← Back to Skills Marketplace
1237
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install pencil-renderer
Description
Render DNA codes to Pencil .pen frames. Does ONE thing well.
Input: DNA code + component type (hero, card, form, etc.)
Output: .pen frame ID + screenshot
Use when: design-exploration or other orchestrators need to render
visual proposals using Pencil MCP backend.
Usage Guidance
This skill appears to do exactly what it says: translate DNA codes into Pencil frames using the Pencil MCP backend. Before installing, confirm that your platform's MCP integration is trusted and that any credentials for Pencil MCP are managed by the platform (not this skill). Note that MCP-side operations may include AI image generation (G(..., "ai", ...)) and creating/storing .pen files/screenshots — consider whether those outputs may be visible to other users or logs in your environment. If you rely on sensitive or proprietary DNA inputs, ensure the MCP service's data handling/privacy policies meet your requirements. No environment variables or local installs are required by the skill itself.
Capability Analysis
Type: OpenClaw Skill
Name: pencil-renderer
Version: 0.1.2
The skill is classified as suspicious due to the `G()` function in `references/batch-design-patterns.md` and `references/dna-to-pencil.md`. This function allows the agent to generate or retrieve images from external AI or stock services using user-provided prompts and keywords. While plausibly needed for the skill's stated purpose of rendering visual proposals, this represents a risky capability involving external network calls and potential for prompt injection against third-party services (e.g., for resource exhaustion, inappropriate content generation, or other abuses), even if no malicious intent is evident in the provided examples. The `SKILL.md` itself does not contain malicious prompt injection against the OpenClaw agent.
Capability Assessment
Purpose & Capability
Name/description match the SKILL.md and reference files: all operations are calls to a Pencil MCP surface (mcp__pencil__*) to open documents, map DNA axes to Pencil properties, run batch design operations, and capture screenshots. Nothing in the package asks for unrelated cloud or system credentials or tools.
Instruction Scope
Runtime instructions are narrowly scoped to Pencil MCP operations (get_editor_state, open_document, get_style_guide, batch_design, get_screenshot) and to deterministic DNA→Pencil mappings from the provided references. The only potentially notable operation is G(..., "ai", ...) which triggers MCP-side image generation — this is consistent with rendering and is called via the MCP API, not by the skill reading arbitrary system files or env vars.
Install Mechanism
Instruction-only skill with no install spec, no external downloads, and no code executed locally — lowest install risk.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. That matches its instructions which call the platform's MCP APIs rather than asking for secrets directly.
Persistence & Privilege
always is false and there is no indication the skill modifies other skills or system settings. The skill can be invoked autonomously (platform default), which is expected for an orchestrator-invoked renderer.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install pencil-renderer - After installation, invoke the skill by name or use
/pencil-renderer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
- Added in-depth reference: dna-to-pencil.md, detailing complete DNA axis to Pencil property mappings.
- Added batch-design-patterns.md, describing standard operation sequences for design execution.
- No changes to workflow or interface; new reference files enhance documentation and implementation clarity.
v0.1.1
## pencil-renderer 0.1.1
- No changes to files detected for this release.
- No updates or modifications were made compared to the previous version.
v0.1.0
Initial release of pencil-renderer.
- Translates aesthetic DNA codes into Pencil .pen frames using MCP backend.
- Accepts DNA code and component type to render standardized component templates (hero, card, form, etc.).
- Returns frame ID and screenshot for visual verification.
- Deterministic mapping from DNA to Pencil properties ensures repeatability.
- Designed to be called by orchestrators, not end users directly.
Metadata
Frequently Asked Questions
What is Pencil Renderer?
Render DNA codes to Pencil .pen frames. Does ONE thing well. Input: DNA code + component type (hero, card, form, etc.) Output: .pen frame ID + screenshot Use when: design-exploration or other orchestrators need to render visual proposals using Pencil MCP backend. It is an AI Agent Skill for Claude Code / OpenClaw, with 1237 downloads so far.
How do I install Pencil Renderer?
Run "/install pencil-renderer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Pencil Renderer free?
Yes, Pencil Renderer is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Pencil Renderer support?
Pencil Renderer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Pencil Renderer?
It is built and maintained by Jcwen (@jcwen); the current version is v0.1.2.
More Skills