Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →collabs-inc/collaborator-canvas
Control Collaborator's spatial canvas from the terminal using the `collab-canvas` CLI.
Passed 22 of 22 test cases with the skill, and 4 of 22 without it.
and 24 more in the full report
18 fixed4 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have an image file ./diagram.svg and want to add it to the canvas layout. Does the CLI require specifying the explicit type flag when a supported image extension is present? Provide the creation command.
| Checked | Without skill | With skill |
|---|---|---|
| Uses collab-canvas tile create image --file ./diagram.svg. | Missed | Passed |
The instructions your model reads when the skill loads.
Control Collaborator's spatial canvas from the terminal using the collab-canvas CLI.
The canvas is a pannable, zoomable surface where tiles display terminals, files, images, and graphs.
All positions and sizes use grid units. One grid unit = 20 pixels. Origin (0,0) is the top-left corner. X increases rightward, Y increases downward.
| Type | Use for | Default size (w x h) |
|---|---|---|
term | Terminal / shell session | 20 x 25 |
note | Markdown files (.md) | 22 x 27 |
code | Source code files | 22 x 27 |
image | Images (.png, .jpg, .gif, .webp) | 14 x 14 |
graph | .graph.json or folder graphs | 30 x 25 |
Type is inferred from the file when --file is used:
.md, .txt -> note.graph.json -> graph.png, .jpg, .gif, .svg, .webp -> imagegraphcodeList all tiles on the canvas. Returns JSON array with id, type, position, size, and file path for each tile.
collab-canvas tile list
Create a new tile on the canvas.
test cases passed, vs 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.