PM Toolkit - Excalidraw - "Messy Thoughts" to "Visual Spec" in 30 seconds.

Visualizes Product Manager thoughts (Why, What, How, User Journey) into an editable Excalidraw diagram. Use when the user asks to "visualize specs", "create a PM diagram", or "map out product thoughts".

This skill appears to do what it says: it takes a JSON spec and produces an .excalidraw file locally. Before installing/using it: (1) verify you have Python 3 available (the script runs locally); (2) inspect scripts/layout_diagram.py (it is included) if you want to be certain it contains only expected local file operations — there are no network calls or secret accesses; (3) check the SKILL.md command path (skills/pm-visualizer/scripts/... vs scripts/...) and adjust the invocation to match where the script actually lives; (4) run the script in a directory where writing files is acceptable (it will create output files and you are asked to create output directories); and (5) if you allow autonomous agent invocation, be aware the agent could run the script and write files on your behalf — this is normal but make sure you trust the skill source. Overall the package is coherent and proportional to its stated purpose.

Type: OpenClaw Skill Name: thought-to-excalidraw Version: 1.0.0 The skill is designed to visualize product manager thoughts into an Excalidraw diagram. The `SKILL.md` instructions guide the agent to parse user input, create a temporary JSON file, execute a local Python script (`scripts/layout_diagram.py`) to generate an `.excalidraw` file in a user-owned directory (`~/Downloads/Documents/PM_Visuals/`), and then clean up. The Python script itself only performs local file I/O, reading the temporary JSON and writing the Excalidraw output. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts aimed at harmful actions. All operations are aligned with the stated purpose.