ortho-sheet
Skill2 starsChanged 26 days agoMITView on GitHub
Use when a model needs a dimensioned orthographic reference sheet or turnaround (front/back/left/right/top/bottom) that can be loaded as Blender Image Empties or handed to a factory. Runs the surfacing-artist in a fresh context, renders headless at a stated mm-per-pixel scale and measures the deviation.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-reviewSkill
- ai-mesh-cleanSkill
- cad-buildSkill
- couponSkill
- curriculumSkill
- dfm-reviewSkill
- fileSkill
- gddSkill
- ip-checkSkill
- led-budgetSkill
- lesson-learnedSkill
- makerworld-publishSkill
- material-pickSkill
- mcp-new-toolSkill
- pi-power-budgetSkill
- preprint-checkSkill
- promo-planSkill
- qa-gateSkill
- render-criticSkill
- research-oneSkill
- research-topicSkill
- retopoSkill
- safety-sheetSkill
- sculptSkill
- slicer-questionSkill
- style-bibleSkill
- tech-packSkill
- unit-costSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Verify scale: read the bar's pixel length from the rendered PNG, convert with the stated mm-per-pixel, report deviation %.
- Distinctive: line 35
No dimension bar in frame, or its measured deviation not reported.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Overview
Orthographic sheet for: $ARGUMENTS
Output on disk, in the project folder you name (see templates\project\), or work\ortho\<model-stem>\ if none is given: <model-stem>_ortho.png, the per-view PNGs, ortho.py beside them, and ortho.md (scale, views, bar deviation, Image Empty load notes).
Blender comes from config\paths.yaml (blender_exe) through tools\mm_config.py. If it is empty, stop and say Blender is not configured.
When to use
A model exists (STL/OBJ/GLB/.blend) and someone needs true proportions: a modeler, a factory, a tech pack, a CAD rebuild. Not for a look-dev or hero render (surfacing-artist render output), not when the model must first be made watertight (/ai-mesh-clean).
Steps
- Measure the model with
.venv\Scripts\python.exeandtrimesh: bounding box in mm (NEEDS MAKER if the unit is unknown), centroid, face count. Folders listed inprotected_rootsinconfig\paths.yamlare read only. - Write
ortho.pyfor<blender_exe> --background --python ortho.py -- <model> <views> <width px> <out dir>: import, centre, one orthographic camera per view withortho_scale= largest bbox extent for that view + 10 % margin, flat neutral material and even lighting, a dimension bar object of known length (for example 50 mm) in frame, transparent or white background. Compute and print mm-per-pixel =ortho_scale / width px. - Render each view; composite the sheet (Blender compositor or a second headless pass) with view labels, the mm-per-pixel value and the bar length printed on the sheet.
- Verify scale: read the bar's pixel length from the rendered PNG, convert with the stated mm-per-pixel, report deviation %. The bar is 2 % or less (house target).
- Open the sheet PNG with the Read tool. Write
ortho.md: scale, views, bar deviation, and how to load each view as an Image Empty with matching size per https://docs.blender.org/manual/en/latest/modeling/empties.html. - Return paths, the deviation %, and one line describing what the sheet shows.
Common rationalizations
| Rationalization | Reality |
| "A far perspective camera is close enough." | Perspective foreshortens; a sheet without an orthographic camera and a stated mm-per-pixel cannot be loaded at 2 % deviation or less. |
| "The scale is right by construction, skip the bar." | Measure the bar in pixels. A scale you have not measured is a claim, not a fact. |
| "The model is roughly 120 mm." | Read the bbox from trimesh and state the unit. Eyeballed counts and sizes are how numbers go wrong. |
| "Render ran, sheet done." | Open the PNG. A preview you did not look at has misled builds before. |
Red flags (stop and fix)
- No dimension bar in frame, or its measured deviation not reported.
- mm-per-pixel missing from the sheet or
ortho.md. - Output written into a protected root.
- Sheet PNG never opened.
Verification
ortho.mdstates bbox mm, mm-per-pixel, views rendered and bar deviation % (2 % or less, or the failure stated).- Sheet PNG and per-view PNGs exist beside
ortho.py; the script was run this session. - Sheet PNG opened and described in one line.
- Image Empty load notes present with the manual URL.
- Paths returned.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

