Skip to content
Back to skills

Analyze Model

ASecurity

Produces analysis.json (bounding box, volume, body count, watertightness) for one model file in a work dir by running the bundled mesh script. Use as the first intake stage on any stl, 3mf or obj. Not for rendering, quoting or judging printability; the slicer decides that.

  • 6 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 16, 2026
ai-agentspythonbashapi

Works with

  • api

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 16, 2026

npx -y skills add 3DAPI-Inc/dapilot --skill analyze-model --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Analyze Model?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Analyze Model
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/3dapi-inc-analyze-model/badge)](https://www.skillsdirectory.com/skills/3dapi-inc-analyze-model)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: analyze-model
description: Produces analysis.json (bounding box, volume, body count, watertightness) for one model file in a work dir by running the bundled mesh script. Use as the first intake stage on any stl, 3mf or obj. Not for rendering, quoting or judging printability; the slicer decides that.
allowed-tools: Read, Bash, Write
---

# analyze-model

## When
A brief with `stage: analyze`. The work dir holds `source.<ext>` and no
`analysis.json`.

## Inputs
- `source.stl` | `source.3mf` | `source.obj`

## Procedure
1. If `analysis.json` exists, print a `cached:true` result and stop.
2. Run
   `$PY ${CLAUDE_PLUGIN_ROOT}/scripts/analyze_mesh.py $WORKDIR/source.<ext> > $WORKDIR/analysis.json`.
   Non-zero exit: delete the empty `analysis.json`, return `ok:false` with
   the script's `reason`, stop. Never open the model file yourself.
3. Read `analysis.json`. The one judgement here: if `bodies` > 1 and
   `largest_body_frac` < 0.9, this is an assembly. Put "multi-part, N
   bodies" in the summary so later stages expect several pieces.
4. Summary line: bodies, watertight bodies, volume in cm3 (mm3 / 1000, or
   "volume unknown, open mesh" when null), bbox in mm rounded to integers.
5. Append the log paragraph, remove `.lock`, print the result line.

## Outputs
- `analysis.json`, exactly what the script printed. Fields: `triangles`,
  `bbox_mm`, `volume_mm3`, `area_mm2`, `watertight`, `winding_consistent`,
  `bodies`, `watertight_bodies`, `largest_body_frac`.

## Gate
Auto. No network, no spend.

## Failure
- Unsupported extension: `ok:false`, reason `unsupported: <ext>`.
- Script failure: pass its reason through unchanged.
- Missing Python deps (trimesh, scipy, networkx): the reason will say so;
  pass it through, it is an environment problem for a person.

## Do not
- Do not estimate anything the script did not print.
- Do not decide printability. That is `quote-model`, via the slicer.
- Do not read `source.*` into your context. It is triangle soup.

`$PY` is `${DAPILOT_PYTHON:-python3}`; it must have trimesh, scipy, networkx.

Files in this skill

  • SKILL.md2 KB
  • eval/cases.md1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.