model-recommendation

Analyze .agent.md or .prompt.md files to recommend optimal GitHub Copilot models.

Updated Mar 11, 2026
One-click install
npx skills add https://github.com/selfagency/agentsy --skill model-recommendation-selfagency
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model-recommendation
Source: https://github.com/selfagency/agentsy/tree/main/.agents/skills/model-recommendation
Command: npx skills add https://github.com/selfagency/agentsy --skill model-recommendation-selfagency

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

You waste time and budget choosing Copilot models because you lack an evidence-based way to match a chatmode or prompt’s complexity and tool needs to the right model options.

Core Features & Use Cases

  • Task-aware model selection: Analyzes a .agent.md or .prompt.md file to infer complexity, reasoning depth, context size, and whether vision is needed.
  • Cost-aware recommendations: Factors in Copilot subscription tier (Free/Pro/Pro+) and model multipliers to balance quality with cost-efficiency.
  • Alternatives and integration guidance: Suggests primary + alternative models and provides frontmatter/model-update guidance for fast adoption in VS Code Copilot.
  • Deprecation awareness: Flags deprecated models (e.g., o3, o4-mini, older variants) and recommends migration targets.

Quick Start

Tell the skill the path to the file you want analyzed, your Copilot subscription tier, and whether you prefer speed, cost, quality, or balanced results.

Frequently Asked Questions about model-recommendation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I pick the best GitHub Copilot model for a specific prompt?

To pick the best GitHub Copilot model, you can analyze your `.agent.md` or `.prompt.md` file to evaluate task complexity, required tools, and context size. The skill outputs primary and alternative model recommendations based on your subscription tier.

What is the most cost-efficient Copilot model for code generation tasks?

The most cost-efficient Copilot model depends on your subscription tier and task complexity. Analyzing prompt frontmatter and applying a capability and cost decision matrix balances model multipliers with quality for optimal code generation results.

Can I check if my current Copilot model is deprecated and find migration targets?

Yes, you can check if your Copilot model is deprecated. The skill flags deprecated models like o3 and o4-mini and recommends modern migration targets to ensure your chatmodes and prompts remain functional.

How do I map required capabilities to Copilot models for architecture review?

Map required capabilities by parsing `.agent.md` frontmatter to extract specified tools and reasoning depth. The skill applies a capability decision matrix to match architecture review needs with the appropriate Copilot model.

Does this model selection process work with Free, Pro, and Pro+ Copilot tiers?

Yes, the model selection process works with Free, Pro, and Pro+ Copilot tiers. Recommendations factor in your specific subscription tier and model multipliers to balance quality with cost-efficiency for your available options.