OpticalModeler skill

Agent Skill that turns diagrams and photos of optical setups into editable Blender models with real mounts and an evidence trail

  • 138 ★ on the repository
  • Last commit
  • MIT
Skill

Extended access

Why this level

  • Runs Blender and scripts and writes scene files and renders into the project
  • Works with your source schematics and lab photographs
All reasons and checks

k-telux/opticalmodeler

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/opticalmodeler

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Runs Blender and scripts and writes scene files and renders into the project
  • Works with your source schematics and lab photographs

This is third-party code. Review the repository files before installing.

What it does

OpticalModeler guides an agent through building an optical layout in Blender. The thorlabs-blender-optical-path skill connects the beam route to real apertures, mounts and supports and keeps evidence of where each element came from. You describe the input, what may change and what to return, and the agent builds the model. The description shows five modes. Design starts from an empty scene and a source-backed topology. Reconstruction takes a diagram or photographs and an explicitly retained baseline. Correction works with an accepted model, frozen originals and declared movable degrees of freedom. Audit reads a finished scene read-only and gives precise findings. Presentation creates a separate copy with camera and light without changing geometry. The rules strictly separate installed, candidate and proposed parts. A fixed upper endpoint stays fixed, an optic moves with its mount and supports and a proposed camera is treated as proposed. The READY_FOR_USER_REVIEW status means the handoff is ready for inspection and does not certify hardware, alignment, optical performance or laser safety. The repository holds six conversation walkthroughs with rejections and corrections.

Who it is for. Physicists and optical lab engineers who need a checkable 3D model of a setup from a paper schematic or photos of a bench.

Good fit when

  • A paper schematic has to become a 3D Blender scene with a beam path
  • Photos of a bench need a model where installed and assumed parts are marked differently
  • An accepted model has to be corrected without moving frozen originals and fixed endpoints
  • Before handoff you need a read-only audit of a finished scene with a findings list
  • A presentation needs a copy with camera and light and unchanged geometry

Not a fit when

  • You need optical performance calculations: the model does not certify alignment, parameters or laser safety
  • The work is outside optics: the skill is built around components like Thorlabs and beam paths
  • You need a model in another 3D package: the output targets Blender
  • You need a quick picture without element provenance rules: the set requires an evidence trail

Example request

Use $thorlabs-blender-optical-path to reconstruct these photos on the accepted baseline, keep fixed upper endpoints and mark installed, candidate and proposed parts

Limitations

  • Blender and an agent that supports Agent Skills are required; the result does not replace checking the installed hardware, alignment, optical parameters and laser safety.
  • The project is independent, not affiliated with or endorsed by Thorlabs; English is the technical source while the Chinese and Japanese versions keep the same rules.
  • The model reflects only the input: when specifications are missing, installed and assumed parts stay separate.
  • The validator checks skill editions, resources, manifests and PNG metadata, and the author advises keeping private laboratory identifiers outside the repository.

How to disable. Delete the thorlabs-blender-optical-path folder from the agent skills directory. Blender files and evidence trails stay in your projects.

FAQ

How do I install OpticalModeler?

Run npx skills add k-telux/OpticalModeler. Manually copy the skills/thorlabs-blender-optical-path folder into the agent skills directory.

What can the skill do: design, reconstruction, audit?

Five modes: design a new layout, reconstruct from a schematic or photos, correct an accepted model, audit a finished scene and prepare a presentation copy.

What does READY_FOR_USER_REVIEW mean?

The handoff is ready for human inspection. The status does not certify hardware, thread preload, alignment, optical performance or laser safety.

Is the project affiliated with Thorlabs?

No, it is an independent community workflow not endorsed by Thorlabs. English is the technical source and the Chinese and Japanese versions keep the rules.

What if a part has no specifications?

The skill marks the part as assumed and does not mix it with an installed one. The example is walked through in conversation B with photos and unknown hardware.

Discussion

No questions or reviews yet.

Skills

A loop skill: the agent generates a target screenshot, builds toward it, and uses a critic subagent to close the gap until they match

SkillExtended access2KRepository stars

A Claude Code workflow that builds a dressed, lit Blender scene from reference images or one paragraph, with graded renders.

WorkflowExtended access369Repository stars

A skill collection guides AI agents through Blender modeling, materials, animation and asset checks using supplied Python scripts.

SkillBroad access1KRepository stars

A skill that guides an agent from a Gaussian splat to a Blender scene on Geometry Nodes and Shader Nodes, checked on views.

SkillExtended access83Repository stars

Agent skill for Blender: builds a procedural node system from a video, image or idea and checks the finished graph.

PluginExtended access95Repository stars

A skill and CLI that let Claude Code or Codex make videos as web pages, with the Studio editor to change the result

SkillExtended access6.4KRepository stars

README in short

The page opens with the promise to design the path and keep the evidence, gives install and a sample agent request. Then it lists five work modes, six conversation walkthroughs with rejection and correction, readiness rules and validator checks, license notes and independence from Thorlabs.

README badge

Original SKILL.md

---
name: thorlabs-blender-optical-path
description: Design, reconstruct from photographs or schematics, correct, audit, and present Blender optical systems using provenance-bound CAD and measured optical and mechanical interfaces. Use for optics-only laboratory models, constrained revisions, stateful instruments, and publication renders with explicit evidence and privacy boundaries.
metadata:
  version: "2.0.0"
---

# OpticalModeler 2.0 — Thorlabs Blender Optical Path

Turn a measurement requirement, schematic, or photographed apparatus into an editable, explainable Blender scene. Deliver the requested model and views with evidence that matches the claim. Manufacturer geometry, installed identity, visual readiness, and physical qualification are separate facts.

## Load the relevant references

- Read [physical-gates.md](references/physical-gates.md) before geometry, CAD placement, or mechanical review.
- Read [evidence-contract.md](references/evidence-contract.md) before declaring any PASS or preparing a release.
- Read [history-derived-rules.md](references/history-derived-rules.md) when revising an existing scene or when old fixes may have regressed.
- Read [project-case-study.md](references/project-case-study.md) for the complete G1/G2 2D-to-3D example.
- Read [fresh-design-and-rendering.md](references/fresh-design-and-rendering.md) when the user requests a new measurement path, uses an old example as a quality reference, excludes electronics, or reports inadequate detail/beam visibility.
- Read [photo-reconstruction-and-revisions.md](references/photo-reconstruction-and-revisions.md) for photographed setups, constrained layout changes, repeated user corrections, or selectable ports/shutters.
- Read [presentation-and-delivery.md](references/presentation-and-delivery.md) for material/light changes, image reuse, interactive opening state, and final delivery.
- Read [publication-privacy.md](references/publication-privacy.md) before publishing laboratory-derived guidance or examples. Keep the private identity map outside the public tree.
- Read [end-to-end-workflow.md](references/end-to-end-workflow.md) before a whole-system build or large forward test. Use its single-run ledger instead of splitting one system into independently authored modules.
- Read [multi-run-qualification.md](references/multi-run-qualification.md) before a Skill release or scale/stress campaign that must compare multiple fresh whole-system runs.

Published detailed prompts, correction loops, and final handoffs: [six walkthroughs](https://github.com/k-telux/OpticalModeler/blob/v2.0.0/examples/v2.0/README.md), [English dialogues](https://github.com/k-telux/OpticalModeler/blob/v2.0.0/examples/v2.0/WALKTHROUGHS.md), and [中文交互案例](https://github.com/k-telux/OpticalModeler/blob/v2.0.0/examples/v2.0/WALKTHROUGHS.zh-CN.md). They are edited teaching examples, not raw conversations or a new qualification campaign.

## Authority and revision rules

1. Apply system constraints first, then the newest explicit user wording or annotated screenshot, then active project rules, then this general skill, and only then older artifacts or PASS labels.
2. Freeze submitted or accepted packages. Make corrections in an active revision without overwriting frozen evidence; group related fixes before submission instead of publishing a version for every preview.
3. Keep one writer, run ID, revision root, deterministic generator lineage, saved-Blend lineage, and workflow ledger for the whole system. Use helpers only as read-only reviewers unless an isolated non-shared asset scope is explicit; never stitch independently authored modules into a whole-system claim.
4. Translate every correction into object families, fixed and editable degrees of freedom, world-space geometry, a measurable gate, and required evidence before editing. "Make it compact" does not authorize changing the optical order, internal spacing, or an accepted upper endpoint.
5. Use `BLOCKED` or `UNVERIFIED` when real geometry or evidence is missing. File existence, imported CAD, process success, labels, AABB contact, and self-reported text are not proof.
6. Use existing evidence and photographs before asking a material question. If the user requests a complete review candidate before further measurements, finish that authorized candidate with explicit unknowns; do not invent hardware identity or call it physically qualified.
7. When helpers are authorized, assign isolated scopes and keep ordinary findings in a consolidated queue read at checkpoints. A moving build/render is not stalled. External messages, uploads, and publication require the user's authorization for those actions.

## Core workflow

First choose new measurement design, photograph/schematic reconstruction, constrained correction, presentation-only rerender, or audit-only work. Record which inputs are design authority, reusable assets, or visual references. A new measurement at an old example's quality starts from an empty scene. An explicitly retained reconstruction baseline can be reused read-only in a new revision. For optics-only requests, exclude electrical/data/circuit visualization while retaining optical detectors and their mechanical supports.

Report a problem