OpenClaw Canvas: HTML/JS dashboard display on nodes, live reload, JS eval, screenshot capture
Scanned 5/29/2026
Install via CLI
Skills Directoryopenskills install alphaonedev/openclaw-graph---
name: canvas
cluster: community
description: "OpenClaw Canvas: HTML/JS dashboard display on nodes, live reload, JS eval, screenshot capture"
tags: ["canvas", "dashboard", "html", "openclaw"]
dependencies: []
composes: []
similar_to: []
authorization_required: false
scope: general
model_hint: claude-sonnet
embedding_hint: "openclaw canvas html dashboard display node live reload screenshot"
clawhub_install: "clawhub install canvas"
note: "NOT installed via ClaWHub CLI — registered in Neo4j skill graph only. To activate: clawhub install canvas"
---
# Canvas
## Purpose
OpenClaw Canvas: HTML/JS dashboard display on nodes, live reload, JS eval, screenshot capture
## Install When Needed
```
clawhub install canvas
```
## Note
This skill is registered in the Neo4j skill graph for discovery purposes only.
It is **NOT installed** via the traditional ClaWHub methodology.
When a task matches this skill, the agent will inform you to install it if needed.
## When to Use
- When the task requires canvas capabilities
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
