What do I need to use Model Prompt Pack?

Topic and object(s); Level of detail; Trusted sources available; The 3D tool; Style.

Is Model Prompt Pack free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Model Prompt Pack

Q: How do I know the Model Prompt Pack output is good?

The skill verifies itself against its own quality checks: There is exactly one prompt card per object or part to be generated; Every label in the parts list names a trusted source with publisher and title; No label appears without a source; unsourced parts are dropped or marked unlabelled; Mesh names in the parts list match the names the prompt cards assign.

🔵 Stable🕐 updated 2026-10-04 ✅ 5/5 🔷 SkillSpec L3 pm-3d-explorer

Use when asked to write prompts for image-to-3D or text-to-3D tools, generate 3D models of a topic's parts, plan the assets for a 3D explorer, or build a labelled parts list with sources. Produces prompts for image-to-3D tools, one per object, plus a parts list for labelling in which every label names a trusted source, and states that generated geometry is illustrative, not authoritative. Second step of explorer-pipeline.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Write image-to-3D prompts for the parts of the human heart, with a sourced parts list.”“Plan the 3D assets for a jet engine explorer.”“Give me a prompt per part for generating a plant cell in 3D.”“I need labelled 3D models for a volcano cross-section. Sources must be cited.”

What to give it

▸Topic and object(s) — one assembly, or several separate objects

▸Level of detail — which parts a learner must identify, from the interface brief if there is one

▸Trusted sources available — to the user, or the curriculum or standard to follow

▸The 3D tool — , if chosen (for example an image-to-3D service, or an open model such as TRELLIS or Hunyuan3D), and any polygon or file-size limits

▸Style — realistic, stylised or diagrammatic

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓There is exactly one prompt card per object or part to be generated

✓Every label in the parts list names a trusted source with publisher and title

✓No label appears without a source; unsourced parts are dropped or marked unlabelled

✓Mesh names in the parts list match the names the prompt cards assign

✓Every prompt card includes a fit check against a named source figure

✓The illustrative statement is included and names the source used for labels

✓Export notes state scale, origin and a file-size target

⚠️ What it refuses to do

**Trusting the mesh.** Generators add plausible detail; check each part against the source figure.

**Wikipedia as the only source.** Use it to find the underlying reference, then cite that.

**Prompting for the labelled diagram.** Text in generated images is unreliable and copies textbook layouts; generate clean objects and label in the viewer.

**One giant mesh.** Without separate parts there is nothing to click or explode.

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="model-prompt-pack"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Model Prompt Pack is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog