forgecad-image-prompt

Generates builder-honest AI image prompts from ForgeCAD models, build briefs, and design documents.

927|103|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/KoStard/forgecad-public-kit --skill forgecad-image-prompt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: forgecad-image-prompt
Source: https://github.com/KoStard/forgecad-public-kit/tree/main/skills/forgecad-image-prompt
Command: npx skills add https://github.com/KoStard/forgecad-public-kit --skill forgecad-image-prompt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Writing image-generation prompts for mechanical CAD projects often produces fantasy concept art that hides how the artifact is actually built. This Skill turns a concrete ForgeCAD model, build brief, HLD, or LLD into image prompts that preserve subsystem truth, visible mechanisms, materials, and mechanical hierarchy.

Core Features & Use Cases

  • Honest Hero Renders: Produces a primary prompt showing the final artifact as a physically buildable, mechanically honest object with visible part boundaries.
  • Multiple Render Modes: Supports builder-first mechanical views, mild exploded module views, workshop prototype realism, and end-effector close-ups, each with signature phrasing.
  • Structured Prompt Skeleton: Enforces a fixed block order (identity, mechanism truth, materials, pose, shot/lighting, negatives) plus a reusable negatives list banning fake consumer shells, hidden mechanics, and CAD-drawing pretense.
  • Use Case: You have a .forge.js robot hand model and need marketing-ready renders. The Skill reads the model, identifies subassemblies like the wrist, gripper, belts, and pulleys, and outputs a hero render prompt plus optional support prompts.

Quick Start

Use the forgecad-image-prompt skill to turn my robot-hand .forge.js model into an honest hero render prompt that shows the gripper mechanism and visible part boundaries.

Frequently Asked Questions about forgecad-image-prompt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write image prompts for a CAD model that look buildable?

Describe the artifact identity and scale first, then state major subassemblies and mechanism truth, materials and colors, pose, and camera setup. End with negatives banning fake sleek shells, hidden mechanics, and sci-fi styling so the render stays mechanically honest.

What input does this Skill need before generating image prompts?

It needs an artifact concrete enough to visualize: a specific .forge.js model, build brief, HLD, or LLD. Vague briefs should go through a design-spec step first, since the Skill reads minimum context like the entry model file and one key helper.

Can I generate exploded views of my ForgeCAD assembly?

Yes, the mild exploded mode separates major modules with small clean gaps to teach assembly logic, avoiding per-screw chaos. The CAD model itself stays the complete assembled product; the exploded view is image-only.

When should I not use image prompt generation for a design?

Avoid it when the brief is still vague or the geometry is undecided, since the Skill refuses to invent internals and stays honest only at the subsystem level. Finalize the design spec first so mechanism truth can be captured accurately.

What negative prompts prevent unrealistic mechanical renders?

The fixed negatives list bans fake sleek consumer shells, hidden mechanics, over-smoothed geometry, sci-fi styling, CAD-drawing or blueprint pretense, unrequested cutaways, and any text, labels, or humans in the render.