wizardshit
Work on wizardshit.ai — Joel's AI education platform teaching the exploratory journey of building systems with and around AI. Covers the Next.js app in gremlin, The Claw course design, and the manage brain vault. Triggers on: 'wizardshit', 'wizard shit', 'wizardshit.ai', 'the claw course', 'agent game generation', 'zots', 'minions of toil'.
What this skill does
# wizardshit.ai Joel's AI education platform. The crux: **teach the exploratory journey of building systems with and around AI.** Not a polished curriculum factory — a system that teaches by showing the system being built. Digital garden philosophy applied to AI education. ## Repositories ### App: `~/Code/badass-courses/gremlin/apps/wizardshit-ai/` Next.js 16 app in the gremlin monorepo (`badass-courses/gremlin`). Uses the badass-courses platform: - `@badass-courses/core`, `@badass-courses/sdk`, `@badass-courses/next`, `@badass-courses/ui` - Convex backend via `@badass-courses/convex-adapter` - Package name: `@wizardshit/web` The gremlin monorepo has its own `AGENTS.md` — **read it before any gremlin work**: ```bash cat ~/Code/badass-courses/gremlin/AGENTS.md ``` ### Brain/Design: `~/Code/joelhooks/manage/` Vercel manage repo with PARA-structured brain vault. Course design docs live here: - `brain/01 Projects/Agent Game Generation/` — The Claw course design bible - `skills/the-claw-course-design/SKILL.md` — course design process skill - `docs/decisions/` — ADRs for the manage workspace Key design documents (read in order): 1. `Course Concept.md` — canonical spec (~5K words) 2. `Lesson Bookends.md` — first and last lesson, fully workshopped 3. `Game Design Patterns.md` — 20 patterns mapping game mechanics → agent architecture 4. `Research - Schell Lenses x Dwarf Fortress x The Claw.md` 5. `Research - 4CID Learning Design Bible.md` 6. `Research - Dwarf Fortress Design Philosophy.md` 7. `Research - just-bash as Game Engine.md` 8. `Research - Game Design Bibles.md` — Koster + Schell 9. `Research - Prior Art and Landscape.md` 10. `Research - Multi-Agent Frameworks as MUD Architecture.md` 11. `Research - MUD Architecture and Platform Primitives.md` ### Public gist (full design docs): https://gist.github.com/joelhooks/99b7188fdd775b32b646ee72484774cc ## Two Versions 1. **Vercel Academy** — toned-down business version. Vercel-native stack (Workflow, Sandbox, Queues, AI Gateway, just-bash). Draft: https://vercel.com/academy/draft/agent-game-generation 2. **wizardshit.ai** — the full unfiltered version. Free to use whatever infra. Inngest, k8s, Redis, self-hosted — whatever's best. ## The Claw: Minions of Toil The flagship course. A roguelite colony management sim where Zots (autonomous AI agents) toil in a fantasy dungeon generated from real codebases. Core insight: **the game mechanics ARE agent architecture patterns.** Health bar = context window. Abilities = tools. Party = multi-agent delegation. Combat = error handling. The representation IS the thing. Design foundations: - **Koster** — fun = learning patterns in a safe space - **Schell** — 100+ lenses for design evaluation - **4C/ID** — whole-task from day 1, scaffolding fades, driven by what breaks - **Dwarf Fortress** — colony management, autonomous actors, "losing is fun", emergent narrative Tech (wizardshit version — free to choose): - **just-bash** — the game engine (virtual filesystem sandbox) - **AI SDK** — Zot brains - **Inngest** — tick engine, durable workflows - Whatever persistence/state makes sense Linear: [DX-2875](https://linear.app/vercel/issue/DX-2875/agent-game-generation) ## Working With This Project 1. For gremlin app work: `cd ~/Code/badass-courses/gremlin` and read its AGENTS.md 2. For course design: `cd ~/Code/joelhooks/manage` and read the brain vault docs 3. For joelclaw integration: this is where wizardshit infra decisions may overlap with joelclaw patterns 4. Load the `gremlin` skill for gremlin-repo-specific guidance
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.