shinyobjectz

montology's vocabulary — every defined word, its code and its test. GENERATED from .monty/ontology.db by `monty sync`; never hand-edit. Check `monty onto check <name>` BEFORE naming anything.

Design-system and vocabulary drift for this repo — the Tailwind theme as enforced tokens, rogue values with nearest-token receipts, words as a database checked before naming anything, org ontologies inherited across repos, and token-precise renames. Use when…

How a workspace's vocabulary starts — phased questions served to the people who own the code as a clean one-question-at-a-time form in their browser (a local HTML file, no hosted service), answers returned to the agent on disk, each round written from the…

Agent CLI and deck DSL for Reactable — native stage + metal Mac capture. Author decks in `.work` format, preview via `reactable stage open` (same WKWebView as recording), manage takes and HyperFrames post. Use when authoring presentation recordings, editing…

Model-aware image prompting for Nano Banana Pro and Nano Banana 2. Covers generation, editing, continuity, text-in-image, style routing, and structured JSON output.

This skill should be used when the user wants to generate images, edit photos, design YouTube thumbnails, create infographics, build storyboards, or translate text inside images using Nano Banana (Google's Gemini image generation models). Applies to any…

blazie's vocabulary — every defined word, its code and its test. GENERATED from .monty/ontology.db by `monty sync`; never hand-edit. Check `monty onto check <name>` BEFORE naming anything.

Work against a blazie cluster through the control plane's MCP server — run Lua against worlds, claim worlds, read how a cluster is opening. Use when the task touches a blazie backend.

Routes Code-as-X requirements to categories and polyglot tool chains. Reads catalog and router .work files, creates session.work files, drives the code-as worktop, and runs local step scripts. Use for presentations, video, diagrams, CAD, documents, or any…

Evaluate and improve the Agent Experience (AX) of a tool, API, SDK, skill, or system — how well it serves an average agent. Use when the user says "agent ergonomics", "AX", "rate the agent ergonomics of X", "how agent-friendly is this", or invokes…