ApertureOscillation
3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis — to surface design tensions,…
Read, create, and edit tldraw .tldr canvas files deterministically — sketch hand-drawn-register diagrams (boxes, arrows, sticky notes, frames, text) directly into a canvas file the user opens in any tldraw surface, and read a rough canvas back as structured data to organize it.
$ npx -y skills add danielmiessler/personal_ai_infrastructure --skill Tldraw --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/TldrawContext preview
The summary Claude sees to decide when to auto-load this skill.
Read, create, and edit tldraw .tldr canvas files deterministically — sketch hand-drawn-register diagrams (boxes, arrows, sticky notes, frames, text) directly into a canvas file the user opens in any tldraw surface, and read a rough canvas back as structured data to organize it.
name: Tldraw version: 1.0.1 description: Read, create, and edit tldraw .tldr canvas files deterministically — sketch hand-drawn-register diagrams (boxes, arrows, sticky notes, frames, text) directly into a canvas file the user opens in any tldraw surface, and read a rough canvas back as structured data to organize it. USE WHEN tldraw, .tldr file, whiteboard, canvas, sketch a diagram, hand-drawn diagram, draw this on a canvas, put this on the whiteboard, structure my canvas, organize my whiteboard, read my canvas, cluster my sticky notes. NOT FOR polished static images, infographics, or mermaid diagrams (use Art), web UI design (use Webdesign), programmatic video (use Remotion).
Deterministic read/write for tldraw canvases. The `.tldr` format is plain JSON (`{tldrawFileFormatVersion: 1, schema, records}`); `Tools/Tldr.ts` writes records that pass tldraw's own validator, so generated files open cleanly in the tldraw web editor, the VS Code tldraw extension, or the desktop app. Two directions: model → canvas (sketch diagrams) and canvas → model (read and structure a human's rough thinking).
**Before executing, check for user customizations at:** `~/.claude/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/Tldraw/`
If this directory exists, load and apply any PREFERENCES.md found there (default canvas directory, preferred colors/register, default open surface). If not, proceed with defaults.
**When executing a workflow, do BOTH:**
1. **Send voice notification**:
curl -s -X POST http://localhost:31337/notify \
-H "Content-Type: application/json" \
-d '{"message": "Running WORKFLOWNAME in Tldraw"}' \
> /dev/null 2>&1 &2. **Output text notification**:
Running **WorkflowName** in **Tldraw**...
| Workflow | Trigger | File | |----------|---------|------| | **SketchDiagram** | "sketch a diagram", "draw this on a canvas", "tldraw diagram" | `Workflows/SketchDiagram.md` | | **StructureCanvas** | "structure my canvas", "organize my whiteboard", "read my canvas" | `Workflows/StructureCanvas.md` |
**Example 1: Diagram for a post**
User: "Sketch the three-stage pipeline as a hand-drawn diagram" → Invokes SketchDiagram workflow → Writes spec JSON, runs Tldr.ts create + add, validates → Returns the .tldr path and how to open it; user nudges shapes and exports
**Example 2: Organize an ideation canvas**
User: "I dumped ideas on my canvas — structure them" → Invokes StructureCanvas workflow → Tldr.ts inspect --json reads every shape's text and position → Clusters related items, adds frames + arrows, moves shapes into groups → User reopens the same file and sees the organized version
After completing any workflow, append a single JSONL entry:
echo '{"ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","skill":"Tldraw","workflow":"WORKFLOW_USED","input":"8_WORD_SUMMARY","status":"ok|error","duration_s":SECONDS}' >> ~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl⛰️ The Life Operating System — an intent engineering platform that moves you from your current state to your ideal state, in life and work.
Repo: danielmiessler/personal_ai_infrastructure
3-pass scope oscillation that holds a question constant while shifting zoom — narrow/tactical, wide/strategic, then synthesis — to surface design tensions,…
Curated aphorism collection with CRUD — content-based matching, themed search, thinker research, DB maintenance. Quotes organized by author/theme/context/usage…
Scrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls…
Search and retrieve arXiv academic papers by topic, category, or paper ID — with AlphaXiv-enriched AI-generated overviews. Uses arXiv Atom API across…
Static visual content across 20+ formats — diagrams, mermaid, infographics, D3 dashboards, comics, icons, wallpaper — via Nano Banana Pro (default), Nano…
AI audio editing pipeline: Whisper word-level transcription → Claude segment classification (KEEP/CUT_FILLER/CUT_FALSE_START/CUT_STUTTER/CUT_DEAD_AIR) → ffmpeg…