cad-viewer
Skill1 starsChanged 3 months agoMITView on GitHub
Start CAD Viewer and return review links for explicit CAD, implicit CAD, and robot-description files. Use when visually reviewing `.step`, `.stp`, `.implicit.js`, `.implicit.mjs`, `.glb`, `.stl`, `.3mf`, `.dxf`, `.urdf`, `.srdf`, or `.sdf` files, especially when handed off from CAD, implicit-cad, URDF, SRDF, or SDF generation skills.
2 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- tlinedeep/claude-skillsedited, first seen Jun 3, 2026
- Glow-maker/skillstheir own version, first seen Apr 27, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- tlinedeep/claude-skills★ 025% same
Wrote their own version · 1
- Glow-maker/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- advertising-imagery-agentSkill
- agent-watchSkill
- aria-intelligenceSkill
- bambu-labsSkill
- cadSkill
- dataset-engineeringSkill
- design-business-agentSkill
- design-loopSkill
- dxfSkill
- elite-engineeringSkill
- emil-deign-skillSkill
- env-harnessSkill
- gcodeSkill
- human-writingSkill
- implicit-cadSkill
- inference-engineeringSkill
- kernel-engineeringSkill
- lamp-method-first-principles-thinkingSkill
- marketing-and-advertising-agentSkill
- model-evalSkill
- new-project-architectureSkill
- opportunity-hunterSkill
- rlmSkill
- rlSkill
- sdfSkill
- sendcutsendSkill
- sftSkill
- srdfSkill
- step-partsSkill
- synthesys-bug-triageSkill
- taste-maxSkill
- urdfSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 5 are distinctive, and 7 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Use the installed local skill files as the runtime source of truth.
- Distinctive: line 15
Use this skill to open existing or newly generated CAD, implicit CAD, robot-description, or DXF files in CAD Viewer and hand back live …
- Very specific: line 20
Start one local CAD Viewer with npm run start.
- Distinctive: line 26
Run from this skill directory:
- Very specific: line 59
If port 3245 is already in use, the launcher exits with an error rather than rolling to another port.
- Very specific: line 64
Add --json to also print a machine-readable result as the last stdout line beginning with { ({"url": ..., "port": ..., "action": "start"}).
- Very specific: line 70
Before returning any link, resolve <directory>/<file> and confirm it exists.
- Very specific: line 79
Start the Viewer once and pick one workspace root for the session.
- Distinctive: line 84
Do not stop an existing Viewer server unless the user asks.
- Distinctive: line 85
If Viewer startup fails, report the failure and continue with the owning skill's non-GUI validation or artifacts.
- Very specific: line 89
Read references/viewer-features.md when you need supported file types, Viewer controls, or file-specific feature details.
- Very specific: line 90
Read references/moveit2-server.md only when the user specifically needs optional SRDF MoveIt2 IK or path-planning controls.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
CAD Viewer
Provenance: maintained in earthtojake/text-to-cad. Use the installed local skill files as the runtime source of truth; the repository link is only for provenance and release review. If the user asks to modify, debug, or iterate on CAD Viewer source itself, clone that repository and work there — this installed skill runtime runs the Viewer, it is not where you edit it.
Use this skill to open existing or newly generated CAD, implicit CAD, robot-description, or DXF files in CAD Viewer and hand back live review links. The expected input is one or more explicit file paths.
Start Viewer
Start one local CAD Viewer with npm run start. It serves the prebuilt Viewer
bundle plus the CAD API on a single fixed port (3245). It is NOT started
against a directory — a URL names the directory, so one Viewer serves any folder.
The default port
3245is0xCAD— "CAD" in hexadecimal.
Run from this skill directory:
npm --prefix scripts/viewer run start -- --host 127.0.0.1URL shape
A Viewer URL's path is the absolute directory, exactly as in a file:// URL,
and file= selects one artifact inside it:
http://127.0.0.1:3245/absolute/project/models?file=mechanisms/lift_table.step.pyAlways build the path from an absolute directory. The Viewer runs from an
arbitrary working directory — usually wherever the skill happens to be installed,
not the model directory — so a relative path resolves against the wrong place.
The file= value is relative to that directory.
On Windows the drive goes in the path, after the URL's leading slash, with
forward slashes: D:\project\models is http://127.0.0.1:3245/D:/project/models.
The launcher prints this form already; build it the same way by hand.
The path is the workspace, not the file's folder. The Viewer scans it
recursively, so the file browser lists every model beneath it and the user can
switch files without a new link. Pick the directory the user thinks of as their
model workspace — typically the project's models/ directory, or the nearest
common parent of the files you were asked to review — and put the rest of the
path in file=. Naming the artifact's own deep folder
(.../models/step/mechanisms?file=lift_table.step.py) opens the same model but hides
the rest of the project, which is almost never what the user wants.
If port 3245 is already in use, the launcher exits with an error rather than
rolling to another port; rerun with an explicit free port, --port <n>, and use
the URL it prints. In sandboxed agent environments, local binding failures such
as EPERM/EACCES can be expected; rerun with the needed permission/escalation.
Add --json to also print a machine-readable result as the last stdout line
beginning with { ({"url": ..., "port": ..., "action": "start"}). The printed
URL points at the launch directory; replace its path to review any other folder.
Links
- Before returning any link, resolve
<directory>/<file>and confirm it exists. For a generated model pass the generator source (<name>.step.py) — that is what the catalog itself lists, the backend resolves it directly and builds the render artifacts on demand, and no.stepfile needs to exist. It is also the only form that carries aparamssidecar, because a same-stem<name>.step.pyshadows<name>.stepanyway. For an imported STEP with no generator, pass the.step/.stpitself. If the resolved path is missing, do not return the link; report the problem and point to the correct path. - Return one Viewer URL per requested file.
- Start the Viewer once and pick one workspace root for the session. Every link
is that same absolute root plus
?file=<path relative to it>, so all of them share one browsable catalog. Only use a second root for an artifact that lives outside the first. - For directory-only review links, return the directory URL without
?file=. - Do not stop an existing Viewer server unless the user asks.
- If Viewer startup fails, report the failure and continue with the owning skill's non-GUI validation or artifacts.
References
- Read
references/viewer-features.mdwhen you need supported file types, Viewer controls, or file-specific feature details. - Read
references/moveit2-server.mdonly when the user specifically needs optional SRDF MoveIt2 IK or path-planning controls.
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.

