Skip to content

k-telux/OpticalModeler

Repository files navigation

OpticalModeler

From 2D photonics schematics to physically auditable Blender optical tables.

English · 简体中文 · 日本語

Validation Agent Skills Blender License: MIT

Nature-style render of a physically audited G1/G2 optical table

OpticalModeler is an evidence-first Agent Skill for reconstructing laboratory optical paths in Blender. It treats optical topology, real apertures, manufacturer CAD, fasteners, load paths, fiber routing, and artifact lineage as hard acceptance gates—not decorative details.

Independent community project. Not affiliated with or endorsed by Thorlabs, Inc. Product names identify compatible hardware only. A rendered CAD assembly is not a mechanical, spectral, laser-safety, or experimental certification.

Why OpticalModeler

Physical assembly Optical truth Fail-closed evidence
Post-first placement, real table holes, fasteners, load paths, and supported hardware. Centered apertures, splitter planes, branch continuity, internal fine beams, and fiber bend constraints. Reopened-scene audits, ray/BVH checks, hashes, manifests, annotated renders, and explicit PASS / BLOCKED / UNVERIFIED states.

2D input → verified 3D output

Original schematic Annotated 3D reconstruction
Original G1/G2 schematic Annotated top view of the reconstructed optical table

The sanitized G1/G2 case study includes the original 2D input, editorial 3D renders, and a machine-readable acceptance record. Vendor STEP/CAD files and the large laboratory .blend are intentionally excluded.

Install

With a compatible Agent Skills installer:

npx skills add k-telux/OpticalModeler

Or copy skills/thorlabs-blender-optical-path into your agent's skills directory.

Quick start

Use $thorlabs-blender-optical-path to reconstruct this pump-probe schematic in Blender and produce a fail-closed physical audit.
Audit this optical table for real post/load paths, centered apertures, beam clearance, fiber bend radius, and stale evidence.

The skill guides the agent to:

  1. map schematic nodes to experimental roles, real assets, ports, and support paths;
  2. solve optical centers, surfaces, splitter planes, and branch continuity;
  3. assemble hardware post-first from verified table holes;
  4. prove one representative instance before propagation;
  5. reopen the saved scene and run mesh, ray, and BVH checks;
  6. package visual, GLB, report, manifest, hash, and rule-compliance evidence consistently.

Repository map

skills/thorlabs-blender-optical-path/   canonical English skill
i18n/zh-CN/                            Simplified Chinese edition
i18n/ja/                               Japanese edition
rules/                                 reusable project-memory template
examples/g1g2/                         sanitized 2D-to-3D case study
scripts/validate_repository.py         dependency-free release gate

The English skill is the technical source of truth. Localized editions are maintained as language entry points and explicitly defer to the canonical geometry and evidence references.

Validation and limits

  • Manufacturer CAD is an asset source, never proof of correct assembly.
  • Free-space rays, guided fiber, and electrical cables remain semantically distinct.
  • Whole-project success requires an active-rule compliance matrix; scoped evidence stays PARTIAL/SCOPED.
  • The repository excludes third-party CAD, private paths, oversized Blend files, and unsupported real-world performance claims.
  • Every release is checked for skill metadata, links, file size, privacy leaks, forbidden CAD binaries, and acceptance-state consistency.

See CONTRIBUTING.md for rule proposals and case-study submissions, and SECURITY.md for responsible disclosure.

Maintained by telux. Released under the MIT License.

About

Evidence-gated Agent Skill for reconstructing 2D photonics schematics as physically auditable Blender optical tables with CAD, beam-path, mechanics, and render proof.

Topics

Resources

License

Contributing

Security policy

Stars

60 stars

Watchers

0 watching

Forks

Packages

 
 
 

Contributors

Languages