arkaos 4.7.1 → 4.8.0

package/departments/dev/skills/security-compliance/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: dev/security-compliance
 description: >
-  Security audit preparation, ISMS gap analysis, control assessment, and ISO 27001 certification support for engineering teams.
+  Security audit preparation and ISO 27001 certification support: ISMS gap
+  analysis against clauses 4-10, Annex A control assessment (93 controls),
+  maturity scoring, evidence collection, and finding classification
+  (major/minor NC). TRIGGER: "compliance", "ISO 27001", "ISMS", "auditoria de
+  certificação", "gap analysis de segurança", "audit readiness", "/dev
+  security-compliance". SKIP: hands-on technical vulnerability audit ->
+  dev/security-audit (code and config, not the management system); SOC 2 or
+  GDPR programmes -> ops skills arka-soc2-compliance / arka-gdpr-compliance.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/dev/skills/skill-audit/SKILL.md

@@ -1,7 +1,15 @@
 ---
 name: dev/skill-audit
 description: >
-  Audit AI agent skills for security vulnerabilities: prompt injection, code execution, data leakage, supply chain risks.
+  Audit AI agent skill directories for security risks BEFORE installation
+  (OWASP LLM Top 10): code execution patterns (eval, shell injection,
+  exfiltration), prompt injection in SKILL.md, supply chain risks
+  (typosquatting, unpinned deps), and filesystem violations — PASS/WARN/FAIL
+  verdict. TRIGGER: "skill audit", "audita esta skill", "is this skill safe",
+  "verifica a skill antes de instalar", "scan the skill", "/dev skill-audit".
+  SKIP: securing your own AI application or agents -> dev/ai-security (your
+  system, not third-party skills); project dependency CVEs ->
+  dev/dependency-audit.
 allowed-tools: [Read, Bash, Grep, Glob, Agent]
 ---
 

package/departments/dev/skills/spec/SKILL.md

@@ -1,20 +1,17 @@
 ---
 name: arka-dev-spec
 description: >
-  Spec-driven development gate, constitution MUST rule spec-driven (Constitution #7 — no code
-  without an approved spec): creates, validates, and manages feature
-  specifications with the Living Specs engine (core/specs/), covering scope,
-  acceptance criteria, data model, API contracts, UI/UX requirements, edge
-  cases, and test scenarios. TRIGGER: "spec", "specification",
-  "requirements", "requisitos", "define feature", "write spec", "escreve a
-  spec", "critérios de aceitação", "describe what to build", "/dev spec";
-  auto-invoked as Phase 0 of every code-modifying dev workflow (/dev
-  feature, /dev api, /dev db, code-modifying /dev do) — load BEFORE writing
-  any code. SKIP: multi-agent planning, complexity escalation, or "how do
-  we execute this" -> /arka-forge (the Forge plans the WORK; spec defines
-  the WHAT — requirements and acceptance criteria); reviewing existing code
-  -> dev/code-review; /dev debug and /dev refactor operate on existing code
-  and need no new spec.
+  Spec-driven development gate, constitution MUST rule spec-driven
+  (Constitution #7 — no code without an approved spec): creates, validates,
+  and manages feature specifications with the Living Specs engine
+  (core/specs/) — scope, acceptance criteria, data model, API contracts,
+  edge cases, test scenarios. TRIGGER: "spec", "requirements", "requisitos",
+  "write spec", "escreve a spec", "critérios de aceitação", "/dev spec";
+  auto-invoked as Phase 0 of every code-modifying dev workflow — load BEFORE
+  writing any code. SKIP: multi-agent planning or "how do we execute this"
+  -> /arka-forge (the Forge plans the WORK; spec defines the WHAT);
+  reviewing existing code -> dev/code-review; /dev debug and /dev refactor
+  operate on existing code and need no new spec.
 ---
 
 # Spec-Driven Development — ARKA OS Dev Department

package/departments/dev/skills/stack-check/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: dev/stack-check
 description: >
-  Audit current tech stack: versions, dependencies, security, performance, upgrade paths.
+  Audit the current tech stack through a 12-Factor lens: framework and runtime
+  versions, dependency health, security posture, performance, and upgrade
+  paths — outputs a stack health report with upgrade recommendations and risk
+  assessment. TRIGGER: "stack check", "audita o stack", "are we outdated",
+  "devíamos atualizar o Laravel", "upgrade path", "tech stack review", "/dev
+  stack-check". SKIP: CVE/license-focused package analysis ->
+  dev/dependency-audit (deps only; stack-check is holistic); accumulated code
+  debt scoring -> dev/tech-debt.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/dev/skills/tdd-cycle/SKILL.md

@@ -1,8 +1,14 @@
 ---
 name: dev/tdd-cycle
 description: >
-  Test-Driven Development using Kent Beck's Red-Green-Refactor cycle.
-  Write failing test first, minimal code to pass, then refactor.
+  Test-Driven Development with Kent Beck's Red-Green-Refactor cycle: write the
+  failing test first, minimum code to pass, refactor on green — enforces the
+  testing pyramid (70/20/10) and >= 80% coverage across
+  PHPUnit/Pest/Vitest/Jest/pytest/Playwright. TRIGGER: "test", "TDD", "escreve
+  os testes", "write tests first", "cobertura de testes", "red green
+  refactor", "/dev test"; load BEFORE implementing feature code. SKIP:
+  clicking through a native app -> dev/app-test (exploratory, not automated
+  tests); planning a refactor's safety net -> dev/refactor-plan.
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob]
 ---
 

package/departments/dev/skills/tech-debt/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: dev/tech-debt
 description: >
-  Identify, classify, score, and prioritize technical debt. Generate remediation plans with cost-of-delay analysis.
+  Identify, classify, score, and prioritize technical debt (Ward Cunningham
+  metaphor + cost-of-delay): six debt categories, weighted severity scoring, a
+  prioritization matrix, and remediation plans tied to velocity and risk.
+  TRIGGER: "tech debt", "dívida técnica", "o código está uma confusão",
+  "prioritize cleanup", "TODOs everywhere", "/dev tech-debt". SKIP: planning
+  one specific refactoring with a test safety net -> dev/refactor-plan (the
+  execution plan; tech-debt is the inventory); dependency staleness only ->
+  dev/dependency-audit.
 allowed-tools: [Read, Bash, Grep, Glob, Agent]
 ---
 

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

@@ -1,7 +1,15 @@
 ---
 name: ecom/analytics
 description: >
-  E-commerce analytics: AOV, conversion rate, CLV, ROAS, cart abandonment rate.
+  E-commerce metrics analysis — AOV, conversion rate, CLV, ROAS, and cart
+  abandonment — delivered as a dashboard with funnel visualization and
+  benchmark comparison, plus browser verification that GA4, Meta Pixel, and
+  GTM tracking fire correctly. TRIGGER: "métricas da loja", "qual é o AOV",
+  "store analytics", "conversion rate da loja", "verifica o tracking GA4",
+  "/ecom analytics". SKIP: cross-channel campaign reporting ->
+  marketing/analytics-report (campaign-level, not store-level metrics);
+  diagnosing WHY conversion is low and building a test backlog
+  -> ecom/cro-optimize (research-driven optimization, not measurement).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/browse-competitor/SKILL.md

@@ -1,9 +1,16 @@
 ---
 name: ecom/browse-competitor
 description: >
-  Navigate a competitor's e-commerce site and extract structured intelligence:
-  product categories, price ranges, promotions, layout patterns, and screenshots.
-  Requires browser integration (claude --chrome or /chrome).
+  Navigates a competitor's e-commerce site with browser integration and
+  extracts structured intelligence — product categories, price ranges,
+  promotions, layout patterns, payment and shipping info — with screenshots
+  into an Obsidian report; falls back to WebFetch when no browser is
+  available. TRIGGER: "espia a loja do concorrente", "analisa o site da
+  concorrência", "browse competitor store", "vê os preços deles", "/ecom
+  browse-competitor <url>". SKIP: strategic competitive landscape without live
+  navigation -> marketing/competitor-analysis (research-based positioning, no
+  browser needed); auditing YOUR OWN store -> ecom/store-audit (5-agent audit
+  of the store you control).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

package/departments/ecom/skills/cart-recovery/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: ecom/cart-recovery
 description: >
-  Cart abandonment email sequence: 3 emails (1h, 24h, 72h) with urgency escalation.
+  Designs a cart abandonment recovery email sequence — 3 emails at 1h, 24h,
+  and 72h with urgency escalation — delivering subject lines, body copy,
+  timing, and incentive strategy. TRIGGER: "carrinho abandonado", "recupera
+  carrinhos abandonados", "abandoned cart emails", "sequência de recuperação
+  de carrinho", "/ecom cart-recovery". SKIP: broader nurture or promotional
+  email flows -> landing/email-sequence (persuasion sequences beyond cart
+  abandonment); deciding WHICH customers to target by value first
+  -> ecom/rfm-segment (segmentation precedes the flow).
 allowed-tools: [Read, Write, Edit, Bash, Grep, Glob, Agent, WebFetch, WebSearch]
 ---
 

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]
 ---