clawdis-canvas
About
This skill enables developers to programmatically control the Clawdis Canvas panel via CLI for presenting HTML/JS interfaces and A2UI surfaces. Key capabilities include rendering content, evaluating JavaScript, capturing snapshots, and managing gateway-hosted A2UI applications with action bridging. Use it to automate UI testing, visualization, and interaction workflows within the Clawdis environment.
Quick Install
Claude Code
Recommended/plugin add https://github.com/steipete/clawdisgit clone https://github.com/steipete/clawdis.git ~/.claude/skills/clawdis-canvasCopy and paste this command in Claude Code to install this skill
Documentation
Clawdis Canvas
Use Canvas to render HTML/JS or A2UI surfaces and capture snapshots.
Core commands
- Present:
clawdis canvas present [--node <id>] [--target <path>] - Hide:
clawdis canvas hide - Eval JS:
clawdis canvas eval --js "..." - Snapshot:
clawdis canvas snapshot
A2UI
- Push JSONL:
clawdis canvas a2ui push --jsonl /path/to/file.jsonl - Reset:
clawdis canvas a2ui reset
Notes
- Keep HTML under
~/clawd/canvaswhen targeting remote nodes. - Use snapshot after renders to verify UI state.
- Treat A2UI as gateway-hosted at
http(s)://<gateway-host>:18789/__clawdis__/a2ui/. - Rely on
canvas a2ui push/resetto auto-navigate the Canvas to the gateway-hosted A2UI page. - Expect A2UI to fail if the Gateway does not advertise
canvasHostUrlor is unreachable:A2UI_HOST_NOT_CONFIGUREDA2UI_HOST_UNAVAILABLE
A2UI quick flow
- Ensure the Gateway is running and reachable from the node.
- Build JSONL with v0.8 server→client messages (
beginRendering,surfaceUpdate,dataModelUpdate,deleteSurface).- Do not use v0.9
createSurface(unsupported).
- Do not use v0.9
- Push JSONL and (optionally) snapshot the result.
Example JSONL (v0.8)
cat > /tmp/a2ui-v0.8.jsonl <<'EOF'
{"surfaceUpdate":{"surfaceId":"main","components":[{"id":"root","component":{"Column":{"children":{"explicitList":["title","content"]}}}},{"id":"title","component":{"Text":{"text":{"literalString":"A2UI (v0.8)"},"usageHint":"h1"}}},{"id":"content","component":{"Text":{"text":{"literalString":"If you can read this, A2UI is live."},"usageHint":"body"}}}]}}
{"beginRendering":{"surfaceId":"main","root":"root"}}
EOF
clawdis canvas a2ui push --jsonl /tmp/a2ui-v0.8.jsonl --node <id>
Action callbacks (A2UI → agent)
- A2UI user actions (buttons, etc.) are bridged from the WebView back to the node via
clawdisCanvasA2UIAction. - Handle them on the agent side as
CANVAS_A2UImessages (node → gateway → agent).
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
creating-opencode-plugins
MetaThis skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
Algorithmic Art Generation
MetaThis skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.
