Individual skill

model-prompt-pack

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.

plugins/pm-3d-explorer/skills/model-prompt-pack/SKILL.md

Read pinned source

Source commit f7c90bc09ee05dc25cf257bdb1826f2c2552c2cb

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,540
Repository last updated
Nov 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Model Prompt Pack

Image-to-3D tools can turn a clean reference image into a usable mesh in minutes, but they invent detail: an extra valve, a wrongly placed bone, a plausible part that does not exist. For an explorer that teaches, the geometry can be approximate; the labels cannot be wrong. This skill writes one prompt per object for generating reference images and meshes, and a parts list in which every label is tied to a named trusted source.

## The accuracy rule

1. **Every label needs a named trusted source**: a textbook with edition, a standards body, a peer-reviewed paper, a museum or manufacturer reference, or an educational body's published material. A URL alone is not a source unless it identifies the publisher.
2. **Generated geometry is illustrative, not authoritative.** Every output that shows the model says so, and the viewer displays the statement.
3. **No source, no label.** A part the user cannot source is either dropped or shown as "unlabelled".

## Required Inputs

Ask for these if not provided:
- **Topic and object(s)**: one assembly, or several separate objects
Back to top