Prepare, audit, implement, homologate, and publish Nuvemshop/Tiendanube apps. Use when the user needs help with Nuvemshop Partner Portal app creation, public App Store publication, private client distribution, OAuth, scopes, webhooks, API usage, NubeSDK migration or development, Nexo embedded admin apps, Nimbus/design requirements, homologation artifacts, demo videos, FAQ/support docs, billing/publication data, app descriptions, or approval checklists.
Covers building, extending, debugging, and maintaining Foundry VTT modules for v13+. This skill applies when scaffolding a new module, writing custom Actor/Item types with TypeDataModel, building ApplicationV2 sheets or dialogs, registering hooks or settings, implementing socket communication, extending the canvas with PIXI.js, managing compendium packs, using ActiveEffects, setting up TypeScript with fvtt-types, configuring Vite/Rollup builds, localizing strings, or migrating modules between Foundry versions. Triggers on: "Foundry module", "FVTT", "FoundryVTT", "foundryvtt module", "ApplicationV2", "TypeDataModel", "actor sheet", "module.json", "fvtt-types", "libWrapper", "socketlib", or any task involving Foundry VTT module development.
Covers building, extending, and maintaining Foundry VTT game systems for v13+. This skill applies when scaffolding a new system, defining Actor/Item types with TypeDataModel, customizing dice mechanics, implementing combat & initiative, building character sheets, handling system data migration, or configuring template.json. Triggers on: "Foundry system", "FVTT system", "system.json", "template.json", "foundryvtt system", "Actor subclass", "Item subclass", "custom dice", "DiceTerm", "system development", "game system", "RPG system", "statusEffects", "hotbarDrop", "custom enricher", "JournalEntryPage", "TokenDocument", or any task involving Foundry VTT system development.
Build production AI agents with the Claude Agent SDK (TypeScript: @anthropic-ai/claude-agent-sdk, Python: claude-agent-sdk). Use this skill whenever: building programmatic agents with Claude, using query() or ClaudeSDKClient, configuring hooks/subagents/MCP servers/custom tools, setting up permissions or sessions, deploying agents to Docker/CI/CD/cloud, importing @anthropic-ai/claude-agent-sdk or claude-agent-sdk, mentioning 'agent sdk' or 'claude sdk' in a coding context, building autonomous agents that read files/run commands/edit code, or any task involving programmatic Claude Code integration. Even if the user just says 'build an agent' or 'automate with Claude' — use this skill.
Use when adding audio to a game — SFX generation, adaptive music, voice acting, and audio state machine integration. Covers BOTH ElevenLabs API AND Vertex AI Lyria as user-choosable alternatives for game audio production.
Comprehensive game MVP interviewer and planner. Interviews you in progressive groups, researches genre conventions and reference games, then produces an actionable MVP First Draft with starter project files. Use when starting a new game project from scratch.
Analyzes a game system against design principles — economy health metrics, difficulty curve, reward schedules, and progression cost curves. Flags imbalances with severity levels. Use after creating an MVP plan with game-architect. Extract the analysis scope (economy/difficulty/progression/rewards/all) from the user's message.
Builds a game component from the MVP plan — production TypeScript + Vitest tests + mock dependencies + build registry tracking. Extract the component name from the user's message (or "status" to check progress). Requires docs/mvp-first-draft.md — run game-architect first.