Simulink Customize A2l logo

Simulink Customize A2l

OrganizationPopular
matlab
simulink-customize-a2l

Customize A2L (ASAP2) files generated from Simulink models using coder.asap2 and coder.mapping APIs. Use this skill when adding COMPU_METHODs, creating GROUPs, converting STD_AXIS to COM_AXIS, adding BIT_OPERATIONs, creating VARIANT_CODING, excluding measurements or struct elements, removing DEFAULT_EVENT_LIST, or any A2L customization for calibration tool compatibility (INCA, CANape). Also use when the user mentions ASAP2, ECU calibration data, A2L export.

Overview

Publishermatlab
Repositorysimulink-agentic-toolkit
Skill namesimulink-customize-a2l
Stars
1.2K
Forks
112
Bundled files
6
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by matlab on GitHub. Read the source before you install it.

Installation

Install the Simulink Customize A2l AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/code-generation/simulink-customize-a2l
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/matlab/simulink-agentic-toolkit.git /tmp/simulink-agentic-toolkit
mkdir -p .claude/skills
cp -r /tmp/simulink-agentic-toolkit/skills-catalog/code-generation/simulink-customize-a2l .claude/skills/simulink-customize-a2l
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Simulink Customize A2l in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Simulink Customize A2l on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Simulink Customize A2l is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Customize A2L Files

Customize A2L (ASAP2) files generated from Simulink models using the coder.asap2 and coder.mapping APIs, avoiding silent errors and undocumented pitfalls.

When to Use

  • Adding or modifying COMPU_METHODs (LINEAR, RAT_FUNC, TAB_VERB, IDENTICAL)
  • Creating or modifying GROUPs in the A2L file
  • Converting STD_AXIS to COM_AXIS for lookup tables
  • Adding BIT_OPERATION (LEFT_SHIFT, RIGHT_SHIFT, SIGN_EXTEND) to measurements
  • Creating VARIANT_CODING (VarCriterion, VarCharacteristic)
  • Excluding inports, outports, or struct elements from the A2L
  • Removing DEFAULT_EVENT_LIST or other IF_DATA blocks
  • Any customization passed via CustomEcuDescriptions to coder.asap2.export

When NOT to Use

  • Reading or parsing existing A2L files (use Vehicle Network Toolbox a2lfile)
  • Configuring XCP/CAN transport layers
  • Setting up Simulink model code generation (storage classes, data dictionaries)
  • General Embedded Coder build workflows without A2L customization

Core Workflow

Decision: Direct export vs. customization workflow

  • No element customization needed (only configuration like excluding struct elements or DEFAULT_EVENT_LIST): call coder.asap2.export directly with name-value options. No getEcuDescriptions needed.
  • Element customization needed (adding/modifying/deleting measurements, characteristics, groups, etc.): use the full getEcuDescriptions → customize → export workflow.
matlab
% === Path A: Config-only (no element changes) ===
load_system(modelName);
slbuild(modelName);
coder.asap2.export(modelName, SupportStructureElements=false, IncludeDefaultEventList=false);

% === Path B: Element customization ===
load_system(modelName);
slbuild(modelName);

% 1. Create ECU descriptions — pass ALL configuration options here
descObj = coder.asap2.getEcuDescriptions(modelName, ...
    SupportStructureElements=false, ...
    IncludeDefaultEventList=false);

% 2. Customize elements
add(descObj, newElement);
set(descObj, 'ElementType', 'Name', Prop=value);
info = get(descObj, 'ElementType', 'Name');
names = find(descObj, 'ElementType');
delete(descObj, 'ElementType', 'Name');

% 3. Export — MUST pass descObj back or all customizations are silently lost
coder.asap2.export(modelName, CustomEcuDescriptions=descObj);

Critical: When using Path B, omitting CustomEcuDescriptions=descObj in the export call silently discards all customizations with no error.

Critical: When using Path B, construction-time options (SupportStructureElements, etc.) CANNOT be passed to export alongside CustomEcuDescriptions — they must be passed to getEcuDescriptions.

Key Functions

FunctionPurpose
coder.asap2.getEcuDescriptionsCreate ECU description object (construction-time config)
coder.asap2.exportExport A2L file with customizations
coder.asap2.CompuMethodCreate computation method
coder.asap2.CharacteristicCreate characteristic (parameter)
coder.asap2.MeasurementCreate measurement (signal)
coder.asap2.GroupCreate A2L group
coder.asap2.RecordLayoutCreate record layout
coder.asap2.AxisInfoCreate axis points or axis descriptor
coder.asap2.VarCriterionCreate variant criterion
coder.asap2.VarCharacteristicCreate variant characteristic
coder.asap2.FunctionCreate FUNCTION object for grouping measurements/characteristics
coder.mapping.api.getGet code mapping object (persistent settings)
setInport / setOutportControl inport/outport A2L export (persistent)

See references/object-properties.md for mandatory fields, valid types, and creation order for each coder.asap2.* class.

Pattern Routing

Match the user's task to the correct reference for detailed guidance:

TaskKey RuleReference
Add COMPU_METHOD (RAT_FUNC, LINEAR, TAB_VERB)RAT_FUNC COEFFS direction is PHYS→INT — invert the desired formulareferences/compu-method-guidance.md
Convert STD_AXIS to COM_AXIS (shared breakpoints)Use ForceShared=true on the Characteristic — do NOT manually create AXIS_PTSreferences/customization-patterns.md
Add BIT_OPERATION to a measurementMust set BOTH BitMask AND MaskData — either alone produces no outputreferences/customization-patterns.md
Exclude inports/outports persistentlyUse coder.mapping.api + setInport/setOutport + slbuildreferences/customization-patterns.md
Create VARIANT_CODINGMust create supporting CHARACTERISTIC objects (selection + variant-dependent) with RecordLayouts and CompuMethods BEFORE VarCriterion/VarCharacteristic. All multi-value properties must be string arrays (not char/cell).references/variant-coding-guidance.md
Create Characteristic (CURVE, MAP, CUBOID)RecordLayout struct array must match axis count for STD_AXIS typesreferences/object-properties.md
Create MeasurementSet DataType='SWORD', EcuAddress='@ECU_Address@name@', CompuMethodName='NO_COMPU_METHOD' as defaultsreferences/object-properties.md
Create GroupSee mandatory fields and ROOT constraintreferences/object-properties.md
Create RecordLayoutStruct array required for multi-axis types (MAP, CUBOID); single struct for VALUE/VAL_BLKreferences/object-properties.md
Create AxisInfo / AXIS_PTSDual role: add(descObj, axisInfo) creates AXIS_PTS; characteristic.AxisInfo = [...] creates AXIS_DESCRreferences/object-properties.md
Control construction-time options (SupportStructureElements, IncludeDefaultEventList, etc.)Must pass at getEcuDescriptions() — cannot set after construction or pass to export with CustomEcuDescriptionsreferences/construction-time-properties.md

Release Requirements

FeatureMinimum Release
COMPU_METHOD, Measurement, Characteristic, BIT_OPERATIONR2022b
RecordLayout, AxisInfo (STD_AXIS, CUBOID)R2023a
Group (ROOT groups)R2023b
VarCriterion, VarCharacteristic (variant coding)R2025a

If the user's release is too old, inform them. Do not attempt workarounds — the APIs do not exist on older releases.

Common Mistakes

These cause silent failures or incorrect calibration data. Always check before generating code:

MistakeWhy It's WrongCorrect Approach
coder.asap2.export(modelName) without CustomEcuDescriptions=descObjSilently discards all customizations — no error, exports default A2LAlways pass descObj back when using the customization workflow
RAT_FUNC Coefficients = [0 0.5 -40 0 0 1] for "PHYS = 0.5×INT - 40"COEFFS is PHYS→INT, not INT→PHYS — produces the inverse conversionInvert: INT = 2×PHYS + 80 → [0 2 80 0 0 1]. See references/compu-method-guidance.md
set(descObj, ..., 'CompuMethodName', name) before adding the CompuMethodset() auto-creates a placeholder that blocks subsequent add()delete() the auto-created placeholder, then add() the user's version
MaskData.Shift without BitMaskBIT_OPERATION block is only emitted when both are setAlways set BitMask (e.g., '0xFF') alongside MaskData
MaskData.Shift = 3 expecting LEFT_SHIFTPositive = RIGHT_SHIFT; sign is counterintuitiveUse -3 for LEFT_SHIFT 3
Manually creating AXIS_PTS for STD→COM_AXISUnnecessary complexity; error-prone struct array handlingUse set(descObj, 'Characteristic', name, 'ForceShared', true)
descObj.SupportStructureElements = falseNot a settable property after constructionPass at creation: getEcuDescriptions(mdl, SupportStructureElements=false)
VarAddress = '0x5000' (char vector)Char vector silently produces empty output — no addresses, no criterion nameMust be string array: ["0x5000","0x5008"]
CompuVTabValues.Integers = [0,1,2]Property does not existUse CompuVTabValues.Values = [0, 1, 2]
CompuVTabValues.Literals = {'A','B'} (cell array)Accepted without error but exports 0 elementsMust be string array: ["A","B"]
Skipping slbuild after setInport/setOutportExport silently produces stale A2L with old settingsAlways slbuild after code mapping changes before export
Hardcoding EcuAddress = '0x0000'Calibration tools cannot resolve the address at import timeUse '@ECU_Address@<elementName>@' for linker resolution
Leaving mandatory fields unset on new objectsBlank fields produce invalid A2L — calibration tools reject the fileSee references/object-properties.md for required fields per class
Creating VarCriterion/VarCharacteristic without supporting CHARACTERISTICsVARIANT_CODING references characteristics that don't exist — calibration tool rejects the fileCreate selection CHARACTERISTIC (with TAB_VERB CompuMethod) and variant-dependent CHARACTERISTIC (with RecordLayout) BEFORE VarCriterion/VarCharacteristic. See references/variant-coding-guidance.md

Conventions

  • Verify A2L output with fileread after export — use contains for additions, ~contains for deletions/exclusions
  • Use string arrays (not char vectors or cell arrays) for all multi-value properties
  • Pass all configuration at getEcuDescriptions() construction time
  • Use ForceShared=true for STD→COM_AXIS (never build AXIS_PTS manually for this)
  • Use delete(descObj, 'ElementType', 'Name') to remove auto-created placeholders — this is the only recovery from the auto-creation trap caused by set() on a reference name before the referenced object exists
  • Prefer coder.mapping.api over coder.asap2 when settings should persist with the model

Copyright 2026 The MathWorks, Inc.


Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Simulink Customize A2l AI skill do?

Customize A2L (ASAP2) files generated from Simulink models using coder.asap2 and coder.mapping APIs. Use this skill when adding COMPU_METHODs, creating GROUPs, converting STD_AXIS to COM_AXIS, adding BIT_OPERATIONs, creating VARIANT_CODING, excluding measurements or struct elements, removing DEFAULT_EVENT_LIST, or any A2L customization for calibration tool compatibility (INCA, CANape). Also use when the user mentions ASAP2, ECU calibration data, A2L export.

Why use Simulink Customize A2l on TypingMind?

Because you install it once and use it with any model. Simulink Customize A2l is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Simulink Customize A2l in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/code-generation/simulink-customize-a2l. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Simulink Customize A2l?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Simulink Customize A2l?

As many as you like. As long as a model supports skills, you can use Simulink Customize A2l with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Simulink Customize A2l AI skill free?

It is published on GitHub by matlab. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇