Pencil To Code

Export .pen design to React/Tailwind code. Does ONE thing well. Input: .pen frame ID or file path Output: React component code + Tailwind config Use when: design-exploration or user needs implementation code from a finalized Pencil design.

This skill appears coherent and limited to converting Pencil (.pen) designs into React + Tailwind output. Before installing: (1) confirm you only give it access to design files you intend to convert (it reads filePath/nodeId and can take screenshots of frames), (2) review generated code for any external image URLs or embedded data (images in designs may point to external hosts), and (3) if provenance matters, consider the unknown source/homepage — although the skill is instruction-only (no install), verify the owner/trust if you plan to use it in automated pipelines. If you need stronger assurance, ask the publisher for a homepage or source repository so you can inspect any implementation that may be added later.

Type: OpenClaw Skill Name: pencil-to-code Version: 0.1.0 The OpenClaw AgentSkills bundle 'pencil-to-code' appears benign. Its purpose is clearly defined as exporting .pen designs to React/Tailwind code, and all instructions in SKILL.md and references/node-mapping.md are directly aligned with this goal. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts designed to manipulate the AI agent into harmful or out-of-scope actions. The use of `filePath` in `mcp__pencil__` calls is inherent to the skill's function and does not indicate malicious intent from this skill, though platform-level input sanitization would be critical for such APIs.