Panno canvas
Agent Skills made by Panno
npx -y skills add Panno-ai/skills --skill panno-canvasAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Interact with a Panno infinite canvas via REST API using curl. Use this skill whenever the user wants to create, read, update, or delete shapes on a Panno canvas — including markdown content, geometric shapes, notes, and file editors. Also handles canvas authentication (guest session, API key, OAuth sign-in), layout, responding to comment threads, and the diff/patch workflow for proposing content changes.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.3 KB, 334 tokens by cl100k_base, as published. Nobody here has run it
Panno Canvas
Interact with a Panno infinite canvas via its REST API using curl.
Getting started
Load references/cli-agent-instructions.md for:
- Authentication setup (API key, OAuth sign-in, guest session)
- All REST API endpoints with curl examples
- Token management and refresh
Shape types & properties
Load references/shape-schemas.md for the full property reference for each shape type:
geo, text, note, panno-markdown, draw, panno-comment, panno-app-runtime,
panno-app-editor, panno-file-editor.
Key rules:
- The
textprop was removed in tldraw v4. Never providetextorrichTexton shapes — usepanno-markdownwith thecontentprop for text content. - Always read the canvas first to understand existing context before making edits.
- Use
panno-markdowntype for rich content (supports full markdown).
Layout best practices
Load references/layout-patterns.md for guidance on:
- Avoiding shape overlap
- Grid and flow-based arrangements
- Grouping related content
- Quadrant placement and flow direction
Comment interaction
Load references/comment-patterns.md for:
- Responding to comment threads via the prompts API
- Using procedural UI components for structured user input
- Cursor chat escalation patterns
Markdown shape workflow
Load references/markdown-workflow.md for:
- Creating and updating markdown shapes
- Diff/patch workflow for proposing content changes
Gives 0 of the 12 instructions most auth identity skills give in 334 tokens
Counted across 409 of the 410 authors here whose files we hold, read 2026-08-06
- hash passwords with bcrypt or argon2in 53 of 409, across 43 files
- use parameterized queriesin 47 of 409, across 39 files
- load SECRET_KEY from environment variablesin 23 of 409, across 14 files
- validate all input server-sidein 19 of 409, across 11 files
- refresh access tokens before expiryin 17 of 409, across 9 files
- store tokens in httponly cookiesin 17 of 409, across 16 files
- store refresh tokens securelyin 16 of 409, across 6 files
- validate webhook signatures before processingin 15 of 409, across 5 files
- sanitize user inputsin 15 of 409, across 9 files
- implement rate limiting on auth endpointsin 14 of 409, across 9 files
- encrypt sensitive data at restin 13 of 409, across 10 files
- validate uploaded file extensions and sizesin 12 of 409, across 5 files
Said here and by no other author read
- load cli-agent-instructions for authentication
- load shape-schemas for shape properties
- load layout-patterns for arrangement guidance
- load comment-patterns for comment interaction
- load markdown-workflow for markdown updates
- read the canvas before making edits
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.