model-recommendation
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
npx skills add majiayu000/claude-skill-registry --skill model-recommendation-dhaim-svg-githuboverview --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Analyze .agent.md or .prompt.md files to understand purpose, complexity, and required capabilities, then recommend the most suitable AI model(s) from GitHub Copilot's options. Provide rationale based on task characteristics, model strengths, cost-efficiency, and performance trade-offs.
How it works
The skill reads a target .agent.md or .prompt.md file, extracts frontmatter, and analyzes the body to determine task complexity, reasoning depth, code generation needs, multi-turn requirements, context window, and any specialized capabilities. It categorizes the task into one of several patterns (e.g., Simple Repetitive Tasks, Code Generation, Complex Refactoring, Debugging, Planning/Research, Code Review, Specialized Domain Tasks, Advanced Reasoning). It then evaluates available models (e.g., GPT-4.1, GPT-5 mini, GPT-5, Claude Sonnet 3.5/4/4.5, Claude Opus 4.1, Gemini 2.5 Pro, Grok Code Fast 1, and deprecated options) against a selection matrix and a decision-tree to propose a primary model and up to two alternatives. It considers subscription tier (Free, Pro, Pro+) and a priority factor (Speed, Cost, Quality, Balanced) to contextualize recommendations. It may reference Context7 for up-to-date capabilities if uncertainty exists. Finally, it formats a structured markdown report with sections for file analysis, task characteristics, model recommendations, and integration guidance.
When to use it
Use when you need an evidence-based model selection for a given prompt or agent file. Triggered when analyzing a new or updated .agent.md or .prompt.md to determine the best fit model based on the file content and user subscription constraints.
What it can touch
The workflow relies on frontmatter and body content analysis to map to model capabilities. It considers the following inputs and constraints: input file path, optional subscriptionTier (Free, Pro, Pro+), and priorityFactor (Balanced, Speed, Cost, Quality). It references the available models list and tools declared in frontmatter to align model capabilities with task requirements.
Caveats
- Outputs depend on the accuracy of file analysis and the stated capabilities matrix.
- Some model capabilities may require verification via Context7 if uncertain about current features or deprecation status.
- The skill adheres to the declared list of models and does not imply outcomes beyond stated model mappings and the decision tree.
# AI Model Recommendation for Copilot Chat Modes and Prompts ## Mission Analyze `.agent.md` or `.prompt.md` files to understand their purpose, complexity, and required capabilities, then recommend the most suitable AI model(s) from GitHub Copilot's available options. Provide rationale based on task characteristics, model strengths, cost-efficiency, and performance trade-offs. ## Scope & Preconditions - **Input**: Path to a `.agent.md` or `.prompt.md` file - **Available Models**: GPT-4.1, GPT-5, GPT-5 mini, GPT-5 Codex, Claude Sonnet 3.5, Claude Sonnet 4, Claude Sonnet 4.5, Claude Opus 4.1, Gemini 2.5 Pro, Gemini 2.0 Flash, Grok Code Fast 1, o3, o4-mini (with deprecation dates) - **Model Auto-Selection**: Available in VS Code (Sept 2025+) - selects from GPT-4.1, GPT-5 mini, GPT-5, Claude Sonnet 3.5, Claude Sonnet 4.5 (excludes premium multipliers > 1) - **Context**: GitHub Copilot subscription tiers (Free: 2K completions + 50 chat/month with 0x models only; Pro: unlimited 0x + 1000 premium/month; Pro+: unlimited 0x + 5000 premium/month) ## Inputs Required: - `${input:filePath:Path to .agent.md or .prompt.md file}` - Absolute or workspace-relative path to the file to analyze Optional
- Mission
- Scope & Preconditions
- Inputs
- Workflow
- 1. File Analysis Phase
- 2. Model Evaluation Phase
- 3. Recommendation Generation Phase
- 4. Integration Recommendations
- 5. Context7 Integration for Up-to-Date Information
- Output Expectations
- Report Structure
- Output Quality Standards
- Quality Assurance
- Validation Steps
What does the model-recommendation skill do?
Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill model-recommendation-dhaim-svg-githuboverview --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.