Generate standard-compliant IEEE 802.11 waveforms using MATLAB WLAN Toolbox.
SkillScore78Maintained
Automatic
◆Coding pack
Last verified 8/16/2026
What it changes
Passed 17 of 22 test cases with the skill, and 3 of 22 without it.
Without skill13%
With skill78%
Checks it passed that the model alone missed
Passes integer microsecond value 2000 to wlanAPEPLength.
Passes integer microsecond value 3000 to wlanAPEPLength.
Calls showAllocation to visualize resource unit allocations.
and 19 more in the full report
15 fixed3 passed either way5 still failing0 broke
Pass-rate lift
+65 pp
Tokens
+250%
Agent turns
0%
Response time
-15%
Model gemini-3.6-flashMeasured 8/16/2026v118 of 23 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 15
Prompt
After instantiating an 802.11be EHT-MU configuration object in MATLAB, what function should I call to programmatically inspect assigned RU sizes, user counts per RU, and subchannel indices?
What was checked, without and with the skill
Checked
Without skill
With skill
Calls ruInfo on the configuration object.
Passed
Passed
Notes that ruInfo returns cell arrays for EHT configurations to support MRUs.
Missed
Passed
case-23 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md480 lines8 files
Generate WLAN Waveforms
Generate standard-compliant IEEE 802.11 waveforms for device testing, link-level
simulation, or signal analysis. This skill covers the transmit chain: configure
the PHY format, size the payload, generate the time-domain IQ waveform, and plot.
When to Use
Generating WLAN/Wi-Fi test waveforms for any 802.11 standard
Creating the transmit side of a link-level simulation
Building packets with specific MAC frame types (Data, Block Ack, Beacon, etc.)
Configuring OFDMA resource unit allocations (HE-MU, EHT-MU, or UHR-MU)
Targeting a specific packet duration or transmit time
When NOT to Use
Channel modeling, receiver processing, EVM/spectral mask — not covered
Non-WLAN waveforms (5G NR, LTE, Bluetooth)
UHR (802.11bn) requires R2026a or later. If the user requests a UHR waveform
and their release is older, inform them that UHR support was introduced in R2026a
and recommend upgrading.
Workflow
Every waveform generation follows this pipeline:
Select format → create the config object (see Format Selection)
Configure PHY → set bandwidth, MCS, spatial streams, antennas
Size the payload → set PSDU/APEP length directly or from a target duration
Create payload bits → random bits or MAC frame via wlanMACFrame
Import PyTorch, ONNX, or Keras 3 / TensorFlow 2.16+ deep learning models into MATLAB as dlnetwork objects. Use when importing .pt2 exported programs, traced .pt files, .onnx models, or Keras 3 models via matlabsaver. Covers importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromKeras, importNetworkFromTensorFlow, torch.export.export, PyTorchInputSizes, InputDataFormats, matlabsaver, tf_keras downgrade, numeric validation against PyTorch or ONNX Runtime, and placeholder/custom layer im