Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →matlab/matlab-deploy-embedded-code
Deploy MATLAB-generated code to embedded hardware using Embedded Coder.
Passed 24 of 24 test cases with the skill, and 10 of 24 without it.
and 21 more in the full report
15 fixed10 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am deploying to an embedded MCU with 32 KB of SRAM. Write the MATLAB configuration setting to limit the generated stack usage to 512 bytes.
| Checked | Without skill | With skill |
|---|---|---|
| Sets StackUsageMax to 512. | Missed | Passed |
| Configures stack limit constraints on the coder configuration object. | Passed | Passed |
The instructions your model reads when the skill loads.
Configure MATLAB Coder with Embedded Coder for production-quality code generation targeting embedded hardware, and verify correctness with processor-in-the-loop (PIL) testing.
matlab-deploy-embedded-ai; for the full AI compression and model-loading workflow, trigger matlab-deploy-embedded-ai firstcodegen workflowscfg = coder.config("lib", "ecoder", true);
The "ecoder", true flag creates an ERT-based (Embedded Real-Time) configuration
that generates production-quality code with no OS dependencies.
With coder.hardware:
cfg.Hardware = coder.hardware("STM32F746G-Discovery");
Without the support package, configure hardware manually:
test cases passed, vs 10 / 24 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.