claude-code-arcane 1.0.0

package/skills/game-analysis/references/playtest-template.md

@@ -0,0 +1,28 @@
+# Playtest Report Template & Analysis
+
+## Template Sections (`playtest new`)
+
+| Sección | Campos |
+|---------|--------|
+| **Session info** | Fecha, build/version, duración, tester, plataforma, input method, tipo de sesión |
+| **Test focus** | Qué features/flows se testean |
+| **First impressions** (5 min) | Entendió goal? Controles? Respuesta emocional |
+| **Gameplay flow** | Qué funcionó, pain points (con severity), puntos de confusión, momentos de deleite |
+| **Bugs** | Tabla: descripción, severity, reproducible |
+| **Feature feedback** | Por feature: entendió propósito? Engaging? Sugerencias |
+| **Quantitative** | Deaths, tiempo por área, items usados, features descubiertas vs missed |
+| **Overall** | Jugaría de nuevo? Dificultad, pacing, duración de sesión preferida |
+| **Top 3 prioridades** | Los 3 findings más importantes |
+
+## Modo análisis (`playtest analyze [path]`)
+
+Leer notas raw, cross-referenciar con GDDs, estructurar en el template. Flaggear observaciones que contradicen la intención de diseño.
+
+## Categorización de findings
+
+| Categoría | Qué | Siguiente paso |
+|-----------|-----|---------------|
+| **Design changes** | Fun issues, confusión del jugador, mecánicas rotas | Actualizar GDD, evaluar impacto downstream |
+| **Balance adjustments** | Números incorrectos, difficulty spikes/dips | Correr `/game-analysis balance [system]` |
+| **Bug reports** | Defectos de implementación reproducibles | Issue tracker |
+| **Polish items** | Fricción, feel issues, no bloquean progreso | Backlog para fase de polish |

package/skills/game-audit/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: game-audit
+description: "Audit assets, docs and cross-document consistency: naming, orphaned assets, doc-vs-code contradictions, balance red flags, entity registry."
+category: "gamedev"
+argument-hint: "[assets|docs|consistency|full] [path]"
+user-invocable: true
+allowed-tools: Read, Glob, Grep, Bash
+---
+# game-audit — Assets + Documents
+
+Auditoría diagnóstica read-only. Produce reporte, no modifica archivos.
+
+## 1. Asset Audit
+
+| Directorio | Checks |
+|------------|--------|
+| Art (textures, sprites, meshes) | Naming, power-of-two, format (PNG UI, compressed 3D), size budget |
+| Audio (SFX, music) | Naming, sample rate, format (OGG/MP3), duration |
+| Data (JSON, YAML, SO) | Schema compliance, formato válido |
+
+### Checks
+- **Naming**: `lowercase_underscores`, patrón `[cat]_[name]_[variant].[ext]`
+- **Orphaned**: sin referencias en código/escenas — verificar carga dinámica (Addressables, Resources.Load) antes de flaggear
+- **Missing**: referencia en código a asset inexistente
+- **Size**: comparar contra budget del art bible
+
+Standards source: art bible > CLAUDE.md > flaggear "no standard defined"
+
+## 2. Document Audit
+
+Args: `gdd`, `spec-docs`, `gdd-vs-code`, `balance`, path específico, o sin arg = full.
+
+| Tipo | Severidad | Qué buscar |
+|------|-----------|------------|
+| Contradicciones | CRITICAL | Misma mecánica descrita diferente entre docs/código |
+| Gaps | HIGH | TBD/vacío, mecánicas sin definir, fórmulas sin números |
+| Coherencia | MEDIUM | Edge cases, terminología inconsistente, fórmulas absurdas |
+| Balance | MEDIUM | Estrategias dominantes, opciones peores, snowball, economía rota |
+| Completitud | HIGH | Scope incompleto, dependencias ocultas |
+
+Gap classification: Bloqueante (no se puede implementar) > Importante (antes del milestone) > Nice to have.
+
+## 3. Consistency Check (entity registry)
+
+Arg: `consistency`, `consistency entity:<name>`, `consistency item:<name>`.
+
+Si existe registry (`design/registry/entities.yaml`): cargar lookup tables → grep nombres en GDDs → extraer valores cercanos → comparar.
+
+| Tipo | Acción |
+|------|--------|
+| CONFLICT | Mismo nombre, valores diferentes — resolver antes de avanzar |
+| STALE REGISTRY | Source GDD cambió, registry no actualizado |
+| UNVERIFIABLE | Sin atributos comparables — solo informativo |
+
+Resolución: GDD source es autoritativo. Si no existe registry → informar que se requiere uno.
+
+## Formato del reporte
+
+Estado general: SALUDABLE / NECESITA ATENCIÓN / CRÍTICO. Resumen ejecutivo (2-3 oraciones). Hallazgos en formato PAS condensado (≤5 líneas c/u) con severity. Asset compliance table. Sección "lo que está bien". Action items priorizados.
+
+## Anti-patterns
+
+- Auditar sin leer art bible primero
+- Orphaned sin verificar carga dinámica
+- Mezclar severidades sin priorizar
+- Solo criticar sin reconocer buen diseño

package/skills/game-docs/SKILL.md

@@ -0,0 +1,58 @@
+---
+name: game-docs
+description: "Game design docs: GDD completo (core loop, balance, glosario) y PAS para decisiones de diseño."
+category: "gamedev"
+argument-hint: "[gdd [game-name] | pas [problem-title]]"
+user-invocable: true
+allowed-tools: Read, Glob, Grep, Write, Edit
+---
+# game-docs — GDD + Design Decisions
+
+Dos formatos de documentación de game design: GDD completo y PAS para decisiones puntuales.
+
+---
+
+## 1. GDD (Game Design Document)
+
+### Input
+
+Preguntar al usuario:
+1. **Nombre del juego**
+2. **Género** (roguelite, RPG, puzzle, platformer, etc.)
+3. **Plataforma** (PC, mobile, consola, web)
+4. **Elevator pitch** (1-2 oraciones: qué es y qué lo hace único)
+5. **Mecánica core** (qué hace el jugador el 80% del tiempo)
+6. **Referentes** (juegos similares o inspiraciones)
+7. **Contexto** (tesis, indie, jam, estudio, tamaño equipo)
+
+### Estructura del GDD
+
+16 secciones: Resumen, Concepto, Pilares, Arte, Game Feel, Glosario, Core Loop, Sistema Core, Niveles, Enemigos, Items, Economía, UI/UX, Audio, Scope, Decisiones Abiertas. Adaptar al género.
+
+> → Read references/gdd-structure.md for full section table with content guidelines
+
+---
+
+## 2. PAS (Problema-Análisis-Solución)
+
+Formato para decisiones de diseño puntuales: Problema → Análisis → Opciones → Decisión. Usar para mecánicas problemáticas, balance, features, playtest feedback. NO para GDD completo, specs técnicas o bugs.
+
+> → Read references/pas-format.md for full PAS template, usage criteria, and examples
+
+---
+
+## Reglas de escritura (ambos formatos)
+
+Bullets > párrafos. Números concretos > descripciones vagas. No divagar, no repetir entre secciones. [TBD] para decisiones pendientes.
+
+> → Read references/writing-rules.md for full 9-rule list with examples
+
+---
+
+## Rules
+
+- Siempre en español
+- El GDD es documento vivo — versionar y fechar
+- Incluir scope MVP vs full game
+- Si falta info → [TBD] + listar en Decisiones Abiertas
+- Los pilares son obligatorios — todo se evalúa contra ellos

package/skills/game-docs/references/gdd-structure.md

@@ -0,0 +1,24 @@
+# GDD Structure — Full Section Reference
+
+| # | Sección | Contenido clave |
+|---|---------|----------------|
+| 1 | Resumen | Tabla: género, plataforma, engine, perspectiva, sesión promedio, target audience |
+| 2 | Concepto | Elevator pitch en 2-3 oraciones. "Es como [A] pero con [B]" |
+| 3 | Pilares de diseño | 3 pilares. Test: si feature no soporta ≥1 pilar → no entra |
+| 4 | Dirección de arte | Estilo visual, paleta, referencias (o delegar a `/art-bible`) |
+| 5 | Game feel | Principios de feedback visual/táctil |
+| 6 | Glosario | Tabla: término, significado, alternativas prohibidas |
+| 7 | Core loop | Diagrama + tabla de capas (micro/medio/macro) con duración |
+| 8 | Sistema core | Flujo principal, mecánicas del jugador, tablas de valores |
+| 9 | Niveles/mundo | Generación (procedural/handcrafted/híbrido), tipos, progresión de dificultad |
+| 10 | Enemigos | Tabla: nombre, HP, daño, comportamiento, aparición. AI/patterns |
+| 11 | Items/equip | Categorías con efecto, balance de items |
+| 12 | Economía | Recursos (obtención/gasto), curva de progresión, meta-progresión |
+| 13 | UI/UX | Pantallas principales, HUD en gameplay |
+| 14 | Audio | Música por situación, SFX clave |
+| 15 | Scope | MVP checklist, roadmap por fase (Prototype→VS→Alpha→Beta→Release) |
+| 16 | Decisiones abiertas | Tabla: pregunta, opciones, status ([TBD] o decidido) |
+
+Apéndices opcionales: fórmulas de balance, tablas de stats, diagramas de estado.
+
+Adaptar secciones al género — un puzzle no necesita "enemigos".

package/skills/game-docs/references/pas-format.md

@@ -0,0 +1,49 @@
+# PAS Format — Problema-Analisis-Solucion
+
+Para decisiones de diseño, cambios de balance, evaluación de mecánicas, feedback de playtest.
+
+## Formato
+
+```markdown
+# [Título conciso]
+
+## Problema
+**Qué pasa:**
+- [Hecho concreto — qué no funciona o falta]
+
+**Impacto en el jugador:**
+- [Experiencia negativa concreta]
+
+## Análisis
+**Por qué pasa:**
+- [Causa raíz]
+
+**Variables que influyen:**
+- [Variable]: [valor actual] → [efecto]
+
+## Opciones
+### A: [Nombre]
+[1 oración] — Pro: [ventaja] / Contra: [desventaja] / Esfuerzo: [bajo|medio|alto]
+
+### B: [Nombre]
+[1 oración] — Pro / Contra / Esfuerzo
+
+## Decisión
+**Elegimos: Opción [X]**
+**Justificación:** [1-2 oraciones]
+**Cambios concretos:** [valores exactos]
+**Status:** Decidido / Pendiente / [TBD]
+```
+
+## Cuándo usar PAS
+
+- Mecánicas problemáticas
+- Propuestas de cambio de balance
+- Decisiones de diseño (nueva feature, cambio de sistema)
+- Evaluación de feedback de playtest
+
+## Cuándo NO
+
+- GDD completo → usar sección GDD
+- Spec técnica → RFC/ADR
+- Bug report → issue tracker

package/skills/game-docs/references/writing-rules.md

@@ -0,0 +1,17 @@
+# Writing Rules (ambos formatos)
+
+1. **NO divagar** — cada oración aporta info nueva
+2. **Bullet points > párrafos** — siempre
+3. **Números concretos > descripciones vagas** — "100 HP, 2 AP" no "vida moderada"
+4. **NO preguntas retóricas ni recomendaciones genéricas**
+5. **NO repetir información** entre secciones
+6. **Máximo 2-3 oraciones** por descripción de sistema. Si necesita más → tabla
+7. **Decisiones pendientes** → marcar [TBD] y listar en sección 16
+8. **Glosario** → usar términos definidos consistentemente en todo el doc
+9. **PAS: máximo 6 bullets** en Problema, **2-4 opciones**, **2 oraciones** de justificación
+
+### Ejemplo bien vs mal
+
+**Mal:** "El sistema de combate presenta algunos desafíos interesantes que vale la pena analizar. Cuando el jugador se enfrenta a enemigos..."
+
+**Bien:** "El jugador falla 60%+ de ataques en Floor 1 con dados d6 base. El threshold de Goblin (4) es demasiado alto para el loadout inicial (4xd6)."

package/skills/gate-check/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: gate-check
+description: "Quality gate validation for phase transitions: artifact checks, quality criteria, verdict with blockers"
+category: "workflow"
+argument-hint: "[target-phase] [--review full|lean|solo]"
+user-invocable: true
+allowed-tools: Read, Glob, Grep, Bash, Write, Task, AskUserQuestion
+model: opus
+---
+# gate-check — Phase Gate Validation
+
+Validates project readiness to advance to the next phase. Checks required artifacts, quality standards, and blockers. Produces verdict: PASS / CONCERNS / FAIL.
+
+## Software phases
+
+1. **Discovery** — Scope, tech choices, NFRs
+2. **Design** — Architecture, ADRs, threat model, API spec
+3. **Pre-Production** — Epics, test framework, CI/CD, env setup
+4. **Production** — Feature development, coverage, error tracking
+5. **Pre-Release** — Load test, security audit, a11y, runbooks
+6. **Release** — Deploy prep, monitoring, rollback plan
+
+## Gate criteria per transition
+
+### Discovery -> Design
+- [ ] Scope doc / PRD with problem statement, success metrics, out-of-scope
+- [ ] Tech choices documented (framework, DB, cache, queue)
+- [ ] Non-functional requirements (latency, throughput, scale)
+
+### Design -> Pre-Production
+- [ ] Architecture doc with layered design
+- [ ] >= 3 ADRs covering foundation decisions (auth, data, API)
+- [ ] API spec (OpenAPI/GraphQL) if applicable
+- [ ] DB schema initial (migrations or ERD)
+- [ ] Threat model if PII/auth/financial data involved
+
+### Pre-Production -> Production
+- [ ] Test framework initialized with examples
+- [ ] CI/CD pipeline functional (runs on every PR)
+- [ ] Epics defined with acceptance criteria
+- [ ] Environment setup documented, secrets wired (.env.example)
+
+### Production -> Pre-Release
+- [ ] All MVP features implemented
+- [ ] Test coverage: >70% domain, >50% integration
+- [ ] Error tracking wired (Sentry, Datadog, etc.)
+- [ ] Structured logging with request IDs
+- [ ] Staging deploy with smoke tests passing
+
+### Pre-Release -> Release
+- [ ] Load test results meeting targets
+- [ ] Security audit: HIGH/CRITICAL findings remediated
+- [ ] Accessibility audit (WCAG AA) if public UI
+- [ ] Incident runbooks documented
+- [ ] Rollback plan documented
+- [ ] Monitoring dashboards configured
+- [ ] Changelog / release notes drafted
+
+## Execution process
+
+1. **Detect current phase** from `production/stage.txt` or infer from project structure
+2. **Check artifacts** — verify files exist with meaningful content (not just template headers)
+3. **Run quality checks** — tests via CI, coverage, linting
+4. **Cross-reference** — architecture docs vs implementation, sprint plans vs work items
+5. **Mark unverifiable items** as MANUAL CHECK NEEDED — never assume PASS
+
+## Verdict rules
+
+| Condition | Verdict |
+|-----------|---------|
+| All artifacts present + all quality checks pass | **PASS** |
+| Minor gaps addressable during next phase | **CONCERNS** |
+| Critical blockers must resolve before advancing | **FAIL** |
+
+## Chain-of-verification
+
+Before finalizing, generate 5 challenge questions to disprove the verdict:
+- For PASS: "Which checks did I verify by reading files vs inferring?"
+- For CONCERNS: "Could any concern escalate to a blocker?"
+- For FAIL: "What is the minimal path to PASS?"
+
+Answer each independently, revise verdict only with specific evidence.
+
+## On PASS
+
+Write new phase to `production/stage.txt` (with user confirmation).
+
+## Anti-patterns
+
+- Assuming PASS for items not actually verified
+- Checking file existence without verifying meaningful content
+- Skipping cross-reference between design docs and implementation
+- Blocking the user — verdict is advisory, user makes final call

package/skills/gcp-cloud-architect/SKILL.md

@@ -0,0 +1,127 @@
+---
+name: gcp-cloud-architect
+description: "Design GCP architectures with Terraform IaC, Cloud Run, GKE, BigQuery pipelines, cost optimization, and Cloud Build CI/CD for startups and enterprises."
+argument-hint: ""
+category: "devops"
+user-invocable: true
+allowed-tools: Read, Glob, Grep, Bash
+---
+
+# GCP Cloud Architect
+
+Design scalable, cost-effective Google Cloud architectures for startups and enterprises with infrastructure-as-code templates.
+
+---
+
+## Workflow
+
+### Step 1: Gather Requirements
+
+Collect application specifications:
+- Application type (web app, mobile backend, data pipeline, SaaS)
+- Expected users and requests per second
+- Budget constraints (monthly spend limit)
+- Team size and GCP experience level
+- Compliance requirements (GDPR, HIPAA, SOC 2)
+- Availability requirements (SLA, RPO/RTO)
+
+### Step 2: Design Architecture
+
+Select from recommended patterns:
+- **Serverless Web**: Cloud Storage + Cloud CDN + Cloud Run + Firestore
+- **Microservices on GKE**: GKE Autopilot + Cloud SQL + Memorystore + Pub/Sub
+- **Serverless Data Pipeline**: Pub/Sub + Dataflow + BigQuery + Looker
+- **ML Platform**: Vertex AI + Cloud Storage + BigQuery + Cloud Functions
+
+See `references/architecture_patterns.md` for detailed pattern specifications with service stacks, Terraform configs, and cost estimates.
+
+**Validation checkpoint:** Confirm the recommended pattern matches the team's operational maturity and compliance requirements before proceeding.
+
+### Step 3: Estimate Cost
+
+```bash
+python scripts/cost_optimizer.py --resources current_setup.json --monthly-spend 2000
+```
+
+Output includes monthly cost breakdown, right-sizing recommendations, committed use discount opportunities, and sustained use discount analysis. Use the [GCP Pricing Calculator](https://cloud.google.com/products/calculator) for detailed estimates.
+
+### Step 4: Generate IaC
+
+```bash
+python scripts/deployment_manager.py --app-name my-app --pattern serverless_web --region us-central1
+```
+
+Generates production-ready Terraform HCL and gcloud CLI scripts. See `references/architecture_patterns.md` for full template examples including Cloud CDN, Identity Platform, IAM, and Cloud Monitoring.
+
+### Step 5: Configure CI/CD
+
+Set up automated deployment with Cloud Build or GitHub Actions. See `references/best_practices.md` for cloudbuild.yaml templates and trigger configuration.
+
+### Step 6: Security Review
+
+Verify security configuration:
+- IAM roles follow least privilege (prefer predefined over basic roles)
+- Service accounts use Workload Identity for GKE
+- VPC Service Controls for sensitive APIs
+- Cloud KMS for customer-managed encryption
+- Cloud Audit Logs enabled for all admin activity
+- Secret Manager for all credentials
+
+---
+
+## Tools
+
+### architecture_designer.py
+Recommends GCP services based on workload requirements.
+
+```bash
+python scripts/architecture_designer.py --input requirements.json --output design.json
+```
+
+### cost_optimizer.py
+Analyzes GCP resources for cost savings: idle removal, right-sizing, committed use discounts, storage transitions.
+
+```bash
+python scripts/cost_optimizer.py --resources inventory.json --monthly-spend 5000
+```
+
+### deployment_manager.py
+Generates gcloud CLI scripts and Terraform configurations.
+
+```bash
+python scripts/deployment_manager.py --app-name my-app --pattern serverless_web --region us-central1
+```
+
+---
+
+## Quick Start
+
+| Scenario | Architecture | Estimated Cost |
+|----------|-------------|----------------|
+| Web App on Cloud Run (<1k users) | Cloud Run + Firestore + Identity Platform + Cloud CDN | $15-40/mo |
+| Microservices SaaS (50k users) | GKE Autopilot + Cloud SQL + Memorystore + Cloud Build | $500-2000/mo |
+| Serverless Data Pipeline | Pub/Sub + Dataflow + BigQuery + Looker | Variable |
+| ML Platform | Vertex AI + Cloud Storage + BigQuery + Cloud Functions | Variable |
+
+---
+
+## Anti-Patterns
+
+| Anti-Pattern | Better Approach |
+|---|---|
+| Using default VPC for production | Custom VPC with private subnets |
+| Over-provisioning GKE node pools | GKE Autopilot or cluster autoscaler |
+| Storing secrets in env vars | Secret Manager with Workload Identity |
+| Single-region deployment for SaaS | Multi-region with Cloud Load Balancing |
+| BigQuery on-demand for heavy workloads | BigQuery slots (flat-rate) for consistency |
+| Cloud Functions for long tasks (>60s) | Cloud Run for longer-running tasks |
+
+---
+
+## Reference Documentation
+
+| Document | Contents |
+|----------|----------|
+| `references/architecture_patterns.md` | 6 patterns with Terraform configs, gcloud scripts, cost estimates |
+| `references/service_selection.md` | Decision matrices for compute, database, storage, messaging |
+| `references/best_practices.md` | Naming, labels, IAM, networking, monitoring, DR |