Agent skill

Canvas Expand

by Xiangyu-CAS in Xiangyu-CAS/codex-canvas

Outpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas.

MITAuto-check passed

Install Canvas Expand

skills CLI
$ npx skills add Xiangyu-CAS/codex-canvas --skill canvas-expand -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Xiangyu-CAS/codex-canvas canvas-expand --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Xiangyu-CAS/codex-canvas.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/canvas-expand .claude/skills/canvas-expand && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
canvas-expand
GitHub stars
137
Token cost
~390 tokens
SKILL.md length
215 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Outpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas.

  • Works in 8 steps: Codex-Canvas first creates a padded PNG… → Use the user's Expand preset, scale,… → Preserve the source subject identity,… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Canvas Expand is an agent skill from Xiangyu-CAS/codex-canvas. Outpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas.

Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Infinite canvas plugin for codex; Codex无限画布插件,图层分离,涂抹修改. The licence is MIT.

Example prompts

  • “/canvas-expand”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Codex-Canvas first creates a padded PNG input using the selected scale, target ratio, and the user's final source-image position inside…
  2. Use the user's Expand preset, scale, ratio, and optional text as the primary expansion instruction.
  3. Preserve the source subject identity, visible text, composition anchor, perspective, lighting, colors, and design intent.
  4. Fill the padded surrounding area with coherent generated content. Do not leave blurred padding, blank margins, checkerboards, seams, or…
  5. Extend the scene or design outside the current frame. Do not crop, zoom in, replace the main subject, or redesign unrelated content.
  6. Keep the original image content visually coherent with the newly generated surrounding area.
  7. Save the final expanded image as a PNG under the Codex-Canvas job output directory.
  8. Codex-Canvas will collect the output and place it in a row to the right of the source image.

What it can do on your machine

Read from SKILL.md and the folder at commit b801839. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Canvas Expand loads about 390 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 215 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~390

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Xiangyu-CAS/codex-canvas at commit b801839, republished under its MIT licence (© Xiangyu-CAS). 215 words, ~390 tokens.

Download SKILL.mdSave it as .claude/skills/canvas-expand/SKILL.md (or your agent's skills folder).
name
canvas-expand
description
Outpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas.

Codex-Canvas Expand

Use this skill when the user invokes Expand from Codex-Canvas or asks to extend a selected canvas image beyond its current edges.

Behavior

  1. Codex-Canvas first creates a padded PNG input using the selected scale, target ratio, and the user's final source-image position inside the preview frame. Treat the pasted original content as locked source content and the padded surroundings as the outpaint region.
  2. Use the user's Expand preset, scale, ratio, and optional text as the primary expansion instruction.
  3. Preserve the source subject identity, visible text, composition anchor, perspective, lighting, colors, and design intent.
  4. Fill the padded surrounding area with coherent generated content. Do not leave blurred padding, blank margins, checkerboards, seams, or artificial borders in the final image.
  5. Extend the scene or design outside the current frame. Do not crop, zoom in, replace the main subject, or redesign unrelated content.
  6. Keep the original image content visually coherent with the newly generated surrounding area.
  7. Save the final expanded image as a PNG under the Codex-Canvas job output directory.
  8. Codex-Canvas will collect the output and place it in a row to the right of the source image.

Do not ask follow-up questions from a background Expand job. Make the most reasonable outpainted expansion from the provided instruction.

© Xiangyu-CAS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/canvas-expand of Xiangyu-CAS/codex-canvas.

Open the folder on GitHubat commit b801839

Compare with similar skills

Canvas Expand next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Canvas Expand compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Canvas Expand this skillXiangyu-CAS/codex-canvas137—~390Automated safety check: PassMIT
Canvasopenclaw/openclaw392k—~263Automated safety check: PassMIT
Canva Designerasgeirtj/system_prompts_leaks69k—~2.1kAutomated safety check: PassCC0-1.0
Plan Canvasaffaan-m/ECC277k1 repos~2.2kAutomated safety check: PassMIT
Engine Selectionsickn33/agentic-awesome-skills47k1 repos~1.2kAutomated safety check: PassMIT
Canvas Designanthropics/skills180k52 repos~3kAutomated safety check: PassApache-2.0

Similar skills

  • Canvas

    openclaw/openclaw

    Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

    392k GitHub stars~263 tokensUpdated today
    Auto-check passed
  • Canva Designer

    asgeirtj/system_prompts_leaks

    Creates and edits Canva designs, generates images and works with brand kits through the canva CLI and Canva's official MCP server, from decks to social posts.

    69k GitHub stars~2.1k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Plan Canvas

    affaan-m/ECC

    Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page.

    277k GitHub starsUsed in 1 repo~2.2k tokens
    Frontend & DesignAuto-check passed
  • Engine Selection

    sickn33/agentic-awesome-skills

    Selects game engines and frameworks by platform, genre, and architecture (full canvas shell vs hybrid DOM shell + guest viewport).

    47k GitHub starsUsed in 1 repo~1.2k tokens
    Game DevelopmentAuto-check passed
  • Canvas Design

    anthropics/skills

    Official

    Creates original posters and static art as PNG or PDF by first writing a short design philosophy, then expressing it visually on a canvas.

    180k GitHub starsUsed in 52 repos~3k tokens
    Media & CreativeAuto-check passed
  • Canvas Automation

    ComposioHQ/awesome-claude-skills

    Automate Canvas tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~727 tokens
    Productivity & AutomationAuto-check passed

More from Xiangyu-CAS/codex-canvas

  • Codex Canvas

    Xiangyu-CAS/codex-canvas

    安装、更新并使用 Codex-Canvas。通过 Red SkillHub 或其他 Skill 渠道获得本 Skill 后,继续把最新稳定版 Codex-Canvas 安装为 Codex personal plugin;Skill 安装不是终态。适用于用户要求安装或升级 codex-canvas、输入 /canvas、打开本地无限画布、收集生成图片、把画布图片发送回 Codex 对话,或运行…

    137 GitHub stars~880 tokensUpdated 10 days ago
    Auto-check passed
  • Canvas

    Xiangyu-CAS/codex-canvas

    Open and use Codex-Canvas, a project-local infinite canvas for Codex image generation.

    137 GitHub stars~1.7k tokensUpdated 10 days ago
    Auto-check passed
  • Canvas Edit Elements

    Xiangyu-CAS/codex-canvas

    Generate an instance segmentation map for a selected Codex-Canvas image, split the source into transparent element layers, and collect the layers back onto the canvas.

    137 GitHub stars~1.1k tokensUpdated 10 days ago
    Auto-check passed
  • Canvas Quick Edit

    Xiangyu-CAS/codex-canvas

    Run a user-described Quick Edit on a selected Codex-Canvas image and collect the result back onto the canvas.

    137 GitHub stars~505 tokensUpdated 10 days ago
    Auto-check passed
  • Canvas Edit Text

    Xiangyu-CAS/codex-canvas

    Recognize visible text in a selected Codex-Canvas image, apply a user-described text edit with imagegen, and collect the result back onto the canvas.

    137 GitHub stars~365 tokensUpdated 10 days ago
    Auto-check passed
  • Canvas Remove Bg

    Xiangyu-CAS/codex-canvas

    Remove the background from a selected Codex-Canvas image and collect a transparent PNG result back onto the canvas.

    137 GitHub stars~400 tokensUpdated 10 days ago
    Auto-check passed

Questions about Canvas Expand

What does Canvas Expand do?

Outpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas. Canvas Expand is an agent skill from Xiangyu-CAS/codex-canvas. Outpaint a selected Codex-Canvas image beyond its current frame and collect the expanded image back onto the canvas.

How do I install Canvas Expand in Claude Code?

Run `npx skills add Xiangyu-CAS/codex-canvas --skill canvas-expand -a claude-code`. Or copy the skill folder (skills/canvas-expand in Xiangyu-CAS/codex-canvas) into .claude/skills/canvas-expand in your project. Claude Code loads it when a task matches its description.

How do I install Canvas Expand in Codex?

Run `npx skills add Xiangyu-CAS/codex-canvas --skill canvas-expand -a codex`. Or copy the skill folder (skills/canvas-expand in Xiangyu-CAS/codex-canvas) into .agents/skills/canvas-expand in your project. Codex loads it when a task matches its description.

Can I use Canvas Expand in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Xiangyu-CAS/codex-canvas --skill canvas-expand -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/canvas-expand, .gemini/skills/canvas-expand, .github/skills/canvas-expand and .opencode/skills/canvas-expand in your project.

What does Canvas Expand need to run?

SKILL.md names no scripts, command-line tools or credentials: Canvas Expand is instructions for the agent only.

Does Canvas Expand access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Canvas Expand safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Canvas Expand use?

Canvas Expand is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Canvas Expand use?

About 390 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Canvas Expand?

Skills that share tags, products or a category with Canvas Expand: Canvas (openclaw/openclaw, 392k stars), Canva Designer (asgeirtj/system_prompts_leaks, 69k stars), Plan Canvas (affaan-m/ECC, 277k stars) and Engine Selection (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Canvas Expand?

Xiangyu-CAS (a GitHub user) maintains it in Xiangyu-CAS/codex-canvas, which has 137 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 1, 2026.

Source: Xiangyu-CAS/codex-canvas on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.