Dust Breaking Changes logo

Dust Breaking Changes

OrganizationPopular
dust-tt
dust-breaking-changes

CRITICAL guideline - Never introduce breaking changes to the private API without explicit user approval. Always warn and ask for validation first.

Overview

Publisherdust-tt
Repositorydust
Skill namedust-breaking-changes
Stars
1.5K
Forks
370
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by dust-tt on GitHub. Read the source before you install it.

Installation

Install the Dust Breaking Changes 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/dust-tt/dust/tree/main/.claude/skills/dust-breaking-changes
  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/dust-tt/dust.git /tmp/dust
mkdir -p .claude/skills
cp -r /tmp/dust/.claude/skills/dust-breaking-changes .claude/skills/dust-breaking-changes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dust Breaking Changes 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 Dust Breaking Changes 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 Dust Breaking Changes 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.

API Breaking Changes - Critical Rule

CRITICAL: You must NEVER introduce breaking changes to the private API without explicit user approval.

What is a Breaking Change?

A breaking change is any modification that would require existing API consumers to update their code, including:

  • Endpoints: Removing or renaming API endpoints
  • Schemas: Changing request/response schemas
    • Removing fields from responses
    • Changing field types (string → number, object → array, etc.)
    • Making optional fields required
    • Renaming fields
  • Authentication: Modifying authentication or authorization requirements
  • HTTP Methods: Changing HTTP methods (GET → POST) or status codes
  • Error Formats: Altering error response formats or codes
  • Query Parameters: Removing or making required previously optional parameters
  • Headers: Requiring new headers or changing header validation

Process for API Changes

Before making ANY change to API code, follow this process:

1. Identify API Code

API code includes:

  • Route handlers in front-api/routes/**
  • Request/response type definitions used by these routes
  • Validation schemas (Zod, etc.) used in API handlers
  • Middleware that affects API behavior

2. Analyze Impact

When you're about to modify API code, ask yourself:

  • Will this change the shape of the response?
  • Will this require API consumers to update their code?
  • Could this break existing integrations or clients?

3. If Breaking Change: STOP and Warn

If the answer to any of the above is "yes":

DO NOT PROCEED WITH THE CHANGE

Instead:

  1. STOP immediately

  2. WARN the user with a clear message like:

    ⚠️ WARNING: Breaking API Change Detected
    
    The proposed change would be a breaking change to the private API:
    [Explain what specifically would break]
    
    Impact:
    - [List what API consumers would need to update]
    - [List which endpoints are affected]
    
    This requires your explicit approval before I can proceed.
    
    Would you like me to:
    1. Proceed with the breaking change
    2. Find a backwards-compatible alternative
    3. Cancel this change
  3. WAIT for explicit user approval before continuing

4. Only Proceed After Approval

Only after the user has explicitly approved the breaking change should you implement it.

Safe Alternatives to Consider

When a breaking change is detected, suggest backwards-compatible alternatives:

  • Adding fields: Safe (add new optional fields to responses)
  • Deprecation: Add new endpoint/field, mark old as deprecated
  • Default values: Provide sensible defaults for new required fields

Examples

❌ Breaking Change (Requires Approval)

typescript
// Before
type APIResponse = {
  userId: string;
  name: string;
};

// After - BREAKING: removed userId field
type APIResponse = {
  id: string; // renamed from userId
  name: string;
};

✅ Safe Change (No Approval Needed)

typescript
// Before
type APIResponse = {
  userId: string;
  name: string;
};

// After - SAFE: added optional field
type APIResponse = {
  userId: string;
  name: string;
  email?: string; // new optional field
};

✅ Backwards Compatible Alternative

typescript
// SAFE: Keep old field, add new one
type APIResponse = {
  userId: string; // kept for backwards compatibility
  id: string; // new field
  name: string;
};

When This Skill Applies

This rule applies automatically whenever you are:

  • Modifying files in front-api/routes/**
  • Changing type definitions that are exported and used in API responses
  • Updating validation schemas used by API endpoints
  • Refactoring code that affects API contracts

You don't need to manually invoke this skill - these guidelines should be followed automatically for any API-related work.

Frequently asked questions

What does the Dust Breaking Changes AI skill do?

CRITICAL guideline - Never introduce breaking changes to the private API without explicit user approval. Always warn and ask for validation first.

Why use Dust Breaking Changes on TypingMind?

Because you install it once and use it with any model. Dust Breaking Changes 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 Dust Breaking Changes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dust-tt/dust/tree/main/.claude/skills/dust-breaking-changes. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dust Breaking Changes?

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 Dust Breaking Changes?

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

Is the Dust Breaking Changes AI skill free?

Yes. It is published on GitHub by dust-tt under the MIT license. 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 👇