Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.
Install Canvas Ops Skill
$ npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install OpenLoaf/OpenLoaf canvas-ops-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/canvas-ops/en .claude/skills/canvas-ops-skill && rm -rf skills-srcUse ~/.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/
Install the "canvas-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/en into .claude/skills/canvas-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvas-ops-skill", 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 install https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/enType 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.
$ npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install OpenLoaf/OpenLoaf canvas-ops-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/canvas-ops/en .agents/skills/canvas-ops-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "canvas-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/en into .agents/skills/canvas-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvas-ops-skill", 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.
$ npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install OpenLoaf/OpenLoaf canvas-ops-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/canvas-ops/en .cursor/skills/canvas-ops-skill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "canvas-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/en into .cursor/skills/canvas-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvas-ops-skill", 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 https://github.com/OpenLoaf/OpenLoaf.git --path apps/server/src/ai/builtin-skills/canvas-ops/en--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install OpenLoaf/OpenLoaf canvas-ops-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/canvas-ops/en .gemini/skills/canvas-ops-skill && rm -rf skills-srcUse ~/.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/
Install the "canvas-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/en into .gemini/skills/canvas-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvas-ops-skill", 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.
$ gh skill install OpenLoaf/OpenLoaf canvas-ops-skillInstalls 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).
$ npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/canvas-ops/en .github/skills/canvas-ops-skill && rm -rf skills-srcUse ~/.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/
Install the "canvas-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/en into .github/skills/canvas-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvas-ops-skill", 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.
$ npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install OpenLoaf/OpenLoaf canvas-ops-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/canvas-ops/en .opencode/skills/canvas-ops-skill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "canvas-ops-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/canvas-ops/en into .opencode/skills/canvas-ops-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "canvas-ops-skill", 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
canvas-ops-skill- GitHub stars
- 108
- Token cost
- ~1.4k tokens
- SKILL.md length
- 488 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.
- Wants lifecycle management of OpenLoaf canvases / whiteboards: create
- SKILL.md covers Tool Roster, Which One Should I Use?, Node-Level Operations Inside a… and Cross-Skill Collaboration, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Change ownership
What it does
Canvas Ops Skill is an agent skill from OpenLoaf/OpenLoaf. Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership. Typical phrases: "open a whiteboard", "create an architecture diagram canvas", "clean up unused whiteboards". Not for: data-driven chart visualization (→visualization-ops-skill), AI image or video generation (→cloud-media-skill), editing nodes inside an already-open canvas (handled by the canvas sub-agent).
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Image generation, Diagrams and Subagents. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.
When your agent uses it
- Wants lifecycle management of OpenLoaf canvases / whiteboards: create
- Change ownership
Example prompts
- “open a whiteboard”
- “create an architecture diagram canvas”
- “clean up unused whiteboards”
- “/canvas-ops-skill”
What it can do on your machine
Read from SKILL.md and the folder at commit f7eccf6. 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 Ops Skill loads about 1.4k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 488 words of instructions outside code blocks.
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 OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 488 words, ~1,416 tokens.
Download SKILL.mdSave it as
.claude/skills/canvas-ops-skill/SKILL.md (or your agent's skills folder).- name
- canvas-ops-skill
- description
- Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership. Typical phrases: "open a whiteboard", "create an architecture diagram canvas", "clean up unused whiteboards". **Not for**: data-driven chart visualization (→visualization-ops-skill), AI image or video generation (→cloud-media-skill), editing nodes inside an already-open canvas (handled by the canvas sub-agent).
Canvas Ops Skill
Tool Roster
| Tool | Responsibility | Read-only |
|---|---|---|
BoardQuery | Query the canvas list or a single canvas detail (mode: list / get) | Yes |
BoardMutate | Create / update / duplicate / delete a canvas (action: create / update / delete / duplicate / clear-unbound, etc.) | No |
Loading: Both are deferred tools. Before calling, activate their schemas with
ToolSearch(names: "BoardQuery,BoardMutate").
Which One Should I Use?
Pick by intent:
Want to see which canvases exist? → BoardQuery (mode: list)
Want to filter canvases by project? → BoardQuery (mode: list, with projectId)
Want to search canvases by keyword? → BoardQuery (mode: list, with search)
Want to find orphan canvases with no project? → BoardQuery (mode: list, with unboundOnly: true)
Want a canvas's details and nodes? → BoardQuery (mode: get, with boardId)
Want to create a new canvas? → BoardMutate (action: create)
Want to change a canvas's title/pin/owner? → BoardMutate (action: update)
Want to delete a canvas? → BoardMutate (action: delete) ← default
Want to permanently wipe it? → BoardMutate (action: hard-delete)
Want to duplicate a canvas? → BoardMutate (action: duplicate)
Want to clean up every orphan canvas? → BoardMutate (action: clear-unbound)Node-Level Operations Inside a Canvas
Node editing inside a canvas (adding nodes, connecting edges, changing content) is done by a sub-agent or by the canvas editing tools — it is not directly performed by this skill. What you need to know:
BoardQuery { mode: "get" }returns the canvas's full node and edge information, useful for understanding current content- When the user says "add a box", "connect A to B", "edit this node's content" — those are node-level operations handled by the canvas editing agent
- Your responsibility is to manage the canvas itself (create, delete, ownership, duplicate), not to manipulate elements inside it
Cross-Skill Collaboration
Complex scenarios require multiple skills working together:
- User says "create a project architecture flowchart" → first use
ProjectQueryto understand the project structure, thenBoardMutate { action: "create" }to create the canvas, and finally let the canvas editing agent add nodes and edges based on that structure - User says "visualize the task board" → first use
TaskStatusto fetch the task list, then create the canvas and hand off layout to the editing agent
Core Workflows
Workflow 1: Create a New Canvas
1. Confirm the desired canvas title and owning project
2. BoardMutate (action: create, title: "...") → receive boardId
3. If it should belong to a project, include projectId at create timeWorkflow 2: Tidy Up Canvases
1. BoardQuery (mode: list) → fetch all canvases
2. Analyze which ones have no project and which may be duplicates
3. Report the current state to the user and propose a cleanup plan
4. BoardMutate (action: update, projectId: ...) → attach orphans to a project
5. BoardMutate (action: delete) → remove canvases no longer neededWorkflow 3: Find and View a Canvas
1. BoardQuery (mode: list, search: "keyword") → search matching canvases
2. BoardQuery (mode: get, boardId: "...") → fetch canvas detail (with nodes and edges)
3. Show the user a summary of the canvas contentKey Decisions — And Why
Show full SKILL.md (234 more words)Show less
Where Does boardId Come From?
Check pageContext.boardId first (the canvas the user is currently viewing). If there is no context, search with BoardQuery (mode: list) first. Always confirm the correct boardId first.
Operating on the wrong canvas silently corrupts data — concretely: nodes get added to the wrong canvas, the original canvas's edge relationships get polluted, and the canvas the user sees no longer matches what was actually modified. This kind of damage raises no error; the user may notice the content is scrambled much later, and because the operation has already been saved, it cannot be recovered via undo (only by restoring from backup or rebuilding after hard-delete). So "confirm the boardId first" is not flow-OCD — it's protection against irreversible data confusion.
delete vs hard-delete
Default to delete (soft delete, recoverable). Users change their minds all the time. Only use hard-delete when the user explicitly says "wipe it", "permanently delete".
clear-unbound Demands Extreme Caution
It deletes every canvas not attached to a project in one shot. Before running it, you must first call BoardQuery (mode: list, unboundOnly: true) and have the user confirm the list, to avoid accidentally nuking valuable standalone canvases.
Always Confirm Before Deleting
Before any delete, hard-delete, or clear-unbound operation, show the user the list of canvases that will be affected. This follows the same principle as confirming recipients before sending an email — irreversible operations need a human in the loop.
© OpenLoaf, AGPL-3.0. 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 apps/server/src/ai/builtin-skills/canvas-ops/en of OpenLoaf/OpenLoaf.
Open the folder on GitHubat commit f7eccf6
Compare with similar skills
Canvas Ops Skill 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Canvas Ops Skill this skillOpenLoaf/OpenLoaf | 108 | — | ~1.4k | Automated safety check: Pass | AGPL-3.0 | |
| Generate Imageynulihao/AgentSkillOS | 617 | 10 repos | ~1.7k | Automated safety check: Notes | None | |
| SN Motion HTMLOpenSenseNova/SenseNova-Skills | 5.7k | — | ~2.2k | Automated safety check: Notes | MIT | |
| Guizang Material Illustrationop7418/guizang-material-illustration | 1.2k | — | ~1.6k | Automated safety check: Pass | None | |
| Imagensanjay3290/ai-skills | 431 | 6 repos | ~657 | Automated safety check: Pass | Apache-2.0 | |
| Nano Bananakkoppenhaver/cc-nano-banana | 378 | 1 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
SN Motion HTML
OpenSenseNova/SenseNova-Skills
Builds HTML stories where one continuous camera journey advances with page progress, using researched structure, AI stills, Seedance video clips and browser QA.
Guizang Material Illustration
op7418/guizang-material-illustration
Generate Guizang-style material illustrations, labeled explanatory visuals, material-styled chart illustrations, and data-first editorial images from articles, notes, product concepts, workplace…
Imagen
sanjay3290/ai-skills
Generate images using Google Gemini's image generation capabilities.
Nano Banana
kkoppenhaver/cc-nano-banana
REQUIRED for all image generation requests. An agent skill from kkoppenhaver/cc-nano-banana.
Figure
Muuuun/luxas
Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly).
More from OpenLoaf/OpenLoaf
All 33 skills in this repoAgent Orchestration Skill
OpenLoaf/OpenLoaf
Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…
Browser Ops Skill
OpenLoaf/OpenLoaf
Triggered when the user asks for page-level interaction with a specific webpage: login, form filling, button clicks, pagination scraping, screenshots, downloading page images, handling CAPTCHAs or…
Word Document Read, Write and Convert
OpenLoaf/OpenLoaf
Reads, edits, converts and reviews Word documents through three dedicated tools, covering tracked changes, comments, tables, images and format conversion.
Email Operations
OpenLoaf/OpenLoaf
Handles a real email account through query and mutate tools: check the inbox, read, search, reply, forward, compose and organize, with sending always confirmed first.
macOS Desktop Control
OpenLoaf/OpenLoaf
Guides an agent to operate native macOS apps by surveying an app first, acting through intents, menus or keystrokes, and verifying each step, in OpenLoaf Desktop only.
PDF Skill
OpenLoaf/OpenLoaf
All-in-one PDF read / write / convert / OCR. An agent skill from OpenLoaf/OpenLoaf.
Related
Categories
Questions about Canvas Ops Skill
What does Canvas Ops Skill do?
Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership. Canvas Ops Skill is an agent skill from OpenLoaf/OpenLoaf. Triggered when the user wants lifecycle management of OpenLoaf canvases / whiteboards: create, open, filter, duplicate, delete, rename, or change ownership.
When should I use Canvas Ops Skill?
Canvas Ops Skill fits situations like: wants lifecycle management of OpenLoaf canvases / whiteboards: create; change ownership.
How do I install Canvas Ops Skill in Claude Code?
Run `npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/canvas-ops/en in OpenLoaf/OpenLoaf) into .claude/skills/canvas-ops-skill in your project. Claude Code loads it when a task matches its description.
How do I install Canvas Ops Skill in Codex?
Run `npx skills add OpenLoaf/OpenLoaf --skill canvas-ops-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/canvas-ops/en in OpenLoaf/OpenLoaf) into .agents/skills/canvas-ops-skill in your project. Codex loads it when a task matches its description.
Can I use Canvas Ops Skill 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 OpenLoaf/OpenLoaf --skill canvas-ops-skill -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-ops-skill, .gemini/skills/canvas-ops-skill, .github/skills/canvas-ops-skill and .opencode/skills/canvas-ops-skill in your project.
What does Canvas Ops Skill need to run?
SKILL.md names no scripts, command-line tools or credentials: Canvas Ops Skill is instructions for the agent only.
Does Canvas Ops Skill 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 Ops Skill 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 Ops Skill use?
Canvas Ops Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Canvas Ops Skill use?
About 1.4k tokens (SKILL.md is roughly 5.7k 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 Ops Skill?
Skills that share tags, products or a category with Canvas Ops Skill: Generate Image (ynulihao/AgentSkillOS, 617 stars), SN Motion HTML (OpenSenseNova/SenseNova-Skills, 5.7k stars), Guizang Material Illustration (op7418/guizang-material-illustration, 1.2k stars) and Imagen (sanjay3290/ai-skills, 431 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Canvas Ops Skill?
OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 108 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on May 14, 2026.
Source: OpenLoaf/OpenLoaf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.