Analyze task descriptions to recommend Claude models with cost comparisons.
npx skills add https://github.com/ApiliumCode/mayros --skill model-advisor
Please help me install this Agent Skill. Skill: model-advisor Source: https://github.com/ApiliumCode/mayros/tree/main/skills/official/model-advisor Command: npx skills add https://github.com/ApiliumCode/mayros --skill model-advisor
This Skill helps users select the most appropriate and cost-effective Claude AI model for their specific task requirements.
Use the model-advisor skill to recommend the best Claude model for a task involving complex reasoning and research.
High-intent search queries and answers about installing and using this skill.
To choose the best Claude model, you should analyze your task description for complexity and reasoning needs. The advisor evaluates task keywords to recommend Opus, Sonnet, or Haiku, providing a rationale that balances performance with cost efficiency.
The most cost-effective Claude model for complex reasoning depends on balancing capability and expense. The advisor analyzes task descriptions to determine if Opus is necessary or if Sonnet suffices, providing input and output costs per million tokens for comparison.
To compare Claude model costs, review the input and output costs per million tokens provided for Opus, Sonnet, and Haiku. The advisor generates this cost analysis alongside a recommendation to ensure you select the most economical model for your workload.
You need to use Claude Opus instead of Sonnet when your task requires maximum complexity handling and deep reasoning. The advisor analyzes task descriptions for specific keywords matching model strengths to determine if the performance uplift justifies the higher cost.
Yes, the model selection process works without external dependencies. It operates as a standalone skill that analyzes your task description text to match keywords with model strengths and calculate cost efficiency directly.
The limitation of using keyword matching for AI model selection is that it provides a basic recommendation based on task description analysis. It may not capture nuanced performance edge cases, but it does offer clear cost comparisons to guide your final choice.
rogsmeRoute text-based subtasks to OpenCode lazer models using predefined rules.
MadAppGangRoute tasks to AI model tiers based on complexity using keyword heuristics.
JNZaderTrack AI token usage and costs across sessions with budget alerts.
faroukBakariCompare Opus, Sonnet, Haiku, Claude, GPT, and Gemini models by benchmark data and cost multipliers.
