blank-canvas — for Claude Code blank-canvas, ppl-plus-ultra, community, for Claude Code, ide skills, canvas initialization, workspace setup, package.json analysis, Bash scripting, boundary rules enforcement

v1.0.0
GitHub

About this Skill

Perfect for AI Agents needing efficient workflow initialization and phase completion tracking in a canvas workspace environment. blank-canvas is a specialized AI agent skill that initializes and sets up canvas workspaces for efficient coding and development.

Features

Load Canvas Workspace State using package.json and directory structure
Report Phase Completion using Bash scripts and file existence checks
Load Boundary Rules from .claude/AGENT-BOUNDARIES.md for secure coding
Output Summary Report in a standardized format for easy reference

# Core Topics

for Claude Code canvas initialization workspace setup package.json analysis Bash scripting boundary rules enforcement
BigBruddaThunda BigBruddaThunda
[1]
[0]
Updated: 3/16/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Locale and body language aligned
Review Score
8/11
Quality Score
33
Canonical Locale
en
Detected Body Locale
en

Perfect for AI Agents needing efficient workflow initialization and phase completion tracking in a canvas workspace environment. blank-canvas is a specialized AI agent skill that initializes and sets up canvas workspaces for efficient coding and development.

Core Value

Empowers agents to streamline their workflow by initializing the canvas workspace, reporting package details, and tracking phase completion using Bash scripts and glob patterns, while enforcing boundary rules defined in .claude/AGENT-BOUNDARIES.md.

Ideal Agent Persona

Perfect for AI Agents needing efficient workflow initialization and phase completion tracking in a canvas workspace environment.

↓ Capabilities Granted for blank-canvas

Initializing the canvas workspace for efficient AI coding
Tracking phase completion for types, weights, rendering, tokens, and pipeline artifacts
Enforcing boundary rules to prevent writes to prohibited targets like cards/, html/, web/, and middle-math/

! Prerequisites & Limits

  • Requires access to canvas/package.json and directory structure
  • Limited to Bash script execution for phase completion checks
  • Active write scope restricted to canvas/ paths only

Why this page is reference-only

  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Install Path

Start With Installation And Validation

If this skill is worth continuing with, the next step is to confirm the install command, CLI write path, and environment validation.
Trusted Recheck

Cross-Check Against Trusted Picks

If you are still comparing multiple skills or vendors, go back to the trusted collection before amplifying repository noise.
Workflow

Move To Workflow Collections For Team Rollout

When the goal shifts from a single skill to team handoff, approvals, and repeatable execution, move into workflow collections.
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is blank-canvas?

Perfect for AI Agents needing efficient workflow initialization and phase completion tracking in a canvas workspace environment. blank-canvas is a specialized AI agent skill that initializes and sets up canvas workspaces for efficient coding and development.

How do I install blank-canvas?

Run the command: npx killer-skills add BigBruddaThunda/ppl-plus-ultra/blank-canvas. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for blank-canvas?

Key use cases include: Initializing the canvas workspace for efficient AI coding, Tracking phase completion for types, weights, rendering, tokens, and pipeline artifacts, Enforcing boundary rules to prevent writes to prohibited targets like cards/, html/, web/, and middle-math/.

Which IDEs are compatible with blank-canvas?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for blank-canvas?

Requires access to canvas/package.json and directory structure. Limited to Bash script execution for phase completion checks. Active write scope restricted to canvas/ paths only.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add BigBruddaThunda/ppl-plus-ultra/blank-canvas. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use blank-canvas immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

blank-canvas

Boost development with the blank-canvas AI agent skill, initializing canvas workspaces for efficient coding. Discover how it streamlines your workflow and

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Initialize the canvas workspace.

Workflow

1. Load Canvas Workspace State

Read the workspace manifest and directory structure:

Read canvas/package.json
Glob canvas/src/**/*.ts
Glob canvas/tests/**/*.test.ts

Report: package name, version, script targets, and how many source files and test files exist.

2. Report Phase Completion

Check which Phase 1–5 artifacts exist:

PhaseArtifactCheck
1canvas/src/types/scl.tsDoes file exist?
2canvas/src/weights/Does directory contain .ts files?
3canvas/src/rendering/Does directory contain index.ts?
4canvas/src/tokens/tokens.tsDoes file exist?
5canvas/src/rendering/index.tsDoes weightsToCSSVars export exist?

Use Bash: test -f canvas/src/types/scl.ts && echo PHASE1_OK || echo PHASE1_MISSING

For each phase, report: COMPLETE or MISSING.

3. Load Boundary Rules

Read .claude/AGENT-BOUNDARIES.md — specifically the Canvas Path-Gating section and the canvas-renderer subagent constraints.

Confirm the active write scope: canvas/ paths only.

Prohibited write targets:

  • cards/ — workout card content (card-generator territory)
  • html/ — legacy HTML scaffold (separate phase)
  • web/ — web application layer (Phase 4/5)
  • middle-math/ — computation engine (separate workspace)

4. Report Current State

Output a summary in this format:

Canvas Workspace State
======================
Package: [name@version]
Source files: [count]
Test files: [count]

Phase completion:
  Phase 1 (types):     [COMPLETE | MISSING]
  Phase 2 (weights):   [COMPLETE | MISSING]
  Phase 3 (rendering): [COMPLETE | MISSING]
  Phase 4 (tokens):    [COMPLETE | MISSING]
  Phase 5 (pipeline):  [COMPLETE | MISSING]

canvas/components/ contents:
  [list files or "empty — ready for canvas-renderer"]

Active agent scope: canvas/ only
Prohibited: cards/, html/, web/, middle-math/

If $ARGUMENTS is provided, focus the report on the named phase (e.g., "5" → show Phase 5 details).

Related Skills

Looking for an alternative to blank-canvas or another community skill for your workflow? Explore these related open-source skills.

View All

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

The React Framework

★ 138.4k
⑂ 0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

★ 98.6k
⑂ 0
Developer