Matlab Design Pcb CouplerSAFE
The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
Overview
The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
58967e6f32b5OBSERVED · 2026-10-14What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: matlab-design-pcb-coupler
description: "Wilkinson, branchline, ratrace, directional couplers, corporate dividers, Rotman lenses for power splitting and beam-forming. TRIGGER: user asks to design, create, or analyze any coupler, splitter, power divider, combiner, or Rotman lens. Invoke BEFORE writing code — class names and design() availability vary per coupler type. SKIP: EM simulation/S-parameter extraction of an existing component (use matlab-analyze-em), building custom non-catalog geometry (use matlab-assemble-pcb-layout), material/stackup setup only (use matlab-manage-pcb-material), cascading multiple components (use matlab-integrate-pcb-circuit)."
license: https://www.mathworks.com/content/dam/mathworks/license/pmrl/license.md
metadata:
author: MathWorks
version: "1.0"
---
# Designing Couplers and Splitters
## When to Use
- Designing Wilkinson splitters (equal, unequal, wideband) for power division
- Creating branchline or ratrace couplers for quadrature or sum/difference networks
- Building corporate power dividers for array feed networks
- Designing directional couplers for signal sampling
- Creating SIW splitters or Rotman lenses for beam-forming
## When NOT to Use
- Designing transmission lines — use `matlab-design-pcb-transmission-line`
- Designing filters — use `matlab-design-pcb-filter`
- Designing passive components (inductors, capacitors, baluns) — use `matlab-design-pcb-passive`
- Cascading couplers with other components — use `matlab-integrate-pcb-circuit`
- Optimizing coupler performance — use `matlab-optimize-pcb-design`
## Typical Workflow
1. **Before:** `matlab-manage-pcb-material` — set up substrate and conductor
2. **This skill:** Design the coupler or splitter
3. **Check mesh/memory:** `memoryEstimate(obj, fc, 'RetainMesh', true)` — inspect auto-mesh density before committing to a full solve
4. **After:** `matlab-analyze-em` — validate S-parameters → `matlab-optimize-pcb-design` — tune dimensions → `matlab-integrate-pcb-circuit` — cascade into larger network
## Quick Reference — Component Selection
| Object | Type | Ports | Best For |
|--------|------|-------|----------|
| `wilkinsonSplitter` | Equal power divider | 3 | Standard 2-way equal split |
| `wilkinsonSplitterUnequal` | Unequal power divider | 3 | Asymmetric power distribution |
| `wilkinsonSplitterWideband` | Wideband equal divider | 3 | Multi-octave equal split |
| `couplerBranchline` | 90° hybrid | 4 | Quadrature combining/splitting |
| `couplerBranchlineWideband` | Wideband 90° hybrid | 4 | Multi-section wideband quadrature |
| `couplerRatrace` | 180° hybrid | 4 | Sum/difference networks |
| `couplerDirectional` | Directional coupler | 4 | Sampling, multi-section symmetric |
| `splitterTee` | T-junction | 3 | Simple reactive split |
| `powerDividerCorporate` | N-way corporate | N+1 | Array feed networks |
| `SIWSplitter` | SIW power divider | 3 | High-freq waveguide split |
| `rotmanLens` | Beam-forming network | N beam + N array | True-time-delay phased arrays |
## Wilkinson Splitters
### Equal Split
```matlab
ws = design(wilkinsonSplitter, 3e9);
show(ws);
memoryEstimate(ws, 3e9, 'RetainMesh', true); % Check mesh before solving
sp = sparameters(ws, linspace(1e9, 5e9, 51), 'SweepOption', 'interp');
rfplot(sp);
```
Key properties: `SplitLineLength`, `SplitLineWidth`, `Resistance`, `PortLineLength`, `PortLineWidth`, `GroundPlaneWidth`.
### Unequal Split
```matlab
ws = wilkinsonSplitterUnequal;
ws = design(ws, 3e9);
show(ws);
```
The power division ratio is controlled by the impedance transformation arms.
**Property reference (2-element vector properties):**
| Property | Description | Default |
|---|---|---|
| `SplitLineLength` | Length of split lines (m) | `0.0279` |
| `SplitLineWidth` | Width of split lines (m) | `[0.0014 0.0049]` (2-element vector: one per arm) |
| `MatchLineLength` | Length of output matching lines (m) | `0.0277` |
| `MatchLineWidth` | Width of output matching lines (m) | `[0.0039 0.0066]` (2-element vector: one per arm) |
| `Resistance` | Isolation resistor (ohms) | `106` |
### Wideband Wilkinson
Multi-section for extended bandwidth:
```matlab
ws = wilkinsonSplitterWideband;
ws = design(ws, 5e9);
show(ws);
sp = sparameters(ws, linspace(2e9, 8e9, 51), 'SweepOption', 'interp');
rfplot(sp);
```
**Property reference (vector properties scale with `NumSections`):**
| Property | Description | Default (3 sections) |
|---|---|---|
| `NumSections` | Number of cascaded sections | `3` |
| `Shape` | Shape of sections | `"Rectangular"` (`"Circular"`) |
| `SplitLineWidth` | Width of quarter-wave transformers (m) | `[8.55e-04 0.0014 0.0021]` (vector, one per section) |
| `Resistance` | Isolation resistor values (ohms) | `[100 183.40 141.42]` (vector, one per section) |
### Multi-Layer Wilkinson
```matlab
ws = design(wilkinsonSplitter, 5e9);
sub = dielectric("FR4", "Teflon");
sub.Thickness = [1e-3 0.5e-3]; % Set Thickness BEFORE assigning to component
ws.Substrate = sub;
ws.Height = 1.5e-3;
show(ws);
```
## Branchline Couplers
### Standard (Single-Section)
```matlab
bl = design(couplerBranchline, 5e9);
show(bl);
freq = linspace(3e9, 7e9, 51);
sp = sparameters(bl, freq, 'SweepOption', 'interp');
rfplot(sp);
```
Key properties: `SeriesArmLength`, `SeriesArmWidth`, `ShuntArmLength`, `ShuntArmWidth`, `PortLineLength`, `PortLineWidth`.
### Wideband (Multi-Section)
```matlab
blw = couplerBranchlineWideband;
blw.NumSections = 3;
blw = design(blw, 5e9);
show(blw);
```
**Property reference (vector properties scale with `NumSections`):**
| Property | Description | Default (2 sections) |
|---|---|---|
| `NumSections` | Number of branchline sections | `2` |
| `SeriesArmWidth` | Width of series arms (m) | `0.0051` (scalar or vector) |
| `ShuntArmWidth` | Width of shunt arms (m) | `[0.00096 0.0029 0.00096]` (vector, NumSections+1 elements) |
| `IsShielded` | Add metal shielding | `false` |
### Branchline with DGS
Adding DGS improves directivity and isolatTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
58967e6f32b5full audit observations/trust-audit/skill/matlab__matlab-design-pcb-coupler.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | 58967e6f32b5 | SAFE | B | 89 | first audit |
Questions
What does the Matlab Design Pcb Coupler skill do?
The MATLAB Agentic Toolkit brings proven MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.
Is Matlab Design Pcb Coupler safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Matlab Design Pcb Coupler access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (58967e6f32b5), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.