Agent skill

Canvasight Imagegen

by Niall-Young in Niall-Young/Canvasight

Generate new raster images with Codex imagegen and add every final result to the active Canvasight Page as a managed Asset Node.

MITAuto-check passedMedia & Creative

Install Canvasight Imagegen

skills CLI

$ npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a claude-code

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

GitHub CLI

$ gh skill install Niall-Young/Canvasight canvasight-imagegen --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/Niall-Young/Canvasight.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/canvasight/skills/canvasight-imagegen .claude/skills/canvasight-imagegen && 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/

Paste into Claude Code

Install the "canvasight-imagegen" agent skill from https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen into .claude/skills/canvasight-imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvasight-imagegen", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Niall-Young/Canvasight canvasight-imagegen --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Niall-Young/Canvasight.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/canvasight/skills/canvasight-imagegen .agents/skills/canvasight-imagegen && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "canvasight-imagegen" agent skill from https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen into .agents/skills/canvasight-imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvasight-imagegen", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Niall-Young/Canvasight canvasight-imagegen --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Niall-Young/Canvasight.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/canvasight/skills/canvasight-imagegen .cursor/skills/canvasight-imagegen && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "canvasight-imagegen" agent skill from https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen into .cursor/skills/canvasight-imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvasight-imagegen", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Niall-Young/Canvasight.git --path plugins/canvasight/skills/canvasight-imagegen

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Niall-Young/Canvasight canvasight-imagegen --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Niall-Young/Canvasight.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/canvasight/skills/canvasight-imagegen .gemini/skills/canvasight-imagegen && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "canvasight-imagegen" agent skill from https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen into .gemini/skills/canvasight-imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvasight-imagegen", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Niall-Young/Canvasight canvasight-imagegen

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Niall-Young/Canvasight.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/canvasight/skills/canvasight-imagegen .github/skills/canvasight-imagegen && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "canvasight-imagegen" agent skill from https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen into .github/skills/canvasight-imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvasight-imagegen", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Niall-Young/Canvasight canvasight-imagegen --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Niall-Young/Canvasight.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/canvasight/skills/canvasight-imagegen .opencode/skills/canvasight-imagegen && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "canvasight-imagegen" agent skill from https://github.com/Niall-Young/Canvasight/tree/main/plugins/canvasight/skills/canvasight-imagegen into .opencode/skills/canvasight-imagegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvasight-imagegen", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: canvasight-imagegen
GitHub stars: 213
Token cost: ~1.1k tokens
SKILL.md length: 560 words
Files: 2
Skills in repo: 8
Repo updated: Sep 24, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate new raster images with Codex imagegen and add every final result to the active Canvasight Page as a managed Asset Node.

Works in 6 steps: Read the active task's exact… → Reuse a Canvasight native widget only… → Call get_canvasight_graph_context with… → …
The user invokes @Canvasight
SKILL.md covers Workflow and Boundaries
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Canvasight Imagegen is an agent skill from Niall-Young/Canvasight. Generate new raster images with Codex imagegen and add every final result to the active Canvasight Page as a managed Asset Node. Use when the user invokes @Canvasight or otherwise asks to generate, create, draw, or render a new image directly into Canvasight. Do not use for editing an existing Canvasight Asset in place.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Media & Creative, covering Image generation. The repository describes itself as: 用于梳理任务然后交付给 AI 工具的 plugin 插件. The licence is MIT.

When your agent uses it

The user invokes @Canvasight
Otherwise asks to generate
Render a new image directly into Canvasight
Editing an existing Canvasight Asset in place

Example prompts

“/canvasight-imagegen”

Workflow steps

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

Read the active task's exact CODEX_THREAD_ID.
Reuse a Canvasight native widget only when this task already has verified fullscreen ready evidence. Otherwise follow canvasight-open…
Call get_canvasight_graph_context with the same threadId. Preserve its projectPath, contextId, documentRevision, and active Page identity…
Invoke the system $imagegen Skill. Use its built-in tool path by default, one call per requested final image or variant. Follow its…
Keep only outputs that pass imagegen inspection. Call add_canvasight_generated_images with
Treat written, merged, and conflict-copy as successful imports. Report the target Page, created node count, managed project-relative…

What it can do on your machine

Read from SKILL.md and the folder at commit f47e0bf. 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

Canvasight Imagegen loads about 1.1k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 560 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~85
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 Niall-Young/Canvasight at commit f47e0bf, republished under its MIT licence (© Niall-Young). 560 words, ~1,089 tokens.

Download SKILL.mdSave it as .claude/skills/canvasight-imagegen/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: canvasight-imagegen
description: Generate new raster images with Codex imagegen and add every final result to the active Canvasight Page as a managed Asset Node. Use when the user invokes @Canvasight or otherwise asks to generate, create, draw, or render a new image directly into Canvasight. Do not use for editing an existing Canvasight Asset in place.

Canvasight Image Generation

Generate with the system $imagegen Skill, then import the accepted bitmap outputs through Canvasight's atomic generated-image tool. Never hand-edit .scatter, pass an unmanaged path to write_canvasight_graph, or substitute browser automation.

Workflow

Read the active task's exact CODEX_THREAD_ID.
Reuse a Canvasight native widget only when this task already has verified fullscreen ready evidence. Otherwise follow canvasight-open: call open_canvasight with that threadId, preserve its sessionId and openAttemptId, then call await_canvasight_widget_ready. Stop before generation unless the result is verified status: "ready" with React, project hydration, rendered canvas, and visible non-zero canvas evidence.
Call get_canvasight_graph_context with the same threadId. Preserve its projectPath, contextId, documentRevision, and active Page identity before starting image generation. Later Page switches must not retarget the import.
Invoke the system $imagegen Skill. Use its built-in tool path by default, one call per requested final image or variant. Follow its transparency, inspection, retry, and CLI-consent rules exactly.
Keep only outputs that pass imagegen inspection. Call add_canvasight_generated_images with:
- the exact threadId and captured projectPath;
- the captured contextId and documentRevision as expectedRevision;
- one stable unique clientMutationId for this exact batch, reused only for retries;
- one { "path", "title"? } entry per final image, in the requested display order.
Treat written, merged, and conflict-copy as successful imports. Report the target Page, created node count, managed project-relative paths, final prompt set, and whether imagegen used the built-in or user-approved CLI path.

Product-design option flow

When the request is to explore a product or UI design before frontend implementation:

Resolve the target surface, intended user, outcome, viewport, and hard constraints before generation.
Unless the user specifies another count, generate exactly three independent UI images. Each image is one distinct direction with a meaningfully different hierarchy, layout, or interaction model; never combine multiple directions into one image.
Import all accepted options as separate Asset Nodes in their visible result order, then stop so the user can connect the preferred image into the ordinary canvas flow. Do not choose a direction or start implementation on the user's behalf.
Run continues to start only from executable Task or Group surfaces. For this option flow, run the ordinary Task flow: connected image Assets travel with that Task exactly like node attachments did, while generated images outside its reachable flow are unrelated. An Asset never runs independently, and no separate selection marker or persisted role is needed.
If the project exposes a matching product-design or image-to-code Skill, it may be named visibly in the downstream Task body. Do not persist a hidden Skill assignment or assume that an unavailable external Skill is installed.

Show full SKILL.md (127 more words)Show less

Boundaries

This Skill creates new PNG, JPEG, or WebP Asset Nodes only. Do not use it to mutate or replace an existing Canvasight Asset.
Import at most 16 final images per tool call. For a larger explicit request, use successive batches without dropping results.
Do not generate anything when native Canvasight opening or ready verification fails; the requested result could not be delivered to the canvas.
If imagegen fails, do not create a placeholder node. If import fails, keep the generated source and report the actionable Canvasight error.
On context_expired or context_revision_mismatch, do not guess a different Page. Explain that the captured Page binding expired and ask the user to repeat the image request.
Never expose daemon URLs, tokens, or managed absolute paths in the user-facing result.

Files

SKILL.md and 1 other file in plugins/canvasight/skills/canvasight-imagegen of Niall-Young/Canvasight.

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit f47e0bf

Compare with similar skills

Canvasight Imagegen 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.

Canvasight Imagegen compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Canvasight Imagegen this skillNiall-Young/Canvasight	213	—	~1.1k	Automated safety check: Pass	MIT	17 days ago
AI Image Generation and Editingzhayujie/CowAgent	47k	—	~1.3k	Automated safety check: Pass	MIT	yesterday
Structured Image Generationbytedance/deer-flow	84k	4 repos	~2.9k	Automated safety check: Pass	MIT	today
Canghe Comicfreestylefly/canghe-skills	461	8 repos	~3.2k	Automated safety check: Pass	None	4 mo ago
Generate Imageynulihao/AgentSkillOS	618	10 repos	~1.7k	Automated safety check: Notes	None	7 mo ago
GPT Image Generation CLIwuyoscar/GPT-Image2-Skill	5.7k	—	~2.5k	Automated safety check: Notes	MIT	10 days ago

Similar skills

AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
47k GitHub stars~1.3k tokensUpdated yesterday
Media & CreativeAuto-check passed
Structured Image Generation
bytedance/deer-flow
Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.
84k GitHub starsUsed in 4 repos~2.9k tokens
Media & CreativeAuto-check passed
Canghe Comic
freestylefly/canghe-skills
Knowledge comic creator supporting multiple art styles and tones.
461 GitHub starsUsed in 8 repos~3.2k tokens
Media & CreativeAuto-check passed
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
618 GitHub starsUsed in 10 repos~1.7k tokens
Media & CreativeAuto-check: notes
GPT Image Generation CLI
wuyoscar/GPT-Image2-Skill
Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.
5.7k GitHub stars~2.5k tokensUpdated 10 days ago
Media & CreativeAuto-check: notes
Minimal Zine Poster Generator
LiamGvchi/gc-minimal-zine-poster
Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.
7.3k GitHub stars~2.9k tokensUpdated 1 mo ago
Media & CreativeAuto-check passed

More from Niall-Young/Canvasight

All 8 skills in this repo

Canvasight Agent Team
Niall-Young/Canvasight
Follow Canvasight's Agent Team, role-registry, and agent-report protocol.
213 GitHub stars~959 tokensUpdated 17 days ago
Auto-check passed
Canvasight Graph Writer
Niall-Young/Canvasight
Create, refine, or replace Canvasight graphs through writecanvasightgraph; combine professional content Skills with Canvasight's validated horizontal graph structure; and assign explicit or clearly…
213 GitHub stars~4.2k tokensUpdated 17 days ago
Auto-check passed
Canvasight Open
Niall-Young/Canvasight
Open, reopen, attach, and verify Canvasight's Codex native widget, or explicitly open a browser fallback.
213 GitHub stars~1.1k tokensUpdated 17 days ago
Auto-check passed
Canvasight
Niall-Young/Canvasight
Canvasight plugin index. An agent skill from Niall-Young/Canvasight.
213 GitHub stars~807 tokensUpdated 17 days ago
Auto-check passed
Canvasight Run
Niall-Young/Canvasight
Handle Chat-only Canvasight Run output in the current Codex thread.
213 GitHub stars~764 tokensUpdated 17 days ago
Auto-check passed
Canvasight Troubleshooting
Niall-Young/Canvasight
Diagnose and fix Canvasight plugin, MCP, native-widget readiness, host bridge, daemon, browser fallback, Run delivery, install, cache, or connection problems.
213 GitHub stars~710 tokensUpdated 17 days ago
Auto-check passed

Questions about Canvasight Imagegen

What does Canvasight Imagegen do?

Generate new raster images with Codex imagegen and add every final result to the active Canvasight Page as a managed Asset Node. Canvasight Imagegen is an agent skill from Niall-Young/Canvasight. Generate new raster images with Codex imagegen and add every final result to the active Canvasight Page as a managed Asset Node.

When should I use Canvasight Imagegen?

Canvasight Imagegen fits situations like: the user invokes @Canvasight; otherwise asks to generate; render a new image directly into Canvasight; editing an existing Canvasight Asset in place.

How do I install Canvasight Imagegen in Claude Code?

Run `npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a claude-code`. Or copy the skill folder (plugins/canvasight/skills/canvasight-imagegen in Niall-Young/Canvasight) into .claude/skills/canvasight-imagegen in your project. Claude Code loads it when a task matches its description.

How do I install Canvasight Imagegen in Codex?

Run `npx skills add Niall-Young/Canvasight --skill canvasight-imagegen -a codex`. Or copy the skill folder (plugins/canvasight/skills/canvasight-imagegen in Niall-Young/Canvasight) into .agents/skills/canvasight-imagegen in your project. Codex loads it when a task matches its description.

Can I use Canvasight Imagegen 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 Niall-Young/Canvasight --skill canvasight-imagegen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/canvasight-imagegen, .gemini/skills/canvasight-imagegen, .github/skills/canvasight-imagegen and .opencode/skills/canvasight-imagegen in your project.

What does Canvasight Imagegen need to run?

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

Does Canvasight Imagegen 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 Canvasight Imagegen 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 Canvasight Imagegen use?

Canvasight Imagegen 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 Canvasight Imagegen use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Canvasight Imagegen?

Skills that share tags, products or a category with Canvasight Imagegen: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Structured Image Generation (bytedance/deer-flow, 84k stars), Canghe Comic (freestylefly/canghe-skills, 461 stars) and Generate Image (ynulihao/AgentSkillOS, 618 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Canvasight Imagegen?

Niall-Young (a GitHub user) maintains it in Niall-Young/Canvasight, which has 213 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 24, 2026.

Source: Niall-Young/Canvasight on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Canvasight Imagegen

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Canvasight Image Generation

Workflow

Product-design option flow

Boundaries

Files

Compare with similar skills

Similar skills

More from Niall-Young/Canvasight

Related

Questions about Canvasight Imagegen