cad-build
Skill2 starsChanged 26 days agoMITView on GitHub
Use when a part must be built or regenerated in code-CAD (manifold3d/trimesh in the project venv, or Fusion 360) with its source saved beside the STL, geometric checks and a render. Runs the cad-engineer in a fresh context and writes to the project folder named in the arguments.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- agent-reviewSkill
- ai-mesh-cleanSkill
- couponSkill
- curriculumSkill
- dfm-reviewSkill
- fileSkill
- gddSkill
- ip-checkSkill
- led-budgetSkill
- lesson-learnedSkill
- makerworld-publishSkill
- material-pickSkill
- mcp-new-toolSkill
- ortho-sheetSkill
- 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, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
If a reference STL or source is named, measure or read it first with .venv\Scripts\python.exe (trimesh).
- Very specific: line 18
Write report.md; return the folder path and check summary.
≈ “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
Input: $ARGUMENTS, as <output folder> | <spec>. Output: <folder>\<part>.py, <part>.stl, render.png, report.md (measured vs regenerated, checks).
When to use
New parts, regenerations from a spec, or fixes to a part whose source exists (read the source first; never write into a folder listed in protected_roots in config\paths.yaml). Not for organic shapes (/sculpt).
Steps
- If a reference STL or source is named, measure or read it first with
.venv\Scripts\python.exe(trimesh). Parameters at the top of the script, one function per feature. - Export the STL. Checks: watertight,
is_volume, bounds and volume against the reference, distinct generated points, interference / swing / slide-in where mating parts are given. - Render the real STL with Blender headless (
<blender_exe> -b -P <script> -- ...,blender_exefromconfig\paths.yaml; if it is empty, say the render was not done). - Write
report.md; return the folder path and check summary.
Common rationalizations
| Rationalization | Reality |
| "I'll save the script later." | A part whose script was never saved cannot be regenerated or fixed. Script first, STL second. |
| "Nearest vertex is close enough." | Snapping to the nearest vertex can merge distinct features into pairs. Use the nearest point on the edge, then a uniqueness check. |
Red flags
- An STL without a
.pybeside it. - A boolean result that is not
is_volume.
Verification
.py,.stl,render.png,report.mdin the folder.- Checks listed with numbers; any failed check named.
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.

