id concept render

Industrial design AI renders often fail because they lack structural logic, or they lean on vague descriptors like "premium" that produce generic results. This skill enforces a professional ID workflow to generate concept renders that are both aesthetically high-end and structurally plausible. It moves beyond simple prompting by using a multi-step deconstruction of form language, CMF (Color, Material, Finish), and manufacturing constraints.

What it does

• Brief deconstruction: Converts vague ideas into structured technical requirements including usage mode, target cost, and forbidden elements.
• Aesthetic anchoring: Map products to specific form languages like soft minimalism or neo-futurism instead of using empty adjectives.
• Layered prompting: Constructs image prompts using a six-layer framework covering subject, proportion, CMF, and lighting.
• Identity-based deliverables: Tailors output sets for specific roles, such as three-view technical sheets for engineers or lifestyle scenes for e-commerce.
• Systematic iteration: Uses a scoring rubric to evaluate renders for silhouette memory, CMF credibility, and brief fidelity.

How it works

1. Intake: The agent runs a progressive interview to define the product category, user, and key mechanical structures.
2. Confirmation: A mandatory "gate" summarizes the understanding for user approval before any image generation occurs.
3. Drafting: The agent selects a category-specific prompt skeleton and anchors it to design exemplars.
4. Refinement: After generation, the agent identifies the lowest-scoring dimension and targets that specific prompt layer for iteration.

Frameworks & tools

This skill works with the image_generation tool. It references a specialized library of form languages, CMF presets, and DFM (Design for Manufacturing) constraints.

Why this beats prompting it yourself

Standard prompts often produce "hallucinated" details that are impossible to manufacture or buttons that make no ergonomic sense. This skill forces the AI to respect industrial design principles, ensuring the generated concept looks like a real product designed for a specific market tier.

Use cases

• Generating investor-ready hero shots for hardware startup pitches.
• Creating e-commerce listing images with consistent CMF across different angles.
• Scaffolding three-view orthographic renders for mechanical engineering evaluation.
• Exploring divergent form factors during the early concept phase of a design project.

Known limitations

The quality is dependent on the connected image generation model's ability to follow complex spatial instructions. It focuses on external aesthetics and cannot generate internal mechanical internals or CAD-ready files.