claude-code-arcane 2.3.0 → 2.5.0

package/docs/SKILLS-CATALOG.md

@@ -1,8 +1,8 @@
 # Skills Catalog — Claude Code Arcane
 
-Los 397 skills disponibles para proyectos consumidores, organizados por division.
+Los 427 skills disponibles para proyectos consumidores, organizados por division.
 
-La tabla cubre 355: hay 42 skills instalables que todavia no estan catalogados aca. Un test de CI (`src/__tests__/doc-counts.test.ts`) verifica que estos numeros coincidan con el filesystem y que el header de cada seccion coincida con sus filas.
+La tabla cubre 385: hay 42 skills instalables que todavia no estan catalogados aca. Un test de CI (`src/__tests__/doc-counts.test.ts`) verifica que estos numeros coincidan con el filesystem y que el header de cada seccion coincida con sus filas.
 
 ## Como ejecutar un skill
 
@@ -84,7 +84,7 @@ Desde cualquier proyecto que tenga Arcane configurado, escribi `/` seguido del n
 | `/consistency-check` | Detecta inconsistencias cross-documento en stats/items | `[full \| since-last \| entity:<name>]` |
 | `/doc-gdd` | Genera Game Design Document completo | `[game-name]` |
 | `/doc-pas` | Documentacion PAS (Problem-Analysis-Solution) | `[problem o decision title]` |
-| `/install-mcp` | Instala y registra el MCP de Unity (CoplayDev) en el proyecto | `[--secondary] [project-path]` |
+| `/install-mcp` | Conecta Claude con el MCP del engine: Unity (package UPM) o Unreal (plugins del engine) | `[unity\|unreal] [--secondary] [path]` |
 | `/map-systems` | Descompone concepto en sistemas, mapea dependencias | `[next \| system-name] [--review]` |
 | `/playtest-report` | Genera o analiza reporte de playtest | `[new\|analyze path] [--review]` |
 | `/scaffold-unity` | Scaffoldea proyecto Unity estilo Project_T | `[project-name]` |
@@ -100,6 +100,45 @@ Desde cualquier proyecto que tenga Arcane configurado, escribi `/` seguido del n
 
 ---
 
+## Unreal (30 skills)
+
+Instalables con el perfil `unreal-dev`. Procedencia y licencias en `ATTRIBUTION.md`.
+
+| Skill | Descripcion | Uso |
+|-------|-------------|-----|
+| `/ue-project-context` | Documento de contexto del proyecto: modulos, plataformas, convenciones, standards | `[new \| update \| section]` |
+| `/ue-naming-conventions` | Naming de assets y estructura de Content: Prefix_BaseAssetName_Variant_Suffix, prefijos por tipo, layout de carpetas | `[asset, folder o review]` |
+| `/ue-cpp-foundations` | UPROPERTY, UFUNCTION, UCLASS, TArray, TMap, delegates, FString, garbage collection | `[class, type o question]` |
+| `/ue-actor-component-architecture` | Diseno de actors y components: BeginPlay, Tick, attachment, ownership, child actors | `[actor o component]` |
+| `/ue-gameplay-framework` | GameMode, GameState, PlayerController, PlayerState, Pawn, HUD | `[class o flow]` |
+| `/ue-module-build-system` | Build.cs, Target.cs, creacion de modulos, setup de plugins, configuracion de build | `[module o plugin]` |
+| `/ue-async-threading` | Operaciones async, threading, ejecucion paralela, tasks, FRunnable, AsyncTask | `[operation o task]` |
+| `/ue-blueprints` | Blueprint visual scripting: Event Graph, Construction Script, Cast vs Interface vs Dispatcher | `[blueprint o graph]` |
+| `/ue-gameplay-abilities` | GAS: Gameplay Abilities, Effects, Attribute Sets, Tags, Gameplay Cues | `[ability, effect o attribute]` |
+| `/ue-character-movement` | CharacterMovementComponent, movement modes, root motion, network prediction | `[movement mode o feature]` |
+| `/ue-animation-system` | AnimInstance, montages, blend spaces, state machines, notifies, linked anim graphs | `[character o anim feature]` |
+| `/ue-physics-collision` | Colisiones, traces, simulacion fisica, interacciones, Chaos physics | `[interaction o collision setup]` |
+| `/ue-game-features` | Game Feature plugins, modular gameplay, GameFeatureAction, ComponentManager | `[plugin o experience]` |
+| `/ue-networking-replication` | Multiplayer: replication, RPCs, net roles, autoridad server/client | `[system o property]` |
+| `/ue-ai-navigation` | AI controllers, behavior trees, blackboards, perception, NavMesh, EQS | `[behavior o AI feature]` |
+| `/ue-state-trees` | State Tree, state machines, StateTreeTask, Condition, Evaluator | `[state tree o behavior]` |
+| `/ue-mass-entity` | Mass Entity: MassProcessor, MassFragment, MassTag, MassObserver (UE 5.5+) | `[system o entity type]` |
+| `/ue-materials-rendering` | Materials, shaders, dynamic instances, post-process, render targets, Nanite, Lumen | `[material o effect]` |
+| `/ue-niagara-effects` | Niagara: sistemas de particulas, VFX, emitters, data interfaces, simulacion GPU | `[effect o system]` |
+| `/ue-audio-system` | UAudioComponent, SoundCue, MetaSound, atenuacion, concurrencia, analisis | `[sound o audio system]` |
+| `/ue-sequencer-cinematics` | Sequencer, LevelSequence, cutscenes, camera tracks, Movie Render Queue | `[sequence o shot]` |
+| `/ue-world-level-streaming` | World Partition, level streaming, level travel, data layers, world subsystems | `[level o streaming strategy]` |
+| `/ue-procedural-generation` | PCG framework, ProceduralMesh, instanced mesh, generacion en runtime, noise | `[generator o PCG graph]` |
+| `/ue-data-assets-tables` | DataAsset, DataTable, soft references, TSoftObjectPtr, async loading, Asset Manager | `[data type o asset]` |
+| `/ue-serialization-savegames` | Save/load, persistencia de progreso, serializacion de datos, FArchive | `[save system o data]` |
+| `/ue-ui-umg-slate` | UMG, Slate, UserWidget, HUD, BindWidget, Common UI, MVVM | `[widget o UI flow]` |
+| `/ue-input-system` | Enhanced Input: Input Actions, Mapping Contexts, modifiers, triggers | `[action o input scheme]` |
+| `/ue-editor-tools` | Editor utility widgets, Blutility, detail customization, property editors, subsystems | `[tool o customization]` |
+| `/ue-testing-debugging` | Automation tests, functional tests, UE_LOG, visual logger, debug drawing | `[test o debug target]` |
+| `/ue-packaging` | Packaging y cooking: build configs, Game Default Map, RunUAT BuildCookRun | `[platform o build config]` |
+
+---
+
 ## Audio (13 skills)
 
 | Skill | Descripcion | Uso |

package/docs/USER-GUIDE.md

@@ -2,7 +2,7 @@
 
 ## What is Arcane?
 
-Arcane is a configuration harness for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). It provides a curated library of **397 skills**, **106 agents**, **16 hooks**, and **27 rules** that you selectively deploy into any project. Instead of shipping everything to every project (wasting tokens and degrading performance), you pick a **profile** that matches your stack and only the relevant tools get installed.
+Arcane is a configuration harness for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). It provides a curated library of **427 skills**, **109 agents**, **17 hooks**, and **28 rules** that you selectively deploy into any project. Instead of shipping everything to every project (wasting tokens and degrading performance), you pick a **profile** that matches your stack and only the relevant tools get installed.
 
 ## Table of Contents
 
@@ -11,8 +11,7 @@ Arcane is a configuration harness for [Claude Code](https://docs.anthropic.com/e
 - [Quick Start](#quick-start)
 - [Commands Reference](#commands-reference)
 - [Profiles](#profiles)
-  - [Base Profiles](#base-profiles)
-  - [Add-on Profiles](#add-on-profiles)
+  - [Profile Catalog](#profile-catalog)
   - [Core (always included)](#core-always-included)
 - [Profile Composition](#profile-composition)
 - [Adding and Removing Skills](#adding-and-removing-skills)
@@ -65,7 +64,8 @@ Your project now has skills, agents, hooks, rules, and permissions tailored for
 ### `npx claude-code-arcane install` — Install profiles
 
 ```bash
-# Show available profiles (interactive)
+# Interactive picker: detects your stack, pre-selects matching profiles,
+# and lets you add more from a menu grouped by category
 npx claude-code-arcane install
 
 # Install a specific profile
@@ -95,7 +95,7 @@ npx claude-code-arcane add api-design
 # Add multiple skills
 npx claude-code-arcane add security-audit owasp
 
-# Add an entire profile as addon
+# Add an entire profile
 npx claude-code-arcane add +security
 
 # Add multiple profiles
@@ -131,7 +131,7 @@ What gets deleted is read from that profile's definition, so `remove` uses the c
 npx claude-code-arcane list
 ```
 
-Shows all base profiles and add-ons with descriptions, and marks which are currently installed.
+Shows all profiles grouped by category, with descriptions, and marks which are currently installed.
 
 ### `npx claude-code-arcane status` — Check current installation
 
@@ -197,46 +197,21 @@ npx claude-code-arcane global --remove
 
 ## Profiles
 
-### Base Profiles
-
-Base profiles define the primary stack for a project. Pick one or combine multiple.
-
-| Profile | Stack | Skills | Agents |
-|---------|-------|--------|--------|
-| `unity-dev` | Unity programmer — C#, architecture, performance, builds | 25 | game |
-| `unity-design` | Game designer — GDDs, balance, art bible, playtesting | 17 | game |
-| `backend-ts` | Backend TypeScript — Fastify, Prisma, Zod, API design | 33 | engineering |
-| `backend-go` | Backend Go — Clean Arch, DB, auth, API, CI | 19 | engineering |
-| `frontend` | React + Vite + TypeScript | 14 | engineering |
-| `mobile` | React Native + Expo + TypeScript | 12 | engineering |
-| `flutter` | Flutter + Dart cross-platform | 8 | engineering |
-| `android-native` | Kotlin + Jetpack Compose + Material Design 3 | 8 | engineering |
-| `ios-native` | Swift + UIKit/SwiftUI + Apple HIG | 8 | engineering |
-
-### Add-on Profiles
-
-Add-ons extend a base profile with extra capabilities. Combine them with `+`.
-
-| Add-on | Adds | Skills | Agents |
-|--------|------|--------|--------|
-| `+agile` | Sprints, standups, retros, estimates | 10 | management, product |
-| `+docs` | PDF, PPTX, XLSX, DOCX, architecture decisions | 8 | — |
-| `+testing` | Contract, performance, regression, flakiness | 11 | quality |
-| `+infra` | Terraform, observability, secrets, rollback, K8s | 17 | devops |
-| `+database` | Indexing, migrations, seeding, replicas, optimization | 8 | — |
-| `+security` | Audits, OWASP, secrets, backups | 5 | — |
-| `+design` | Figma, UX review, design system, handoff | 6 | product |
-| `+integrations` | GitHub Projects, Slack, Postman | 3 | integrations |
-| `+clickup` | ClickUp via MCP — tasks, docs, time tracking | 3 | — |
-| `+jira` | Jira via REST API — issues, sprints, boards | 3 | — |
-| `+ai` | LLM cost optimization, RAG, ML, data engineering | 7 | ai |
-| `+business` | Contracts, customer success, revenue ops, sales | 4 | business |
-| `+clevel` | C-suite advisors, board prep, strategic ops | 28 | clevel |
-| `+finance` | Investment analysis, financial modeling, SaaS metrics | 3 | business |
-| `+marketing` | Content, growth, SEO/CRO, strategy, analytics | 44 | marketing |
-| `+regulatory` | ISO 13485, GDPR, FDA, SOC 2, ISMS, QMS, MDR | 13 | regulatory |
-| `+self-improving` | Agent self-improvement and skill extraction | 2 | — |
-| `+statusline` | Claude Code status bar (branch, division, session info) | 0 | — |
+### Profile Catalog
+
+All profiles are equal — pick any combination that fits your work. They are grouped by category for discovery (same grouping the interactive picker and `list` use). The full per-profile detail lives in the [README](../README.md#available-profiles); summary by category:
+
+| Category | Profiles |
+|----------|----------|
+| **Backend** | `backend-ts`, `backend-go`, `backend-dotnet`, `backend-nestjs`, `backend-nextjs` |
+| **Frontend & Design** | `frontend`, `design` |
+| **Mobile** | `mobile`, `flutter`, `android-native`, `ios-native` |
+| **Gamedev** | `unity-dev`, `unity-design`, `unreal-dev`, `visual-novel`, `audio` |
+| **Platform & Quality** | `infra`, `database`, `security`, `testing`, `ai` |
+| **Project Management** | `agile`, `jira`, `clickup`, `integrations` |
+| **Business** | `business`, `clevel`, `finance`, `marketing`, `ecommerce`, `regulatory` |
+| **Personal** | `second-brain`, `job-hunt`, `freelance` |
+| **Utilities** | `docs`, `self-improving`, `statusline` |
 
 ### Core (always included)
 
@@ -257,17 +232,16 @@ Every installation automatically loads `core.yaml` first:
 Profiles are combined using the `+` separator. The system deduplicates skills automatically.
 
 ```bash
-npx claude-code-arcane install <base>[+<base>][+<addon>][+<addon>]
+npx claude-code-arcane install <profile>[+<profile>][+<profile>...]
 ```
 
 ### Rules
 
 1. **Always explicit** — there is no "full" or "all" profile. You choose what you need.
 2. **Core is automatic** — the 21 universal skills and all hooks are always included.
-3. **Multiple bases are OK** — combine `unity-dev+unity-design` or `backend-go+frontend`.
-4. **Add-ons extend** — `+agile`, `+clickup`, etc. add capabilities to any base.
-5. **Deduplication is automatic** — overlapping skills across profiles are installed once.
-6. **Replace, not merge** — installing a new profile replaces the previous one entirely (with backup).
+3. **All profiles combine freely** — `unity-dev+unity-design`, `backend-go+frontend`, or `backend-ts+agile+testing`; there is no required "base".
+4. **Deduplication is automatic** — overlapping skills across profiles are installed once.
+5. **Replace, not merge** — installing a new profile replaces the previous one entirely (with backup).
 
 ---
 
@@ -278,7 +252,7 @@ After the initial install, you can incrementally add or remove skills and profil
 ### Add workflow
 
 ```bash
-# Start with a base profile
+# Start with a profile
 npx claude-code-arcane install backend-ts
 
 # Later, add testing and security
@@ -506,7 +480,7 @@ mv ~/projects/my-game/.claude.bak ~/projects/my-game/.claude
 
 ## FAQ
 
-### Can I use multiple base profiles together?
+### Can I combine multiple stack profiles?
 
 Yes. `backend-go+frontend` gives you both Go backend and React frontend skills. Duplicate skills are automatically deduplicated.
 
@@ -541,7 +515,7 @@ Yes, and it's recommended. This way everyone on the team gets the same Claude Co
 
 ### How many tokens does a profile consume?
 
-Each skill adds ~30-100 tokens to the system prompt. A typical base profile (20-30 skills) adds ~1-2k tokens. The core profile adds ~500 tokens. Compare that to loading all 397 skills, which is why selective deploy matters.
+Each skill adds ~30-100 tokens to the system prompt. A typical stack profile (20-30 skills) adds ~1-2k tokens. The core profile adds ~500 tokens. Compare that to loading all 427 skills, which is why selective deploy matters.
 
 ### Why replace instead of merge on install?
 

package/hooks/detect-unreal.sh

@@ -0,0 +1,90 @@
+#!/usr/bin/env bash
+# SessionStart hook: inject a short note identifying the session as operating inside
+# an Unreal Engine project, so Claude defaults to UE conventions and reaches for the
+# ue-* skills. Walks upward from $PWD so sessions started in a subdirectory
+# (Source/, Content/, Plugins/, ...) are still detected.
+#
+# Adapted from EpicGames/unreal-engine-skills-for-claude-code-plugin (MIT).
+# Opt-in debug logging: set CLAUDE_UE_HOOK_DEBUG to any non-empty value.
+set +e
+
+debug() {
+  [[ -n "$CLAUDE_UE_HOOK_DEBUG" ]] && echo "detect-unreal.sh: $*" >&2
+}
+
+is_project_root() {
+  # Reliable top-level markers only. A bare `Engine` directory is NOT a marker: the
+  # Unreal source tree contains an `Engine` module at Engine/Source/Runtime/Engine,
+  # so walking up from a Runtime module would otherwise short-circuit at
+  # Source/Runtime and mis-identify it as the root.
+  local directory="$1"
+  [[ -f "$directory/GenerateProjectFiles.bat" ]] && return 0
+  [[ -f "$directory/GenerateProjectFiles.sh" ]] && return 0
+  [[ -f "$directory/GenerateProjectFiles.command" ]] && return 0
+  for candidate in "$directory"/*.uproject; do
+    [[ -e "$candidate" ]] && return 0
+  done
+  return 1
+}
+
+find_project_root() {
+  local directory="$1"
+  while [[ -n "$directory" ]]; do
+    if is_project_root "$directory"; then
+      echo "$directory"
+      return 0
+    fi
+    local parent
+    parent="$(dirname "$directory")"
+    [[ "$parent" == "$directory" ]] && break
+    directory="$parent"
+  done
+  return 1
+}
+
+main() {
+  local project_root
+  project_root="$(find_project_root "$PWD")"
+  if [[ -z "$project_root" ]]; then
+    debug "no Unreal Engine project marker found walking up from $PWD"
+    return 0
+  fi
+
+  local project_type="game"
+  [[ -d "$project_root/Engine" ]] && project_type="engine"
+
+  local uproject_filename=""
+  for candidate in "$project_root"/*.uproject; do
+    if [[ -e "$candidate" ]]; then
+      uproject_filename="$(basename "$candidate")"
+      break
+    fi
+  done
+
+  debug "project root: $project_root (type=$project_type, uproject=$uproject_filename)"
+
+  local context="This working directory is an Unreal Engine project."
+  if [[ "$project_type" == "engine" ]]; then
+    context="$context It is an Engine source tree."
+  elif [[ -n "$uproject_filename" ]]; then
+    context="$context The project is \`$uproject_filename\`."
+  fi
+  context="$context Prefer Unreal Engine conventions (C++/UObject patterns, Slate, UHT reflection) when suggesting code."
+  context="$context Arcane ships ue-* skills for this stack; run /ue-project-context first if docs/unreal/project-context.md does not exist yet."
+  context="$context Unreal ships its own MCP server as engine plugins; run /install-mcp to enable and connect it."
+
+  if [[ -f "$project_root/.mcp.json" ]]; then
+    context="$context An \`.mcp.json\` is already present at the project root."
+  else
+    context="$context No \`.mcp.json\` is present yet. Run \`ModelContextProtocol.GenerateClientConfig ClaudeCode\` in the editor console to generate one."
+  fi
+
+  # JSON-escape the dynamic content: backslash first, then double quote.
+  local escaped="${context//\\/\\\\}"
+  escaped="${escaped//\"/\\\"}"
+
+  printf '{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"%s"}}\n' "$escaped"
+}
+
+main 2>/dev/null
+exit 0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-arcane",
-  "version": "2.3.0",
+  "version": "2.5.0",
   "description": "Skills, agents, hooks and rules for Claude Code — installable via npx claude-code-arcane",
   "type": "module",
   "bin": {
@@ -42,6 +42,7 @@
     "access": "public"
   },
   "dependencies": {
+    "@clack/prompts": "^1.7.0",
     "chalk": "^5.3.0",
     "commander": "^12.1.0",
     "js-yaml": "^4.1.0",

package/profiles/agile.yaml

@@ -1,6 +1,6 @@
 name: agile
 description: "Gestión de proyecto — sprints, standups, retros, estimates"
-type: addon
+category: management
 
 skills:
   - gh-projects

package/profiles/ai.yaml

@@ -1,6 +1,6 @@
 name: ai
 description: "AI & ML — LLM optimization, RAG, computer vision, data engineering, prompt engineering"
-type: addon
+category: platform
 
 skills:
   - llm-cost-optimizer

package/profiles/android-native.yaml

@@ -1,6 +1,6 @@
 name: android-native
 description: "Android native — Kotlin + Jetpack Compose + Material Design 3"
-type: base
+category: mobile
 
 skills:
   - testing

package/profiles/audio.yaml

@@ -1,6 +1,6 @@
 name: audio
 description: "Game Audio — direccion sonora, composicion, sound design, middleware, VO y QA"
-type: base
+category: gamedev
 
 skills:
   - audio-bible

package/profiles/backend-dotnet.yaml

@@ -1,6 +1,6 @@
 name: backend-dotnet
 description: "Backend .NET — ASP.NET Core (.NET 10), Vertical Slice / Clean Architecture, EF Core + PostgreSQL, JWT + Identity, testing. Best practices priorizadas por impacto."
-type: base
+category: backend
 
 skills:
   # .NET-specific (nuevas)

package/profiles/backend-go.yaml

@@ -1,6 +1,6 @@
 name: backend-go
 description: "Backend Go — scaffold, DB, auth, API design, CI"
-type: base
+category: backend
 
 skills:
   - test-setup

package/profiles/backend-nestjs.yaml

@@ -1,6 +1,6 @@
 name: backend-nestjs
 description: "Backend NestJS — feature modules, DI, guards/pipes, Prisma, JWT, testing, microservicios. Best practices priorizadas por impacto."
-type: base
+category: backend
 
 skills:
   # NestJS-specific (nuevas)

package/profiles/backend-nextjs.yaml

@@ -1,6 +1,6 @@
 name: backend-nextjs
 description: "Next.js full-stack — App Router, RSC, Server Actions, SEO, AI SDK, performance (64 reglas de Vercel). Front + back en un solo runtime."
-type: base
+category: backend
 
 skills:
   # Next.js-specific (nuevas)

package/profiles/backend-ts.yaml

@@ -1,6 +1,6 @@
 name: backend-ts
 description: "Backend TypeScript — Fastify, Prisma, Zod, API design, CI"
-type: base
+category: backend
 
 skills:
   - testing

package/profiles/business.yaml

@@ -1,6 +1,6 @@
 name: business
 description: "Business — contracts, customer success, revenue ops, sales engineering"
-type: addon
+category: business
 
 skills:
   - contract-and-proposal-writer

package/profiles/clevel.yaml

@@ -1,6 +1,6 @@
 name: clevel
 description: "C-Level — executive advisors, board prep, strategic operations, org health"
-type: addon
+category: business
 
 skills:
   - ceo-advisor

package/profiles/clickup.yaml

@@ -1,6 +1,6 @@
 name: clickup
 description: "ClickUp via MCP — tasks, docs, time tracking"
-type: addon
+category: management
 
 skills:
   - clickup

package/profiles/core.yaml

@@ -1,6 +1,6 @@
 name: core
 description: "Skills universales, hooks y rules base"
-type: base
+category: core
 
 skills:
   - commit

package/profiles/database.yaml

@@ -1,6 +1,6 @@
 name: database
 description: "Database avanzado — indexing, migrations, seeding, replicas"
-type: addon
+category: platform
 
 skills:
   - database-indexing

package/profiles/design.yaml

@@ -1,6 +1,6 @@
 name: design
 description: "Figma workflow, UX review, handoff a dev"
-type: addon
+category: frontend
 
 skills:
   - user-persona

package/profiles/docs.yaml

@@ -1,6 +1,6 @@
 name: docs
 description: "Document generation — PDF, PPTX, XLSX, DOCX, architecture"
-type: addon
+category: utilities
 
 skills:
   - pdf-generator

package/profiles/ecommerce.yaml

@@ -1,6 +1,6 @@
 name: ecommerce
 description: "E-Commerce — dominio commerce end-to-end agnostico de lenguaje: data model, carrito/checkout, inventario, ordenes, pagos, promociones, shipping/tax, listings, analytics, feeds, storefront y suscripciones"
-type: addon
+category: business
 
 skills:
   # net-new (12)

package/profiles/finance.yaml

@@ -1,6 +1,6 @@
 name: finance
 description: "Finance — investment analysis, financial modeling, SaaS metrics"
-type: addon
+category: business
 
 skills:
   - business-investment-advisor

package/profiles/flutter.yaml

@@ -1,6 +1,6 @@
 name: flutter
 description: "Flutter + Dart cross-platform development"
-type: base
+category: mobile
 
 skills:
   - testing

package/profiles/freelance.yaml

@@ -1,6 +1,6 @@
 name: freelance
 description: "Freelance — conseguir proyectos como freelancer y ejecutarlos: scan de fuentes publicas sin API key con dedup y scoring, busqueda en los marketplaces (Upwork, Workana) via WebSearch, inteligencia de tarifas de mercado, screening de riesgo del cliente, perfil de plataforma, propuestas con cotizacion sobre piso de tarifa neto, contratos y SOWs, kickoff con validacion de horas contra lo cotizado, registro de horas y change orders, pipeline con costo de adquisicion y utilizacion, y 4 agentes de contexto fresco (review de propuesta, screener adversarial, discovery call, estratega de pipeline)"
-type: addon
+category: personal
 
 skills:
   # Nucleo del perfil

package/profiles/frontend.yaml

@@ -1,6 +1,6 @@
 name: frontend
 description: "Frontend React + Vite + TypeScript"
-type: base
+category: frontend
 
 skills:
   - testing

package/profiles/infra.yaml

@@ -1,6 +1,6 @@
 name: infra
 description: "DevOps/Platform/Ops — deploy, observability, secrets, rollback"
-type: addon
+category: platform
 
 skills:
   - observability

package/profiles/integrations.yaml

@@ -1,6 +1,6 @@
 name: integrations
 description: "Integraciones externas — GitHub Projects, Slack, Postman"
-type: addon
+category: management
 
 skills:
   - gh-projects

package/profiles/ios-native.yaml

@@ -1,6 +1,6 @@
 name: ios-native
 description: "iOS native — Swift + UIKit/SwiftUI + Apple HIG"
-type: base
+category: mobile
 
 skills:
   - testing

package/profiles/jira.yaml

@@ -1,6 +1,6 @@
 name: jira
 description: "Jira via curl/REST API — issues, sprints, boards"
-type: addon
+category: management
 
 skills:
   - jira-tickets

package/profiles/job-hunt.yaml

@@ -1,6 +1,6 @@
 name: job-hunt
 description: "Job Hunt — busqueda laboral end-to-end: perfil maestro, CV ATS con verificacion, scraping de ofertas con dedup, pipeline de postulacion, LinkedIn, portfolio, cover letters, outreach a recruiters, scoring de ofertas, gaps/upskill, prep de entrevistas y 4 agentes de contexto fresco (review de CV, hiring manager, mock interview, diagnostico del embudo)"
-type: addon
+category: personal
 
 skills:
   - job-hunt

package/profiles/marketing.yaml

@@ -1,6 +1,6 @@
 name: marketing
 description: "Marketing — content, growth, SEO/CRO, strategy, analytics, social media"
-type: addon
+category: business
 
 skills:
   - content-creator

package/profiles/mobile.yaml

@@ -1,6 +1,6 @@
 name: mobile
 description: "Mobile React Native + Expo + TypeScript"
-type: base
+category: mobile
 
 skills:
   - testing

package/profiles/regulatory.yaml

@@ -1,6 +1,6 @@
 name: regulatory
 description: "Regulatory & Compliance — ISO 13485, GDPR, FDA, SOC2, ISMS, QMS, MDR"
-type: addon
+category: business
 
 skills:
   - capa-officer

package/profiles/second-brain.yaml

@@ -1,6 +1,6 @@
 name: second-brain
 description: "Second Brain — vault de Obsidian gestionado con Claude Code: captura sin friccion, reviews diario/semanal/mensual, notas atomicas y hub files (PARA + Zettelkasten), busqueda con ranking, captura web, auditoria de salud del vault y sintaxis nativa de Obsidian (markdown, Bases, Canvas)"
-type: addon
+category: personal
 
 skills:
   - second-brain

package/profiles/security.yaml

@@ -1,6 +1,6 @@
 name: security
 description: "Security — audits, OWASP, secrets, backups"
-type: addon
+category: platform
 
 skills:
   - security-audit

package/profiles/self-improving.yaml

@@ -1,6 +1,6 @@
 name: self-improving
 description: "Self-improving — auto-memory curation, skill auditing and optimization"
-type: addon
+category: utilities
 
 skills:
   - self-improving-agent

package/profiles/statusline.yaml

@@ -1,6 +1,6 @@
 name: statusline
 description: "Status bar showing branch, division, and session info in Claude Code"
-type: addon
+category: utilities
 
 skills:
   []