How does it handle behavioral differences in Opus 4.5?

It includes logic to soften aggressive instructions that cause tool overtriggering and adds specific snippets to prevent over-engineering and improve frontend design aesthetics when requested.

Does it support AWS Bedrock and Google Vertex AI?

Yes, it identifies the platform your codebase uses and replaces model strings with the correct Opus 4.5 format for Anthropic (1P), AWS Bedrock, Google Vertex AI, and Azure AI Foundry.

What is the 'effort' parameter mentioned in the skill?

Opus 4.5 supports an effort parameter; this skill sets it to 'high' by default during migration to ensure the model provides the most thorough reasoning and output quality.

Which models can this skill migrate from?

This skill supports migrating code and prompts from Claude Sonnet 4.0, Sonnet 4.5, and Opus 4.1. It specifically does not migrate Haiku models.

Claude Opus 4.5 Migration Assistant

Name: Claude Opus 4.5 Migration Assistant
Author: Microck

byMicrock

•

Developer Tools

Automates the transition of codebases and prompts from previous Claude models to the Opus 4.5 architecture.

About

This skill facilitates a seamless upgrade path for developers moving from Claude Sonnet 4.0, 4.5, or Opus 4.1 to the more powerful Opus 4.5 model. It automatically identifies and updates model identifiers across various platforms including the Anthropic API, AWS Bedrock, Google Vertex AI, and Azure AI Foundry, while removing deprecated beta headers. Beyond simple string replacement, it provides intelligent prompt tuning to mitigate behavioral nuances unique to Opus 4.5, such as tool overtriggering, over-engineering, and specific sensitivity to 'thinking' parameters, ensuring your AI integration remains robust and efficient.

Key Features

Code exploration enhancement for more thorough analysis by the model
Intelligent prompt softening to prevent tool overtriggering and over-engineering
Cross-platform model string updates for Anthropic API, Bedrock, Vertex AI, and Azure
Automated removal of unsupported 1M context beta headers with inline documentation
81 GitHub stars
Automatic configuration of the Opus-specific 'high' effort parameter

Use Cases

Upgrading legacy Claude 3.5 or Opus 4.1 integrations to utilize the latest Opus 4.5 capabilities
Standardizing AI model configurations across multi-cloud environments (AWS, GCP, Azure)
Optimizing system prompts that behave differently or over-engineer solutions after a model version update

About

Key Features

Code exploration enhancement for more thorough analysis by the model
Intelligent prompt softening to prevent tool overtriggering and over-engineering
Cross-platform model string updates for Anthropic API, Bedrock, Vertex AI, and Azure
Automated removal of unsupported 1M context beta headers with inline documentation
81 GitHub stars
Automatic configuration of the Opus-specific 'high' effort parameter

Use Cases

Upgrading legacy Claude 3.5 or Opus 4.1 integrations to utilize the latest Opus 4.5 capabilities
Standardizing AI model configurations across multi-cloud environments (AWS, GCP, Azure)
Optimizing system prompts that behave differently or over-engineer solutions after a model version update