HezaoHezao
Featured
poirot
Poirot is a deep research agent kernel with a middleware-first architecture, five-layer long-term memory, multi-agent orchestration, sandbox isolation, and a three-layer skill self-evolution system, backed by 2400+ tests.
OpticalModeler
OpticalModeler is an Agent Skill that converts 2D photonics schematics into physically auditable, Blender-based 3D optical tables with hard acceptance gates for topology, apertures, CAD, fasteners, load paths, and fiber routing.
Stars
190
7-day growth
No data
Forks
2
Open issues
0
License
MIT
Last updated
2026-07-26
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It treats optical reconstruction as an evidence-first process, enforcing explicit PASS/BLOCKED/UNVERIFIED states through automated ray, mesh, and BVH checks, making it a unique tool for reproducible, auditable lab documentation.
Who it is for
- Optical engineers and lab researchers needing verified 3D reconstructions from 2D schematics
- Blender users working on photonics or laboratory visualization
- AI agent developers building skills for automated scientific modeling
Use cases
- Reconstructing laboratory optical paths from published 2D schematics into fully annotated 3D Blender scenes
- Auditing an existing optical table for correct post placement, centered apertures, beam clearance, and fiber bend radius
- Generating publication-quality rendered images with machine-readable acceptance records (hashes, manifests, rule compliance)
Strengths
- Evidence-first methodology with explicit audit states (PASS/BLOCKED/UNVERIFIED) and automated validation checks
- Treats manufacturer CAD as assets, not proofs, and enforces hardware-first assembly from verified table holes
- Open source (MIT license) and integrates with the Agent Skills ecosystem for extensible use
Considerations
- Requires a compatible Agent Skills installer (e.g., npx skills) and Blender 4.x; not a standalone application
- Excludes third-party CAD, oversized Blend files, and does not provide mechanical, spectral, or safety certifications
- Whole-project success requires an active rule-compliance matrix; scoped evidence remains PARTIAL/SCOPED
README quick start
Quick start
Send message below to your agent:
Description
Evidence-gated Agent Skill for reconstructing 2D photonics schematics as physically auditable Blender optical tables with CAD, beam-path, mechanics, and render proof.
Related repositories
Similar projects matched by category, topics, and programming language.
0xwilliamortiz
Featured
ponytail-improved
Ponytail is a plugin for AI coding agents that enforces a disciplined ladder of reuse before writing code, reducing code volume by roughly 54% while preserving safety.
lopopolo
Featured
harness-engineering
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.