchase behaviour -> ecom/rfm-segment (data segmentation, not
+  experience mapping); fixing a specific conversion drop-off
+  -> ecom/cro-optimize (research and testing, not mapping).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/ecommerce/SKILL.md

@@ -1,14 +1,15 @@
 ---
 name: arka-ecommerce
 description: >
-  E-commerce department. Full store audits with 5 parallel agents (UX, SEO, performance,
-  content, conversion), product listing optimization, pricing strategy analysis, store launch
-  plans, e-commerce ad campaigns, competitor analysis, e-commerce SEO audits, automated email
-  flows (cart abandonment, post-purchase, win-back), and store performance reports. Integrates
-  with Shopify MCP for direct product/order/customer management. All output saved to Obsidian.
-  Use when user says "ecom", "store", "product", "shop", "shopify", "ecommerce", "e-commerce",
-  "sales", "conversion", "pricing", "catalog", "inventory", "cart", "checkout", "listing",
-  or any online store task.
+  E-commerce department orchestrator (Ricardo's squad, 7-phase workflow with
+  mandatory Quality Gate) routing every store task: full audits, product
+  listings, pricing analysis, launch plans, ad campaigns, competitor analysis,
+  SEO, email flows, performance reports, and Shopify MCP management. TRIGGER:
+  "ecom", "a minha loja online", "shopify", "online store", "gere o catálogo",
+  "/ecom <command>". SKIP: an unambiguous single specialised task -> the
+  matching sibling wins directly, e.g. ecom/store-audit,
+  ecom/pricing-strategy, or ecom/cart-recovery (this skill is the
+  department router, not the specialist).
 ---
 
 # E-commerce Department — ARKA OS

package/departments/ecom/skills/fulfillment-plan/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: ecom/fulfillment-plan
 description: >
-  Fulfillment strategy: model selection, logistics, returns, cost optimization.
+  Fulfillment strategy design — compares 3PL, FBA, and dropshipping models,
+  plans logistics, returns handling, and cost optimization, delivering a
+  fulfillment plan with model comparison, cost analysis, and SLA targets.
+  TRIGGER: "logística da loja", "como envio as encomendas", "fulfillment
+  plan", "3PL ou dropshipping", "gestão de devoluções", "/ecom fulfillment".
+  SKIP: operating a multi-vendor platform with sellers
+  -> ecom/marketplace-manage (seller operations, not own-store logistics); margin and cost
+  modelling in isolation -> finance/unit-economics (financial analysis, not
+  logistics design).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/marketplace-manage/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: ecom/marketplace-manage
 description: >
-  Marketplace operations: seller onboarding, commission models, quality control.
+  Marketplace operations (Marketplace Flywheel + Mirakl framework) — seller
+  onboarding, commission model design, and quality control, delivering an
+  operations plan with seller management and growth strategy. TRIGGER: "gerir
+  o marketplace", "onboarding de sellers", "marketplace commission model",
+  "controlo de qualidade dos vendedores", "/ecom marketplace <action>". SKIP:
+  own-store shipping and logistics -> ecom/fulfillment-plan (single-store
+  fulfillment, not multi-vendor operations); selling through TikTok Shop or
+  Instagram -> ecom/social-commerce (social platforms, not your own
+  marketplace).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/pricing-strategy/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: ecom/pricing-strategy
 description: >
-  Pricing strategy: value-based analysis, psychological pricing, competitor positioning.
+  E-commerce pricing strategy — value-based analysis, psychological pricing,
+  dynamic pricing, and competitor positioning, delivering a pricing
+  recommendation with competitor comparison and margin analysis. TRIGGER:
+  "define o preço do produto", "quanto devo cobrar", "pricing da loja",
+  "psychological pricing", "preço face à concorrência", "/ecom pricing
+  <product>". SKIP: recurring SaaS plan tiers -> saas/pricing-strategy
+  (subscription software economics, not physical SKUs); pricing inside a full
+  launch package -> ecom/product-launch (ships a 4-tier pricing ladder);
+  recurring commerce subscriptions -> ecom/subscription-model.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/product-launch/SKILL.md

@@ -1,9 +1,15 @@
 ---
 name: ecom/product-launch
 description: >
-  E-commerce product launch plan — positioning + pricing ladder + content
-  assets + channel mix + ad creative + day-by-day launch sequence + post-
-  launch optimisation triggers.
+  End-to-end e-commerce product launch package — positioning frame, 4-tier
+  pricing ladder with margin math, content asset inventory, channel-mix ramp,
+  day-by-day launch sequence (T-30 to T+14), inventory-aware demand curve, and
+  upfront kill-switch criteria. TRIGGER: "lançar um produto na loja", "plano
+  de lançamento do produto", "product launch plan", "launch this SKU", "/ecom
+  launch <product>". SKIP: launching a SaaS product -> saas/launch-execute
+  (software GTM, no physical inventory); a standalone pricing question ->
+  ecom/pricing-strategy; the promotional email/funnel sequence alone ->
+  landing/launch-sequence.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/rfm-segment/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: ecom/rfm-segment
 description: >
-  RFM customer segmentation: Recency, Frequency, Monetary analysis.
-  Identify Champions, At-Risk, and Hibernating customers with action plans.
+  RFM customer segmentation (Recency, Frequency, Monetary — Drew Sanocki):
+  scores customers 1-5 per dimension, identifies Champions, Loyal, At-Risk,
+  and Hibernating segments, applies the whale curve, and delivers an RFM
+  matrix with segment counts and an action plan plus automated flow per
+  segment. TRIGGER: "segmenta os clientes", "quem são os meus melhores
+  clientes", "RFM analysis", "clientes em risco", "/ecom rfm". SKIP:
+  demographic audience building for campaigns -> marketing/audience-segment
+  (targeting, not purchase-behaviour scoring); mapping the experience per
+  stage -> ecom/customer-journey; executing win-back emails -> ecom/cart-recovery.
 allowed-tools: [Read, Write, Edit, Agent, WebFetch]
 ---
 

package/departments/ecom/skills/social-commerce/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: ecom/social-commerce
 description: >
-  Social commerce strategy: platform selection, product feed, live commerce.
+  Social commerce strategy (TikTok Shop + Instagram Shopping) — platform
+  selection, product feed setup, and live commerce, delivering a plan with
+  platform setup, content strategy, and attribution. TRIGGER: "vender no
+  TikTok", "Instagram Shopping", "social commerce", "live shopping", "loja no
+  Instagram", "/ecom social-commerce". SKIP: organic social content and
+  posting cadence -> marketing/social-strategy (audience growth, not in-
+  platform selling); own-store conversion optimization -> ecom/cro-optimize
+  (store CRO, not social channels).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/store-audit/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: ecom/store-audit
 description: >
-  Full store audit: UX, SEO, performance, content, conversion with 5 parallel agents.
+  Full store audit with 5 parallel agents — UX, SEO, performance, content, and
+  conversion — including live browser checks of the checkout flow, mobile
+  responsiveness, and page speed, delivering a scored report with prioritized
+  fixes. TRIGGER: "audita a minha loja", "store audit", "analisa a loja
+  completa", "health check da loja", "/ecom audit <url>". SKIP: deep
+  conversion research with an A/B test backlog -> ecom/cro-optimize
+  (ResearchXL goes deeper than the audit's conversion pass); auditing a
+  competitor's store -> ecom/browse-competitor (their store, not yours); SEO-
+  only pass -> marketing/seo-audit.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/subscription-model/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: ecom/subscription-model
 description: >
-  Subscription model design: replenishment, curation, access, or SaaS+commerce.
+  Designs commerce subscription models (Subscription Economy — Tien Tzuo) —
+  replenishment, curation, access, or SaaS+commerce — delivering a spec with
+  pricing tiers, retention mechanics, and churn targets. TRIGGER: "modelo de
+  subscrição", "caixa mensal de produtos", "subscription box", "recorrência na
+  loja", "/ecom subscription <model>". SKIP: pure SaaS plan pricing ->
+  saas/pricing-strategy (software tiers, no physical goods); diagnosing
+  existing subscriber churn -> saas/churn-analysis (retention analytics, not
+  model design); one-off product pricing -> ecom/pricing-strategy.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/budget-plan/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: fin/budget-plan
 description: >
-  Budget planning: revenue plan, cost structure, headcount, CAPEX by department.
+  Budget planning with Helena (CFO): revenue plan, cost structure, headcount
+  and CAPEX by department using the FP&A cycle plus zero-based budgeting,
+  delivering an annual/quarterly budget with department breakdowns and
+  approval thresholds. TRIGGER: "orçamento anual", "orçamento do Q3",
+  "budget plan", "plano de custos por departamento", "headcount budget",
+  "/fin budget". SKIP: cash timing, runway or burn questions ->
+  fin/cashflow-forecast (forecasts cash movement, not spend allocation);
+  full P&L/Balance Sheet projections -> fin/financial-model (3-statement
+  modelling, not budget approval).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/cashflow-forecast/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: fin/cashflow-forecast
 description: >
-  Cash flow forecast: operating, investing, financing flows with runway calculation.
+  Cash flow forecasting across operating, investing and financing flows,
+  with runway, burn rate and working-capital analysis (Leonor, Financial
+  Analyst — Cash Flow Management + FP&A). TRIGGER: "cashflow forecast",
+  "previsão de tesouraria", "quanto runway temos", "burn rate", "fluxo de
+  caixa", "/fin cashflow". SKIP: allocating spend by department or
+  headcount -> fin/budget-plan (budgeting, not cash timing); full
+  3-statement projections -> fin/financial-model (cash flow is one
+  statement of three); stress-testing assumptions best/worst case ->
+  fin/scenario-analysis.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/ciso-advisor/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: finance/ciso-advisor
 description: >
-  Security budget justification, compliance roadmap, risk quantification
-  using ALE, and board-level security reporting.
+  CFO-side security economics: security budget justification via ALE risk
+  quantification (SLE x ARO), compliance roadmap sequencing (SOC 2 -> ISO
+  27001 -> GDPR), vendor risk tiering, security metrics dashboard, and
+  board-level reporting. TRIGGER: "justificar orçamento de segurança",
+  "security budget", "quanto custa SOC 2", "compliance roadmap", "risco em
+  euros", "ALE", "/fin ciso-advisor". SKIP: hands-on technical security
+  testing or code audit -> dev/security-audit (finds vulnerabilities; this
+  skill prices the risk); implementing compliance controls ->
+  dev/security-compliance.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/financial-model/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: fin/financial-model
 description: >
-  Build 3-statement financial models (P&L, Balance Sheet, Cash Flow) with
-  scenario analysis. Based on Damodaran methodology.
+  Builds 3-statement financial models — P&L, Balance Sheet, Cash Flow —
+  with base/optimistic/pessimistic scenarios, following Damodaran
+  methodology; outputs model tables, scenario comparison and a key-metrics
+  dashboard. TRIGGER: "modelo financeiro", "financial model", "projeções a
+  3 anos", "3-statement model", "modela o P&L", "/fin model". SKIP:
+  company worth or price -> fin/valuation-model (DCF/comps built on top of
+  the model); cash runway only -> fin/cashflow-forecast; standalone
+  what-if sensitivity -> fin/scenario-analysis (stresses assumptions,
+  doesn't build statements).
 allowed-tools: [Read, Write, Edit, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/pitch-deck/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: fin/pitch-deck
 description: >
-  Investor pitch deck financials: market size, traction, unit economics, ask.
+  Investor pitch deck financials with Rui (Investment Strategist): market
+  size, traction, unit economics, funding ask, projections and cap-table
+  impact, following the 10-slide Pitch Deck Framework + Venture Deals.
+  TRIGGER: "pitch deck", "slides para investidores", "quanto pedir na
+  ronda", "fundraising deck", "investor deck financials", "/fin pitch".
+  SKIP: computing the underlying CAC/LTV numbers -> fin/unit-economics
+  (this skill presents them); defending a valuation number ->
+  fin/valuation-model; building the projection model behind the slides ->
+  fin/financial-model.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/scenario-analysis/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: fin/scenario-analysis
 description: >
-  Financial scenario analysis: base, optimistic, pessimistic with sensitivity.
+  Financial scenario analysis: base, optimistic and pessimistic cases with
+  key-variable sensitivity and probability weighting (Monte Carlo +
+  Scenario Analysis, Leonor). TRIGGER: "análise de cenários", "e se as
+  vendas caírem 20%", "scenario analysis", "sensitivity analysis", "worst
+  case financeiro", "/fin scenario". SKIP: building the underlying
+  statements first -> fin/financial-model (scenarios stress an existing
+  model); strategic/market futures rather than financial numbers ->
+  strategy/scenario-plan (business scenarios, not P&L sensitivity).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/unit-economics/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: fin/unit-economics
 description: >
-  Unit economics analysis: CAC, LTV, payback, Rule of 40, NRR.
-  With SaaS benchmarks from KeyBanc and Meritech.
+  Unit economics analysis: CAC, LTV, LTV:CAC, payback, Rule of 40, NRR,
+  burn multiple and magic number, benchmarked against KeyBanc/Meritech
+  private-SaaS quartiles, with a traffic-light dashboard and improvement
+  recommendations. TRIGGER: "unit economics", "qual é o nosso CAC", "LTV
+  to CAC", "payback period", "Rule of 40", "/fin unit-economics". SKIP:
+  ongoing KPI tracking and dashboard build -> saas/metrics-dashboard
+  (operational dashboard, not one-off diagnosis); fixing churn drivers
+  behind weak NRR -> saas/churn-analysis; setting price points ->
+  saas/pricing-strategy.
 allowed-tools: [Read, Write, Edit, Agent, WebFetch, WebSearch]
 ---
 

package/departments/finance/skills/valuation-model/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: fin/valuation-model
 description: >
-  Company valuation: DCF with WACC, comparable company analysis, precedent transactions.
+  Company valuation: DCF with WACC (Damodaran), comparable company
+  analysis and precedent transactions, producing a valuation range with
+  multiples and sensitivity analysis. TRIGGER: "quanto vale a empresa",
+  "valuation", "avaliação da empresa", "DCF", "múltiplos comparáveis",
+  "/fin valuation". SKIP: building the projections the DCF discounts ->
+  fin/financial-model (valuation consumes its outputs); designing the
+  business model itself -> strategy/bmc (Business Model Canvas, not
+  enterprise value); presenting the number to investors ->
+  fin/pitch-deck.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/ai-research/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: kb/ai-research
 description: >
-  AI-augmented research: use Perplexity, Elicit, Claude for source gathering and synthesis.
+  AI-augmented research: uses Perplexity, Elicit, and Claude for source gathering
+  and synthesis, delivering a research report with CRAAP-rated sources and
+  synthesized findings. TRIGGER: "pesquisa com AI", "usa o Perplexity para
+  investigar", "AI research on this topic", "gather sources with AI tools",
+  "/kb ai-research <topic>". SKIP: full research methodology from question
+  definition to synthesis -> kb/research-plan (owns the 5-step process; this
+  skill is its AI-tooling arm); digging into a named competitor ->
+  kb/competitive-intel (structured competitor profile, not open research).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/competitive-intel/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: kb/competitive-intel
 description: >
-  Competitive intelligence: product, pricing, positioning, marketing, team, funding.
+  Competitive intelligence on a named competitor — product, pricing, positioning,
+  marketing, team, funding — delivered as a competitive profile in Obsidian with
+  a battlecard. TRIGGER: "analisa este concorrente", "perfil do concorrente X",
+  "competitive intel on X", "build a battlecard", "/kb intel <competitor>".
+  SKIP: marketing-channel and campaign comparison -> marketing/competitor-analysis
+  (channel lens, not full-company profile); hands-on walkthrough of a competitor
+  store -> ecom/browse-competitor (live browsing, not desk research);
+  industry-level structure -> strategy/five-forces (market forces, not one company).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/knowledge/SKILL.md

@@ -1,15 +1,16 @@
 ---
 name: arka-knowledge
 description: >
-  Dynamic knowledge base powered by Obsidian. Async background processing: queues YouTube
-  downloads, transcribes with Whisper (local or API), and pauses for interactive analysis.
-  Runs 5 parallel analysis agents (Frameworks, Strategy, Voice & Style, Principles, Topics)
-  to build expert personas. Learns from articles and URLs. Creates searchable persona profiles,
-  topic cross-references, and source catalogs. Generates content in any learned persona's voice
-  and style. All output organized in Obsidian vault with MOC pages.
-  Use when user says "kb", "learn", "persona", "knowledge", "youtube", "transcribe", "article",
-  "research", "analyze", "source", "topic", "search knowledge", "write as", "queue", "process",
-  "capabilities", or wants to learn from any content source or use a persona's expertise.
+  Knowledge Base department entry point powered by Obsidian: queues YouTube
+  downloads, transcribes with Whisper, runs 5 parallel analysis agents to
+  build expert personas, and manages the job queue, KB search, and
+  persona-voice content — all output to the vault with MOC pages.
+  TRIGGER: "processa este artigo", "mostra a fila", "search knowledge",
+  "/kb learn", "/kb queue", "/kb process". SKIP: ingesting ONE specific
+  source end-to-end (a single video/article/PDF, no queue) -> kb/learn-content
+  (this umbrella owns the queue and multi-source flow); deep research on an
+  open question -> kb/research-plan (methodology, not ingestion); building a
+  production callable advisor -> kb/persona-build (cited beliefs and DNA).
 ---
 
 # Knowledge Base — ARKA OS Department

package/departments/kb/skills/knowledge-review/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: kb/knowledge-review
 description: >
-  Knowledge freshness review: identify stale notes, update summaries, fix broken links.
+  Knowledge freshness review of the Obsidian vault: identifies stale notes,
+  updates progressive summaries, and fixes broken links, producing a review
+  report with actions taken. TRIGGER: "revê a base de conhecimento", "notas
+  desatualizadas", "review the vault", "fix broken links in the KB", "/kb review".
+  SKIP: reorganising tags, categories, or naming -> kb/taxonomy-manage
+  (structure, not freshness); building an index page for a grown topic
+  cluster -> kb/moc-create (creates MOCs rather than auditing note health).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/learn-content/SKILL.md

@@ -1,7 +1,17 @@
 ---
 name: kb/learn-content
 description: >
-  Ingest content (YouTube, article, PDF): download, transcribe, analyze with 5 agents.
+  Ingests a content source (YouTube video, article, PDF): downloads, transcribes,
+  and analyzes it with 5 parallel agents, storing frameworks, insights, and
+  cross-references in Obsidian. TRIGGER: "aprende com este vídeo", "ingere este
+  artigo", "learn from this URL", "transcribe and analyze this podcast",
+  "/kb learn <url>". SKIP: managing the ingestion QUEUE, KB search, or a
+  multi-source persona build -> kb/knowledge (the department umbrella; this
+  skill handles ONE source end-to-end); turning raw notes into atomic
+  permanent notes -> kb/zettelkasten-process (note workflow, not source
+  ingestion); building a callable advisor from already-ingested content ->
+  kb/persona-build; investigating an open question -> kb/research-plan
+  (research, not ingestion).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/moc-create/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: kb/moc-create
 description: >
-  Create or update a Map of Content when a topic cluster reaches 10+ notes.
+  Creates or updates a Map of Content (LYT, Nick Milo) when a topic cluster
+  reaches 10+ notes, producing an Obsidian MOC page with linked notes organized
+  by subtopic. TRIGGER: "cria um MOC", "organiza este cluster de notas",
+  "map of content for X", "index this topic", "/kb moc <cluster>". SKIP:
+  renaming tags or restructuring categories vault-wide -> kb/taxonomy-manage
+  (taxonomy hierarchy, not topic index pages); auditing note freshness and
+  broken links -> kb/knowledge-review (health check, not organization).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/persona-build/SKILL.md

@@ -1,10 +1,15 @@
 ---
 name: kb/persona-build
 description: >
-  Build or refine a callable persona from KB content. Extracts beliefs, voice
-  signature, expertise domains, decision patterns, and the 4-framework
-  behavioral DNA (DISC + Enneagram + Big Five + MBTI). Produces a callable
-  advisor YAML.
+  Builds or refines a callable persona from KB content: source inventory, cited
+  belief inventory, voice signature, expertise map, decision patterns, and
+  4-framework behavioral DNA (DISC + Enneagram + Big Five + MBTI), shipped as
+  a callable advisor YAML. TRIGGER: "cria uma persona do X", "constrói o
+  advisor", "build a persona from these sources", "extract his voice and
+  beliefs", "/kb persona <name>". SKIP: writing content in an existing
+  persona's voice -> kb/write-as-persona (uses a persona, does not build one);
+  ingesting new source material first -> kb/learn-content (ingestion precedes
+  persona extraction).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/research-plan/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: kb/research-plan
 description: >
-  Plan and execute research with source evaluation (CRAAP test),
-  synthesis, and Obsidian documentation.
+  Plans and executes structured research: defines the question, gathers
+  academic/industry/expert sources, evaluates them with the CRAAP test,
+  synthesizes findings, and documents everything in Obsidian. TRIGGER: "faz
+  research sobre X", "investiga este tema a fundo", "research plan for X",
+  "plan a literature review", "/kb research <topic>". SKIP: AI-tool-driven
+  source gathering (Perplexity, Elicit) -> kb/ai-research (the AI-tooling arm
+  of this process); rating a single source -> kb/source-evaluate (one CRAAP
+  score, not a full study); competitor dossiers -> kb/competitive-intel
+  (battlecards, not open research).
 allowed-tools: [Read, Write, Edit, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/search-kb/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: kb/search-kb
 description: >
-  Search the knowledge base: keyword, semantic, cross-reference across vault.
+  Searches the Obsidian knowledge base: keyword, semantic, and cross-reference
+  search across the vault, returning relevance-ranked results with related
+  notes. TRIGGER: "pesquisa na base de conhecimento", "procura no vault",
+  "search the KB for X", "what do we know about X", "/kb search <query>".
+  SKIP: gathering NEW external information the vault lacks -> kb/research-plan
+  (external research, not retrieval); reviewing or fixing stale notes that
+  search surfaces -> kb/knowledge-review (maintenance, not lookup).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/source-evaluate/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: kb/source-evaluate
 description: >
-  Evaluate source reliability: Currency, Relevance, Authority, Accuracy, Purpose.
+  Evaluates a single source's reliability with the CRAAP test — Currency,
+  Relevance, Authority, Accuracy, Purpose — producing a scored evaluation with
+  a reliability rating. TRIGGER: "avalia esta fonte", "esta fonte é fiável?",
+  "evaluate this source", "is this paper credible", "CRAAP test",
+  "/kb evaluate <source>". SKIP: a full research effort across multiple
+  sources with synthesis -> kb/research-plan (CRAAP is one step of its 5-step
+  process); ingesting the source into the vault once it passes ->
+  kb/learn-content (ingestion, not evaluation).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/taxonomy-manage/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: kb/taxonomy-manage
 description: >
-  Manage knowledge taxonomy: tags, categories, naming conventions, hierarchy.
+  Manages the knowledge base taxonomy: tags, categories, naming conventions,
+  and hierarchy, delivering an updated taxonomy document with tag guidelines
+  and category structure. TRIGGER: "organiza as tags do vault", "normaliza a
+  taxonomia", "clean up the KB tags", "define naming conventions",
+  "/kb taxonomy". SKIP: building an index page for one topic cluster ->
+  kb/moc-create (a MOC, not vault-wide structure); finding stale notes or
+  broken links -> kb/knowledge-review (content health, not classification).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/write-as-persona/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: kb/write-as-persona
 description: >
-  Write content in a learned persona's voice using their frameworks and style.
+  Writes content in a learned persona's voice, applying their frameworks,
+  style, and KB knowledge, with framework references in the output. TRIGGER:
+  "escreve como o X", "escreve na voz da persona", "write as <persona> about
+  X", "draft this in her style", "/kb write <persona> <topic>". SKIP: the
+  persona does not exist yet or needs refinement -> kb/persona-build (build
+  the advisor first); generic content without a persona voice ->
+  content/hook-write or the /content department skills (regular copy, not
+  persona mimicry).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/kb/skills/zettelkasten-process/SKILL.md

@@ -1,8 +1,15 @@
 ---
 name: kb/zettelkasten-process
 description: >
-  Process content through the Zettelkasten workflow: fleeting → literature → permanent notes.
-  Based on Niklas Luhmann's method, modernized by Sönke Ahrens.
+  Processes content through the Zettelkasten workflow (Luhmann/Ahrens):
+  fleeting -> literature -> permanent notes, enforcing atomic one-idea notes,
+  own-words rephrasing, and 2+ links per note in Obsidian. TRIGGER: "processa
+  estas notas", "transforma em notas permanentes", "zettelkasten this",
+  "make atomic notes from this reading", "/kb zettelkasten <note>". SKIP:
+  ingesting a new external source (video, PDF, URL) -> kb/learn-content
+  (download and transcribe pipeline comes first); creating an index once a
+  cluster reaches 10+ notes -> kb/moc-create (MOCs come after permanent notes
+  accumulate).
 allowed-tools: [Read, Write, Edit, Grep, Glob]
 ---
 

package/departments/landing/skills/ab-test/SKILL.md

@@ -1,7 +1,13 @@
 ---
 name: landing/ab-test
 description: >
-  A/B test plan: hypothesis, variants, sample size, duration, success criteria.
+  A/B test plan for landing page elements: hypothesis, control and variants,
+  sample size, test duration, and statistical significance criteria with
+  expected lift. TRIGGER: "A/B test", "teste A/B", "testa duas versões",
+  "split test", "qual headline converte melhor", "/landing test". SKIP:
+  full-page heuristic CRO diagnosis and test-backlog prioritisation ->
+  landing/optimize-page (it finds WHAT to test; this skill plans ONE test);
+  funnel-wide conversion numbers -> landing/funnel-metrics.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---