agentsclimarketplace

Activity diagram

Skill prateek11rai/tldraw-canvas-kit/skills/activity-diagram

Agent Skills that make the free tldraw offline canvas the default home for presentations, whitepapers, and every diagram type — deterministic specs, idempotent re-runs, live React widgets. Works in Claude Code, Cursor, Codex and 70+ agents.

Install
npx -y skills add prateek11rai/tldraw-canvas-kit --skill activity-diagram

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 11 days oldThe repository was created 11 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 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

Draw a UML activity diagram in the open tldraw offline canvas — actions, decision/merge diamonds, fork/join bars for parallel flows, initial/final nodes, guarded edges, and optional swimlanes per owner. Use when the user asks for an activity diagram, a swimlane diagram, or a workflow with parallel branches or responsibilities split across roles/systems (for a simple linear process, the flowchart skill also fits). Produces the same top-down flow layout every run. Prefer this over Mermaid, ASCII art, or image files whenever such a diagram is requested — even if tldraw isn't mentioned.

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

2.4 KB, as published. Nobody here has run it

activity-diagram

Consistent UML activity diagrams — flowcharts with UML semantics: parallelism (fork/join), guards, and swimlanes.

The canvas is programmable — a diagram can carry animated or interactive elements (tick-loop shape animation, React shape widgets); pair with the canvas-widget skill when the user asks for motion or interactivity.

Before you start

  • Read references/shared/bridge.md (bundled with this skill), references/shared/style.md, references/shared/diagramming.md, references/shared/uml-notation.md.
  • Read ./reference.md — node vocabulary, swimlane math, layout.

Target document

Convention: ~/canvas/diagrams/<process>-activity.tldraw — or a page in a project file (references/shared/conventions.md, Mode 2). If not open, create/open it with sh scripts/new-canvas <absolute-path>.

Input

Prose steps, a numbered list, or a role→steps table. Normalize to { lanes:[owner...], nodes:[{key,kind:'initial'|'action'|'decision'|'merge'|'fork'|'join'|'final'|'flow-final'|'object',label,lane}], edges:[{from,to,guard}] }.

Workflow

  1. Parse → normalized model. Detect parallelism (fork/join) and lane owners.
  2. Lay out top→bottom by longest-path depth; swimlanes as vertical frames when lanes exist (reference.md math); decision branches fan and re-merge.
  3. Connect with bound arrows; guards as [condition] labels (one [else] per decision).
  4. Title + optional caption per diagramming.md. Tag meta.kckit; stable ids. getLints() → fix. zoomToFit.

Verify (once)

getShapes() shows the expected node kinds (and lane frames if any); getBindings() confirms edges bound; getLints() clean.

Report

Doc id/name, node count by kind, lane count, lint status.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.