chardesk
Skill433 starsChanged 7 days agoMITView on GitHub
Use CharDesk when work belongs on a shared spatial Canvas or Slide scene that humans and agents need to inspect, compose, or edit together.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use CharDesk when the task benefits from spatial organization, visible composition, or a persistent shared scene—when relationships, …
- Distinctive: line 28
Create or style content with materials.
- Distinctive: line 31
Read context, locate text precisely, or edit the current live surface with Canvas tools.
- Distinctive: line 33
Create local artifacts or edit existing files with the CLI.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CharDesk
CharDesk is the shared spatial workspace between humans and agents. It turns generated material, structured findings, and visual composition into a readable Canvas or Slide scene that both sides can inspect and edit. The rendered Cell surface is the working result; user direction and the existing document establish the scene, so stay on the requested target.
Use CharDesk when the task benefits from spatial organization, visible composition, or a persistent shared scene—when relationships, placement, or simultaneous inspection matter and the result should be read as a surface rather than as a one-dimensional file. Use ordinary file or shell tools when the task is only to generate or transform source material; pass an existing artifact into Canvas by reference when it is ready for projection.
Editable Freeform and native Slide pages own rendered Cell content. Canvas writes render input into Cells; Markdown and ANSI are input materials, not retained source documents. Native Slides are created and edited through MCP; do not author a Slide by writing a structured file from the Agent side.
Routing
- Create or style content with materials.
- Generate editable Cell pictures from code or generator output with procedural art.
- Read context, locate text precisely, or edit the current live surface with Canvas tools.
- Create local artifacts or edit existing files with the CLI.
- Manage native Slide pages through the MCP lifecycle in Slides.
- Discover or repair tool access with connections.
Stay on the requested target. New local documents default to one Freeform
.chardesk file. Do not create Blackboard packages or substitute a new Canvas
for a requested edit.
Delivery
Perform available Agent actions. Hand off the result and only permission or restart actions that require the human.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

