Configuring Block Policy logo

Configuring Block Policy

OrganizationPopular
matlab
configuring-block-policy

Guide users through creating and managing .satk/block-policy.json for controlling which blocks the agent can use, which are excluded, and which block parameters the agent should not modify. Use when setting up block usage policy for a project.

Overview

Publishermatlab
Repositorysimulink-agentic-toolkit
Skill nameconfiguring-block-policy
Stars
1.2K
Forks
112
Bundled files
1
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.

  • 1 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 Configuring Block Policy 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/model-based-design-core/configuring-block-policy
  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/model-based-design-core/configuring-block-policy .claude/skills/configuring-block-policy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Configuring Block Policy 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 Configuring Block Policy 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 Configuring Block Policy 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.

Configuring Block Policy

Create or update .satk/block-policy.json — the file that controls which blocks (library or built-in) the agent can use, which are excluded, and which block parameters the agent should not modify.

When to Use

  • User asks to set up, create, or configure block policy
  • User asks to restrict or exclude blocks
  • User wants to prevent the agent from modifying certain block parameters
  • building-simulink-models routes here via the policy gate

When NOT to Use

  • Actively building a model → building-simulink-models
  • Improving block descriptions or categories → simulink-curating-library-kg
  • Declaring which libraries exist → Library Setup gate in building-simulink-models

Prerequisites

  • .satk/reuse-libraries.json must exist.

Workflow

  1. Check state — Does .satk/block-policy.json exist? If yes, load and summarize. If no, start fresh.
  2. Policy mode — (skip if no libraries specified) Ask: prefer libraries with built-in fallback, or custom libraries blocks only (no fallback)?
  3. Excluded blocks (optional) — Are there any blocks (library or built-in) that should never be placed in your models? Collect referenceBlock + reason.
  4. Off-limits parameters (optional) — Are there any block parameters you don't want the agent to modify? Collect referenceBlock + protectedParams[].
  5. Save — Validate and write with library.BlockPolicy.save().

API

matlab
policyData = struct();
policyData.policyMode = 'approved_blocks_only';
policyData.fallbackToBuiltins = false;
% Excluded — agent will never place these blocks
policyData.blockedBlocks = struct('referenceBlock', 'LegacyLib/OldCtrl', 'reason', 'Superseded');
% Protected params — agent won't modify these values
policyData.blockRules = struct('referenceBlock', 'Lib/SpeedCtrl', ...
    'protectedParams', {{'Kp', 'Ki', 'Kd'}});

library.BlockPolicy.save(projectRoot, policyData);

For defaults (no restrictions):

matlab
policyData = library.BlockPolicy.defaults();
library.BlockPolicy.save(projectRoot, policyData);

Schema

json
{
  "schemaVersion": 1,
  "policyMode": "approved_blocks_only | prefer_customer_libraries",
  "fallbackToBuiltins": false,
  "blockedBlocks": [
    { "referenceBlock": "LegacyLib/OldController", "reason": "Superseded" }
  ],
  "blockRules": [
    { "referenceBlock": "Lib/SpeedController", "protectedParams": ["Kp", "Ki", "Kd", "SampleTime"] }
  ]
}

Validation Rules

  • policyMode: must be prefer_customer_libraries or approved_blocks_only
  • approved_blocks_only + fallbackToBuiltins: true → rejected (contradictory)
  • protectedParams must be a non-empty array of strings
  • Malformed policy → error (never silently ignored)

Updating an Existing Policy

When .satk/block-policy.json already exists:

  1. Load with library.BlockPolicy.loadRaw(projectRoot, libConfig)
  2. Summarize current state — do NOT re-run the full wizard
  3. Ask what to change, apply to existing struct, save

Common updates: exclude a block, mark params as off-limits, change mode, remove an entry.

Guardrails

  • Never write block-policy.json without user confirmation
  • Always validate before saving (library.BlockPolicy.validate(policyData))
  • If user provides a block name without the full library path, look it up in the KG to resolve the referenceBlock

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 Configuring Block Policy AI skill do?

Guide users through creating and managing .satk/block-policy.json for controlling which blocks the agent can use, which are excluded, and which block parameters the agent should not modify. Use when setting up block usage policy for a project.

Why use Configuring Block Policy on TypingMind?

Because you install it once and use it with any model. Configuring Block Policy 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 Configuring Block Policy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/model-based-design-core/configuring-block-policy. 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 Configuring Block Policy?

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 Configuring Block Policy?

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

Is the Configuring Block Policy 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 👇