{"id":"3177b4a7-f56c-4c8e-a78c-6d831e78b66c","shortId":"33rGy5","kind":"skill","title":"model-recommendation","tagline":"Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency","description":"# AI Model Recommendation for Copilot Chat Modes and Prompts\n\n## Mission\n\nAnalyze `.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.\n\n## Scope & Preconditions\n\n- **Input**: Path to a `.agent.md` or `.prompt.md` file\n- **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)\n- **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)\n- **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)\n\n## Inputs\n\nRequired:\n\n- `${input:filePath:Path to .agent.md or .prompt.md file}` - Absolute or workspace-relative path to the file to analyze\n\nOptional:\n\n- `${input:subscriptionTier:Pro}` - User's Copilot subscription tier (Free, Pro, Pro+) - defaults to Pro\n- `${input:priorityFactor:Balanced}` - Optimization priority (Speed, Cost, Quality, Balanced) - defaults to Balanced\n\n## Workflow\n\n### 1. File Analysis Phase\n\n**Read and Parse File**:\n\n- Read the target `.agent.md` or `.prompt.md` file\n- Extract frontmatter (description, mode, tools, model if specified)\n- Analyze body content to identify:\n  - Task complexity (simple/moderate/complex/advanced)\n  - Required reasoning depth (basic/intermediate/advanced/expert)\n  - Code generation needs (minimal/moderate/extensive)\n  - Multi-turn conversation requirements\n  - Context window needs (small/medium/large)\n  - Specialized capabilities (image analysis, long-context, real-time data)\n\n**Categorize Task Type**:\n\nIdentify the primary task category based on content analysis:\n\n1. **Simple Repetitive Tasks**:\n\n   - Pattern: Formatting, simple refactoring, adding comments/docstrings, basic CRUD\n   - Characteristics: Straightforward logic, minimal context, fast execution preferred\n   - Keywords: format, comment, simple, basic, add docstring, rename, move\n\n2. **Code Generation & Implementation**:\n\n   - Pattern: Writing functions/classes, implementing features, API endpoints, tests\n   - Characteristics: Moderate complexity, domain knowledge, idiomatic code\n   - Keywords: implement, create, generate, write, build, scaffold\n\n3. **Complex Refactoring & Architecture**:\n\n   - Pattern: System design, architectural review, large-scale refactoring, performance optimization\n   - Characteristics: Deep reasoning, multiple components, trade-off analysis\n   - Keywords: architect, refactor, optimize, design, scale, review architecture\n\n4. **Debugging & Problem-Solving**:\n\n   - Pattern: Bug fixing, error analysis, systematic troubleshooting, root cause analysis\n   - Characteristics: Step-by-step reasoning, debugging context, verification needs\n   - Keywords: debug, fix, troubleshoot, diagnose, error, investigate\n\n5. **Planning & Research**:\n\n   - Pattern: Feature planning, research, documentation analysis, ADR creation\n   - Characteristics: Read-only, context gathering, decision-making support\n   - Keywords: plan, research, analyze, investigate, document, assess\n\n6. **Code Review & Quality Analysis**:\n\n   - Pattern: Security analysis, performance review, best practices validation, compliance checking\n   - Characteristics: Critical thinking, pattern recognition, domain expertise\n   - Keywords: review, analyze, security, performance, compliance, validate\n\n7. **Specialized Domain Tasks**:\n\n   - Pattern: Django/framework-specific, accessibility (WCAG), testing (TDD), API design\n   - Characteristics: Deep domain knowledge, framework conventions, standards compliance\n   - Keywords: django, accessibility, wcag, rest, api, testing, tdd\n\n8. **Advanced Reasoning & Multi-Step Workflows**:\n   - Pattern: Algorithmic optimization, complex data transformations, multi-phase workflows\n   - Characteristics: Advanced reasoning, mathematical/algorithmic thinking, sequential logic\n   - Keywords: algorithm, optimize, transform, sequential, reasoning, calculate\n\n**Extract Capability Requirements**:\n\nBased on `tools` in frontmatter and body instructions:\n\n- **Read-only tools** (search, fetch, usages, githubRepo): Lower complexity, faster models suitable\n- **Write operations** (edit/editFiles, new): Moderate complexity, accuracy important\n- **Execution tools** (runCommands, runTests, runTasks): Validation needs, iterative approach\n- **Advanced tools** (context7/\\*, sequential-thinking/\\*): Complex reasoning, premium models beneficial\n- **Multi-modal** (image analysis references): Requires vision-capable models\n\n### 2. Model Evaluation Phase\n\n**Apply Model Selection Criteria**:\n\nFor each available model, evaluate against these dimensions:\n\n#### Model Capabilities Matrix\n\n| Model                   | Multiplier | Speed    | Code Quality | Reasoning | Context | Vision | Best For                                          |\n| ----------------------- | ---------- | -------- | ------------ | --------- | ------- | ------ | ------------------------------------------------- |\n| GPT-4.1                 | 0x         | Fast     | Good         | Good      | 128K    | ✅     | Balanced general tasks, included in all plans     |\n| GPT-5 mini              | 0x         | Fastest  | Good         | Basic     | 128K    | ❌     | Simple tasks, quick responses, cost-effective     |\n| GPT-5                   | 1x         | Moderate | Excellent    | Advanced  | 128K    | ✅     | Complex code, advanced reasoning, multi-turn chat |\n| GPT-5 Codex             | 1x         | Fast     | Excellent    | Good      | 128K    | ❌     | Code optimization, refactoring, algorithmic tasks |\n| Claude Sonnet 3.5       | 1x         | Moderate | Excellent    | Excellent | 200K    | ✅     | Code generation, long context, balanced reasoning |\n| Claude Sonnet 4         | 1x         | Moderate | Excellent    | Advanced  | 200K    | ❌     | Complex code, robust reasoning, enterprise tasks  |\n| Claude Sonnet 4.5       | 1x         | Moderate | Excellent    | Expert    | 200K    | ✅     | Advanced code, architecture, design patterns      |\n| Claude Opus 4.1         | 10x        | Slow     | Outstanding  | Expert    | 1M      | ✅     | Large codebases, architectural review, research   |\n| Gemini 2.5 Pro          | 1x         | Moderate | Excellent    | Advanced  | 2M      | ✅     | Very long context, multi-modal, real-time data    |\n| Gemini 2.0 Flash (dep.) | 0.25x      | Fastest  | Good         | Good      | 1M      | ❌     | Fast responses, cost-effective (deprecated)       |\n| Grok Code Fast 1        | 0.25x      | Fastest  | Good         | Basic     | 128K    | ❌     | Speed-critical simple tasks, preview (free)       |\n| o3 (deprecated)         | 1x         | Slow     | Good         | Expert    | 128K    | ❌     | Advanced reasoning, algorithmic optimization      |\n| o4-mini (deprecated)    | 0.33x      | Fast     | Good         | Good      | 128K    | ❌     | Reasoning at lower cost (deprecated)              |\n\n#### Selection Decision Tree\n\n```\nSTART\n  │\n  ├─ Task Complexity?\n  │   ├─ Simple/Repetitive → GPT-5 mini, Grok Code Fast 1, GPT-4.1\n  │   ├─ Moderate → GPT-4.1, Claude Sonnet 4, GPT-5\n  │   └─ Complex/Advanced → Claude Sonnet 4.5, GPT-5, Gemini 2.5 Pro, Claude Opus 4.1\n  │\n  ├─ Reasoning Depth?\n  │   ├─ Basic → GPT-5 mini, Grok Code Fast 1\n  │   ├─ Intermediate → GPT-4.1, Claude Sonnet 4\n  │   ├─ Advanced → GPT-5, Claude Sonnet 4.5\n  │   └─ Expert → Claude Opus 4.1, o3 (deprecated)\n  │\n  ├─ Code-Specific?\n  │   ├─ Yes → GPT-5 Codex, Claude Sonnet 4.5, GPT-5\n  │   └─ No → GPT-5, Claude Sonnet 4\n  │\n  ├─ Context Size?\n  │   ├─ Small (<50K tokens) → Any model\n  │   ├─ Medium (50-200K) → Claude models, GPT-5, Gemini\n  │   ├─ Large (200K-1M) → Gemini 2.5 Pro, Claude Opus 4.1\n  │   └─ Very Large (>1M) → Gemini 2.5 Pro (2M), Claude Opus 4.1 (1M)\n  │\n  ├─ Vision Required?\n  │   ├─ Yes → GPT-4.1, GPT-5, Claude Sonnet 3.5/4.5, Gemini 2.5 Pro, Claude Opus 4.1\n  │   └─ No → All models\n  │\n  ├─ Cost Sensitivity? (based on subscriptionTier)\n  │   ├─ Free Tier → 0x models only: GPT-4.1, GPT-5 mini, Grok Code Fast 1\n  │   ├─ Pro (1000 premium/month) → Prioritize 0x, use 1x judiciously, avoid 10x\n  │   └─ Pro+ (5000 premium/month) → 1x freely, 10x for critical tasks\n  │\n  └─ Priority Factor?\n      ├─ Speed → GPT-5 mini, Grok Code Fast 1, Gemini 2.0 Flash\n      ├─ Cost → 0x models (GPT-4.1, GPT-5 mini) or lower multipliers (0.25x, 0.33x)\n      ├─ Quality → Claude Sonnet 4.5, GPT-5, Claude Opus 4.1\n      └─ Balanced → GPT-4.1, Claude Sonnet 4, GPT-5\n```\n\n### 3. Recommendation Generation Phase\n\n**Primary Recommendation**:\n\n- Identify the single best model based on task analysis and decision tree\n- Provide specific rationale tied to file content characteristics\n- Explain multiplier cost implications for user's subscription tier\n\n**Alternative Recommendations**:\n\n- Suggest 1-2 alternative models with trade-off explanations\n- Include scenarios where alternatives might be preferred\n- Consider priority factor overrides (speed vs. quality vs. cost)\n\n**Auto-Selection Guidance**:\n\n- Assess if task is suitable for auto model selection (excludes premium models > 1x)\n- Explain when manual selection is beneficial vs. letting Copilot choose\n- Note any limitations of auto-selection for the specific task\n\n**Deprecation Warnings**:\n\n- Flag if file currently specifies a deprecated model (o3, o4-mini, Claude Sonnet 3.7, Gemini 2.0 Flash)\n- Provide migration path to recommended replacement\n- Include timeline for deprecation (e.g., \"o3 deprecating 2025-10-23\")\n\n**Subscription Tier Considerations**:\n\n- **Free Tier**: Recommend only 0x multiplier models (GPT-4.1, GPT-5 mini, Grok Code Fast 1)\n- **Pro Tier**: Balance between 0x (unlimited) and 1x (1000/month) models\n- **Pro+ Tier**: More freedom with 1x models (5000/month), justify 10x usage for exceptional cases\n\n### 4. Integration Recommendations\n\n**Frontmatter Update Guidance**:\n\nIf file does not specify a `model` field:\n\n```markdown\n## Recommendation: Add Model Specification\n\nCurrent frontmatter:\n\\`\\`\\`yaml\n\n---\n\ndescription: \"...\"\ntools: [...]\n\n---\n\n\\`\\`\\`\n\nRecommended frontmatter:\n\\`\\`\\`yaml\n\n---\n\ndescription: \"...\"\nmodel: \"[Recommended Model Name]\"\ntools: [...]\n\n---\n\n\\`\\`\\`\n\nRationale: [Explanation of why this model is optimal for this task]\n```\n\nIf file already specifies a model:\n\n```markdown\n## Current Model Assessment\n\nSpecified model: `[Current Model]` (Multiplier: [X]x)\n\nRecommendation: [Keep current model | Consider switching to [Recommended Model]]\n\nRationale: [Explanation]\n```\n\n**Tool Alignment Check**:\n\nVerify model capabilities align with specified tools:\n\n- If tools include `context7/*` or `sequential-thinking/*`: Recommend advanced reasoning models (Claude Sonnet 4.5, GPT-5, Claude Opus 4.1)\n- If tools include vision-related references: Ensure model supports images (flag if GPT-5 Codex, Claude Sonnet 4, or mini models selected)\n- If tools are read-only (search, fetch): Suggest cost-effective models (GPT-5 mini, Grok Code Fast 1)\n\n### 5. Context7 Integration for Up-to-Date Information\n\n**Leverage Context7 for Model Documentation**:\n\nWhen uncertainty exists about current model capabilities, use Context7 to fetch latest information:\n\n```markdown\n**Verification with Context7**:\n\nUsing `context7/get-library-docs` with library ID `/websites/github_en_copilot`:\n\n- Query topic: \"model capabilities [specific capability question]\"\n- Retrieve current model features, multipliers, deprecation status\n- Cross-reference against analyzed file requirements\n```\n\n**Example Context7 Usage**:\n\n```\nIf unsure whether Claude Sonnet 4.5 supports image analysis:\n→ Use context7 with topic \"Claude Sonnet 4.5 vision image capabilities\"\n→ Confirm feature support before recommending for multi-modal tasks\n```\n\n## Output Expectations\n\n### Report Structure\n\nGenerate a structured markdown report with the following sections:\n\n```markdown\n# AI Model Recommendation Report\n\n**File Analyzed**: `[file path]`\n**File Type**: [chatmode | prompt]\n**Analysis Date**: [YYYY-MM-DD]\n**Subscription Tier**: [Free | Pro | Pro+]\n\n---\n\n## File Summary\n\n**Description**: [from frontmatter]\n**Mode**: [ask | edit | agent]\n**Tools**: [tool list]\n**Current Model**: [specified model or \"Not specified\"]\n\n## Task Analysis\n\n### Task Complexity\n\n- **Level**: [Simple | Moderate | Complex | Advanced]\n- **Reasoning Depth**: [Basic | Intermediate | Advanced | Expert]\n- **Context Requirements**: [Small | Medium | Large | Very Large]\n- **Code Generation**: [Minimal | Moderate | Extensive]\n- **Multi-Modal**: [Yes | No]\n\n### Task Category\n\n[Primary category from 8 categories listed in Workflow Phase 1]\n\n### Key Characteristics\n\n- Characteristic 1: [explanation]\n- Characteristic 2: [explanation]\n- Characteristic 3: [explanation]\n\n## Model Recommendation\n\n### 🏆 Primary Recommendation: [Model Name]\n\n**Multiplier**: [X]x ([cost implications for subscription tier])\n**Strengths**:\n\n- Strength 1: [specific to task]\n- Strength 2: [specific to task]\n- Strength 3: [specific to task]\n\n**Rationale**:\n[Detailed explanation connecting task characteristics to model capabilities]\n\n**Cost Impact** (for [Subscription Tier]):\n\n- Per request multiplier: [X]x\n- Estimated usage: [rough estimate based on task frequency]\n- [Additional cost context]\n\n### 🔄 Alternative Options\n\n#### Option 1: [Model Name]\n\n- **Multiplier**: [X]x\n- **When to Use**: [specific scenarios]\n- **Trade-offs**: [compared to primary recommendation]\n\n#### Option 2: [Model Name]\n\n- **Multiplier**: [X]x\n- **When to Use**: [specific scenarios]\n- **Trade-offs**: [compared to primary recommendation]\n\n### 📊 Model Comparison for This Task\n\n| Criterion        | [Primary Model] | [Alternative 1] | [Alternative 2] |\n| ---------------- | --------------- | --------------- | --------------- |\n| Task Fit         | ⭐⭐⭐⭐⭐      | ⭐⭐⭐⭐        | ⭐⭐⭐          |\n| Code Quality     | [rating]        | [rating]        | [rating]        |\n| Reasoning        | [rating]        | [rating]        | [rating]        |\n| Speed            | [rating]        | [rating]        | [rating]        |\n| Cost Efficiency  | [rating]        | [rating]        | [rating]        |\n| Context Capacity | [capacity]      | [capacity]      | [capacity]      |\n| Vision Support   | [Yes/No]        | [Yes/No]        | [Yes/No]        |\n\n## Auto Model Selection Assessment\n\n**Suitability**: [Recommended | Not Recommended | Situational]\n\n[Explanation of whether auto-selection is appropriate for this task]\n\n**Rationale**:\n\n- [Reason 1]\n- [Reason 2]\n\n**Manual Override Scenarios**:\n\n- [Scenario where user should manually select model]\n- [Scenario where user should manually select model]\n\n## Implementation Guidance\n\n### Frontmatter Update\n\n[Provide specific code block showing recommended frontmatter change]\n\n### Model Selection in VS Code\n\n**To Use Recommended Model**:\n\n1. Open Copilot Chat\n2. Click model dropdown (currently shows \"[current model or Auto]\")\n3. Select **[Recommended Model Name]**\n4. [Optional: When to switch back to Auto]\n\n**Keyboard Shortcut**: `Cmd+Shift+P` → \"Copilot: Change Model\"\n\n### Tool Alignment Verification\n\n[Check results: Are specified tools compatible with recommended model?]\n\n✅ **Compatible Tools**: [list]\n⚠️ **Potential Limitations**: [list if any]\n\n## Deprecation Notices\n\n[If applicable, list any deprecated models in current configuration]\n\n⚠️ **Deprecated Model in Use**: [Model Name] (Deprecation date: [YYYY-MM-DD])\n\n**Migration Path**:\n\n- **Current**: [Deprecated Model]\n- **Replacement**: [Recommended Model]\n- **Action Required**: Update `model:` field in frontmatter by [date]\n- **Behavioral Changes**: [any expected differences]\n\n## Context7 Verification\n\n[If Context7 was used for verification]\n\n**Queries Executed**:\n\n- Topic: \"[query topic]\"\n- Library: `/websites/github_en_copilot`\n- Key Findings: [summary]\n\n## Additional Considerations\n\n### Subscription Tier Recommendations\n\n[Specific advice based on Free/Pro/Pro+ tier]\n\n### Priority Factor Adjustments\n\n[If user specified Speed/Cost/Quality/Balanced, explain how recommendation aligns]\n\n### Long-Term Model Strategy\n\n[Advice for when to re-evaluate model selection as file evolves]\n\n---\n\n## Quick Reference\n\n**TL;DR**: Use **[Primary Model]** for this task due to [one-sentence rationale]. Cost: [X]x multiplier.\n\n**One-Line Update**:\n\\`\\`\\`yaml\nmodel: \"[Recommended Model Name]\"\n\\`\\`\\`\n```\n\n### Output Quality Standards\n\n- **Specific**: Tie all recommendations directly to file content, not generic advice\n- **Actionable**: Provide exact frontmatter code, VS Code steps, clear migration paths\n- **Contextualized**: Consider subscription tier, priority factor, deprecation timelines\n- **Evidence-Based**: Reference model capabilities from Context7 documentation when available\n- **Balanced**: Present trade-offs honestly (speed vs. quality vs. cost)\n- **Up-to-Date**: Flag deprecated models, suggest current alternatives\n\n## Quality Assurance\n\n### Validation Steps\n\n- [ ] File successfully read and parsed\n- [ ] Frontmatter extracted correctly (or noted if missing)\n- [ ] Task complexity accurately categorized (Simple/Moderate/Complex/Advanced)\n- [ ] Primary task category identified from 8 options\n- [ ] Model recommendation aligns with decision tree logic\n- [ ] Multiplier cost explained for user's subscription tier\n- [ ] Alternative models provided with clear trade-off explanations\n- [ ] Auto-selection guidance included (recommended/not recommended/situational)\n- [ ] Deprecated model warnings included if applicable\n- [ ] Frontmatter update example provided (valid YAML)\n- [ ] Tool alignment verified (model capabilities match specified tools)\n- [ ] Context7 used when verification needed for latest model information\n- [ ] Report includes all required sections (summary, analysis, recommendation, implementation)\n\n### Success Criteria\n\n- Recommendation is justified by specific file characteristics\n- Cost impact is clear and appropriate for subscription tier\n- Alternative models cover different priority factors (speed vs. quality vs. cost)\n- Frontmatter update is ready to copy-paste (no placeholders)\n- User can immediately act on recommendation (clear steps)\n- Report is readable and scannable (good structure, tables, emoji markers)\n\n### Failure Triggers\n\n- File path is invalid or unreadable → Stop and request valid path\n- File is not `.agent.md` or `.prompt.md` → Stop and clarify file type\n- Cannot determine task complexity from content → Request more specific file or clarification\n- Model recommendation contradicts documented capabilities → Use Context7 to verify current info\n- Subscription tier is invalid (not Free/Pro/Pro+) → Default to Pro and note assumption\n\n## Advanced Use Cases\n\n### Analyzing Multiple Files\n\nIf user provides multiple files:\n\n1. Analyze each file individually\n2. Generate separate recommendations per file\n3. Provide summary table comparing recommendations\n4. Note any patterns (e.g., \"All debug-related modes benefit from Claude Sonnet 4.5\")\n\n### Comparative Analysis\n\nIf user asks \"Which model is better between X and Y for this file?\":\n\n1. Focus comparison on those two models only\n2. Use side-by-side table format\n3. Declare a winner with specific reasoning\n4. Include cost comparison for subscription tier\n\n### Migration Planning\n\nIf file specifies a deprecated model:\n\n1. Prioritize migration guidance in report\n2. Test current behavior expectations vs. replacement model capabilities\n3. Provide phased migration if breaking changes expected\n4. Include rollback plan if needed\n\n## Examples\n\n### Example 1: Simple Formatting Task\n\n**File**: `format-code.prompt.md`\n**Content**: \"Format Python code with Black style, add type hints\"\n**Recommendation**: GPT-5 mini (0x multiplier, fastest, sufficient for repetitive formatting)\n**Alternative**: Grok Code Fast 1 (0.25x, even faster, preview feature)\n**Rationale**: Task is simple and repetitive; premium reasoning not needed; speed prioritized\n\n### Example 2: Complex Architecture Review\n\n**File**: `architect.agent.md`\n**Content**: \"Review system design for scalability, security, maintainability; analyze trade-offs; provide ADR-level recommendations\"\n**Recommendation**: Claude Sonnet 4.5 (1x multiplier, expert reasoning, excellent for architecture)\n**Alternative**: Claude Opus 4.1 (10x, use for very large codebases >500K tokens)\n**Rationale**: Requires deep reasoning, architectural expertise, design pattern knowledge; Sonnet 4.5 excels at this\n\n### Example 3: Django Expert Mode\n\n**File**: `django.agent.md`\n**Content**: \"Django 5.x expert with ORM optimization, async views, REST API design; uses context7 for up-to-date Django docs\"\n**Recommendation**: GPT-5 (1x multiplier, advanced reasoning, excellent code quality)\n**Alternative**: Claude Sonnet 4.5 (1x, alternative perspective, strong with frameworks)\n**Rationale**: Domain expertise + context7 integration benefits from advanced reasoning; 1x cost justified for expert mode\n\n### Example 4: Free Tier User with Planning Mode\n\n**File**: `plan.agent.md`\n**Content**: \"Research and planning mode with read-only tools (search, fetch, githubRepo)\"\n**Subscription**: Free (2K completions + 50 chat requests/month, 0x models only)\n**Recommendation**: GPT-4.1 (0x, balanced, included in Free tier)\n**Alternative**: GPT-5 mini (0x, faster but less context)\n**Rationale**: Free tier restricted to 0x models; GPT-4.1 provides best balance of quality and context for planning tasks\n\n## Knowledge Base\n\n### Model Multiplier Cost Reference\n\n| Multiplier | Meaning                                          | Free Tier | Pro Usage | Pro+ Usage |\n| ---------- | ------------------------------------------------ | --------- | --------- | ---------- |\n| 0x         | Included in all plans, no premium count          | ✅        | Unlimited | Unlimited  |\n| 0.25x      | 4 requests = 1 premium request                   | ❌        | 4000 uses | 20000 uses |\n| 0.33x      | 3 requests = 1 premium request                   | ❌        | 3000 uses | 15000 uses |\n| 1x         | 1 request = 1 premium request                    | ❌        | 1000 uses | 5000 uses  |\n| 1.25x      | 1 request = 1.25 premium requests                | ❌        | 800 uses  | 4000 uses  |\n| 10x        | 1 request = 10 premium requests (very expensive) | ❌        | 100 uses  | 500 uses   |\n\n### Model Changelog & Deprecations (October 2025)\n\n**Deprecated Models** (Effective 2025-10-23):\n\n- ❌ o3 (1x) → Replace with GPT-5 or Claude Sonnet 4.5 for reasoning\n- ❌ o4-mini (0.33x) → Replace with GPT-5 mini (0x) for cost, GPT-5 (1x) for quality\n- ❌ Claude Sonnet 3.7 (1x) → Replace with Claude Sonnet 4 or 4.5\n- ❌ Claude Sonnet 3.7 Thinking (1.25x) → Replace with Claude Sonnet 4.5\n- ❌ Gemini 2.0 Flash (0.25x) → Replace with Grok Code Fast 1 (0.25x) or GPT-5 mini (0x)\n\n**Preview Models** (Subject to Change):\n\n- 🧪 Claude Sonnet 4.5 (1x) - Preview status, may have API changes\n- 🧪 Grok Code Fast 1 (0.25x) - Preview, free during preview period\n\n**Stable Production Models**:\n\n- ✅ GPT-4.1, GPT-5, GPT-5 mini, GPT-5 Codex (OpenAI)\n- ✅ Claude Sonnet 3.5, Claude Sonnet 4, Claude Opus 4.1 (Anthropic)\n- ✅ Gemini 2.5 Pro (Google)\n\n### Auto Model Selection Behavior (Sept 2025+)\n\n**Included in Auto Selection**:\n\n- GPT-4.1 (0x)\n- GPT-5 mini (0x)\n- GPT-5 (1x)\n- Claude Sonnet 3.5 (1x)\n- Claude Sonnet 4.5 (1x)\n\n**Excluded from Auto Selection**:\n\n- Models with multiplier > 1 (Claude Opus 4.1, deprecated o3)\n- Models blocked by admin policies\n- Models unavailable in subscription plan (1x models in Free tier)\n\n**When Auto Selects**:\n\n- Copilot analyzes prompt complexity, context size, task type\n- Chooses from eligible pool based on availability and rate limits\n- Applies 10% multiplier discount on auto-selected models\n- Shows selected model on hover over response in Chat view\n\n## Context7 Query Templates\n\nUse these query patterns when verification needed:\n\n**Model Capabilities**:\n\n```\nTopic: \"[Model Name] code generation quality capabilities\"\nLibrary: /websites/github_en_copilot\n```\n\n**Model Multipliers**:\n\n```\nTopic: \"[Model Name] request multiplier cost billing\"\nLibrary: /websites/github_en_copilot\n```\n\n**Deprecation Status**:\n\n```\nTopic: \"deprecated models October 2025 timeline\"\nLibrary: /websites/github_en_copilot\n```\n\n**Vision Support**:\n\n```\nTopic: \"[Model Name] image vision multimodal support\"\nLibrary: /websites/github_en_copilot\n```\n\n**Auto Selection**:\n\n```\nTopic: \"auto model selection behavior eligible models\"\nLibrary: /websites/github_en_copilot\n```\n\n---\n\n**Last Updated**: 2025-10-28\n**Model Data Current As Of**: October 2025\n**Deprecation Deadline**: 2025-10-23 for o3, o4-mini, Claude Sonnet 3.7 variants, Gemini 2.0 Flash","tags":["model","recommendation","awesome","copilot","github","agent-skills","agents","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"capabilities":["skill","source-github","skill-model-recommendation","topic-agent-skills","topic-agents","topic-awesome","topic-custom-agents","topic-github-copilot","topic-hacktoberfest","topic-prompt-engineering"],"categories":["awesome-copilot"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/github/awesome-copilot/model-recommendation","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add github/awesome-copilot","source_repo":"https://github.com/github/awesome-copilot","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 33270 github stars · SKILL.md body (25,007 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:52:17.632Z","embedding":null,"createdAt":"2026-04-18T20:26:04.240Z","updatedAt":"2026-05-18T18:52:17.632Z","lastSeenAt":"2026-05-18T18:52:17.632Z","tsv":"'-10':1173,2694,2983,2995 '-2':1077 '-200':907 '-23':1174,2695,2996 '-28':2984 '-4.1':90,141,629,831,834,864,939,966,1010,1032,1186,2571,2595,2796,2831 '-5':92,94,97,143,146,643,658,673,824,839,845,856,870,885,891,894,912,941,968,997,1012,1026,1037,1188,1316,1334,1357,2379,2503,2580,2701,2716,2722,2763,2798,2800,2803,2834,2838 '/4.5':945 '/websites/github_en_copilot':1399,1883,2936,2947,2957,2968,2979 '0.25':761,777,1017,2393,2630,2751,2759,2785 '0.33':805,1019,2641,2711 '0x':168,173,178,630,645,962,978,1007,1182,1198,2381,2566,2572,2582,2592,2620,2718,2765,2832,2836 '1':120,156,230,301,776,829,861,973,1002,1076,1193,1362,1552,1556,1580,1627,1673,1728,1769,2244,2292,2330,2361,2392,2634,2645,2653,2655,2664,2674,2758,2784,2855 '1.25':2662,2666,2741 '10':2676,2898 '100':2681 '1000':174,975,2658 '1000/month':1202 '10x':729,983,989,1213,2450,2673 '128k':634,649,663,679,782,796,810 '15000':2650 '1m':733,766,917,926,934 '1x':659,675,688,702,716,742,792,980,987,1117,1201,1209,2439,2504,2515,2530,2652,2697,2723,2729,2774,2839,2843,2847,2871 '2':330,599,1559,1585,1646,1675,1730,1773,2249,2300,2336,2412 '2.0':115,758,1004,1157,2749,3007 '2.5':112,740,847,919,928,947,2817 '20000':2639 '200k':692,706,720,916 '200k-1m':915 '2025':137,1172,2689,2693,2825,2954,2982,2991,2994 '2k':163,2561 '2m':746,930 '3':356,1038,1562,1590,1783,2255,2308,2345,2473,2643 '3.5':101,149,687,944,2808,2842 '3.7':1155,2728,2739,3004 '3000':2648 '4':104,388,701,837,867,897,1035,1218,1338,1788,2261,2315,2353,2537,2632,2734,2811 '4.1':110,728,851,877,923,933,951,1029,1319,2449,2814,2858 '4.5':107,152,715,843,873,889,1024,1314,1429,1439,2275,2438,2468,2514,2705,2736,2747,2773,2846 '4000':2637,2671 '5':420,1363,2481 '50':165,906,2563 '500':2683 '5000':179,985,2660 '5000/month':1211 '500k':2456 '50k':901 '6':448 '7':477 '8':505,1546,2046 '800':2669 'absolut':191 'access':483,499 'accur':2038 'accuraci':566 'act':2159 'action':1855,1969 'ad':309 'add':326,1234,2374 'addit':1621,1887 'adjust':1900 'admin':2864 'adr':429,2432 'adr-level':2431 'advanc':506,523,577,662,666,705,721,745,797,868,1309,1517,1522,2233,2506,2528 'advic':1893,1914,1968 'agent':1498 'agent.md':35,83,187,241,2190 'ai':12,24,52,1467 'algorithm':513,530,683,799 'align':1291,1296,1805,1908,2050,2092 'alreadi':1264 'altern':1073,1078,1088,1624,1672,1674,2019,2063,2135,2388,2446,2511,2516,2578 'analysi':232,281,300,379,397,402,428,452,455,592,1052,1432,1479,1510,2114,2277 'analyz':4,34,201,253,444,472,1418,1472,2236,2245,2426,2880 'anthrop':2815 'api':339,487,502,2490,2779 'appli':603,2897 'applic':1827,2084 'approach':576 'appropri':1722,2131 'architect':381 'architect.agent.md':2417 'architectur':359,363,387,723,736,2414,2445,2462 'ask':1496,2280 'assess':447,1105,1271,1709 'assumpt':2232 'assur':2021 'async':2487 'auto':130,1102,1111,1133,1706,1719,1782,1795,2073,2820,2828,2850,2877,2903,2969,2972 'auto-select':129,1101,1132,1718,2072,2902 'avail':59,87,132,609,1998,2893 'avoid':982 'back':1793 'balanc':219,225,228,635,697,1030,1196,1999,2573,2598 'base':14,63,297,539,957,1049,1617,1894,1990,2607,2891 'basic':311,325,648,781,854,1520 'basic/intermediate/advanced/expert':264 'behavior':1864,2339,2823,2975 'benefici':587,1123 'benefit':2271,2526 'best':458,626,1047,2597 'better':2284 'bill':2945 'black':2372 'block':1755,2862 'bodi':254,545 'break':2350 'bug':394 'build':354 'calcul':535 'cannot':2198 'capabl':19,46,279,537,597,616,1295,1383,1403,1405,1442,1602,1993,2095,2214,2344,2927,2934 'capac':1697,1698,1699,1700 'case':1217,2235 'categor':289,2039 'categori':296,1542,1544,1547,2043 'caus':401 'chang':1759,1802,1865,2351,2770,2780 'changelog':2686 'characterist':66,313,342,371,403,431,463,489,522,1063,1554,1555,1558,1561,1599,2125 'chat':29,671,1772,2564,2914 'chat/month':166 'chatmod':5,1477 'check':462,1292,1807 'choos':1127,2887 'clarif':2209 'clarifi':2195 'claud':99,102,105,108,147,150,685,699,713,726,835,841,849,865,871,875,887,895,909,921,931,942,949,1022,1027,1033,1153,1312,1317,1336,1427,1437,2273,2436,2447,2512,2703,2726,2732,2737,2745,2771,2806,2809,2812,2840,2844,2856,3002 'clear':1977,2067,2129,2162 'click':1774 'cmd':1798 'code':118,135,265,331,348,449,621,665,680,693,708,722,774,827,859,881,971,1000,1191,1360,1531,1678,1754,1764,1973,1975,2370,2390,2509,2756,2782,2931 'code-specif':880 'codebas':735,2455 'codex':98,674,886,1335,2804 'comment':323 'comments/docstrings':310 'compar':1641,1660,2259,2276 'comparison':1665,2294,2318 'compat':1812,1816 'complet':164,2562 'complex':17,43,259,344,357,515,556,565,583,664,707,821,1512,1516,2037,2201,2413,2882 'complex/advanced':840 'complianc':461,475,496 'compon':375 'configur':1834 'confirm':1443 'connect':1597 'consid':1092,1283,1981 'consider':1177,1888 'content':255,299,1062,1965,2203,2367,2418,2479,2546 'context':157,274,284,317,410,435,624,696,749,898,1524,1623,1696,2586,2602,2883 'context7':579,1303,1364,1373,1385,1393,1422,1434,1869,1872,1995,2099,2216,2493,2524,2916 'context7/get-library-docs':1395 'contextu':1980 'contradict':2212 'convent':494 'convers':272 'copi':2152 'copilot':28,57,159,208,1126,1771,1801,2879 'copy-past':2151 'correct':2031 'cost':22,70,223,655,770,814,955,1006,1066,1100,1353,1573,1603,1622,1691,1942,2009,2056,2126,2145,2317,2531,2610,2720,2944 'cost-effect':654,769,1352 'cost-effici':21,69 'count':2627 'cover':2137 'creat':351 'creation':430 'criteria':606,2118 'criterion':1669 'critic':464,785,991 'cross':1415 'cross-refer':1414 'crud':312 'current':1144,1237,1269,1274,1281,1381,1408,1502,1777,1779,1833,1849,2018,2219,2338,2987 'data':288,516,756,2986 'date':127,1370,1480,1842,1863,2013,2498 'dd':1484,1846 'deadlin':2993 'debug':389,409,414,2268 'debug-rel':2267 'decis':438,817,1054,2052 'decision-mak':437 'declar':2309 'deep':372,490,2460 'default':214,226,2227 'dep':760 'deprec':126,772,791,804,815,879,1139,1147,1168,1171,1412,1824,1830,1835,1841,1850,1986,2015,2079,2328,2687,2690,2859,2948,2951,2992 'depth':263,853,1519 'descript':247,1240,1245,1492 'design':362,384,488,724,2421,2464,2491 'detail':1595 'determin':2199 'diagnos':417 'differ':1868,2138 'dimens':614 'direct':1962 'discount':2900 'django':498,2474,2480,2499 'django.agent.md':2478 'django/framework-specific':482 'doc':2500 'docstr':327 'document':427,446,1376,1996,2213 'domain':345,468,479,491,2522 'dr':1929 'dropdown':1776 'due':1936 'e.g':1169,2265 'edit':1497 'edit/editfiles':562 'effect':656,771,1354,2692 'effici':23,71,1692 'elig':2889,2976 'emoji':2172 'endpoint':340 'ensur':1327 'enterpris':711 'error':396,418 'estim':1613,1616 'evalu':601,611,1920 'even':2395 'evid':1989 'evidence-bas':1988 'evolv':1925 'exact':1971 'exampl':1421,2087,2359,2360,2411,2472,2536 'excel':661,677,690,691,704,718,744,2443,2469,2508 'except':1216 'exclud':153,1114,2848 'execut':319,568,1878 'exist':1379 'expect':1454,1867,2340,2352 'expens':2680 'expert':719,732,795,874,1523,2441,2475,2483,2534 'expertis':469,2463,2523 'explain':1064,1118,1905,2057 'explan':1084,1252,1289,1557,1560,1563,1596,1715,2071 'extens':1535 'extract':245,536,2030 'factor':994,1094,1899,1985,2140 'failur':2174 'fast':119,318,631,676,767,775,807,828,860,972,1001,1192,1361,2391,2757,2783 'faster':557,2396,2583 'fastest':646,763,779,2383 'featur':338,424,1410,1444,2398 'fetch':552,1350,1387,2557 'field':1231,1859 'file':8,38,86,190,199,231,237,244,1061,1143,1225,1263,1419,1471,1473,1475,1490,1924,1964,2024,2124,2176,2187,2196,2207,2238,2243,2247,2254,2291,2325,2365,2416,2477,2544 'filepath':184 'find':1885 'fit':1677 'fix':395,415 'flag':1141,1331,2014 'flash':116,759,1005,1158,2750,3008 'focus':2293 'follow':1464 'format':306,322,2307,2363,2368,2387 'format-code.prompt.md':2366 'framework':493,2520 'free':162,211,789,960,1178,1487,2538,2560,2576,2588,2614,2788,2874 'free/pro/pro':1896,2226 'freedom':1207 'freeli':988 'frequenc':1620 'frontmatt':246,543,1221,1238,1243,1494,1750,1758,1861,1972,2029,2085,2146 'functions/classes':336 'gather':436 'gemini':111,114,739,757,846,913,918,927,946,1003,1156,2748,2816,3006 'general':636 'generat':266,332,352,694,1040,1457,1532,2250,2932 'generic':1967 'github':56,158 'githubrepo':554,2558 'good':632,633,647,678,764,765,780,794,808,809,2169 'googl':2819 'gpt':89,91,93,96,140,142,145,628,642,657,672,823,830,833,838,844,855,863,869,884,890,893,911,938,940,965,967,996,1009,1011,1025,1031,1036,1185,1187,1315,1333,1356,2378,2502,2570,2579,2594,2700,2715,2721,2762,2795,2797,2799,2802,2830,2833,2837 'grok':117,773,826,858,970,999,1190,1359,2389,2755,2781 'guidanc':1104,1223,1749,2075,2333 'hint':2376 'honest':2004 'hover':2910 'id':1398 'identifi':257,292,1044,2044 'idiomat':347 'imag':280,591,1330,1431,1441,2963 'immedi':2158 'impact':1604,2127 'implement':333,337,350,1748,2116 'implic':1067,1574 'import':567 'includ':638,1085,1165,1302,1322,2076,2082,2109,2316,2354,2574,2621,2826 'individu':2248 'info':2220 'inform':1371,1389,2107 'input':79,181,183,203,217 'instruct':546 'integr':1219,1365,2525 'intermedi':862,1521 'invalid':2179,2224 'investig':419,445 'iter':575 'judici':981 'justifi':1212,2121,2532 'k':908 'keep':1280 'key':1553,1884 'keyboard':1796 'keyword':321,349,380,413,441,470,497,529 'knowledg':346,492,2466,2606 'larg':366,734,914,925,1528,1530,2454 'large-scal':365 'last':2980 'latest':1388,2105 'less':2585 'let':1125 'level':1513,2433 'leverag':1372 'librari':1397,1882,2935,2946,2956,2967,2978 'limit':1130,1820,2896 'line':1948 'list':1501,1548,1818,1821,1828 'logic':315,528,2054 'long':283,695,748,1910 'long-context':282 'long-term':1909 'lower':555,813,1015 'maintain':2425 'make':439 'manual':1120,1731,1738,1745 'markdown':1232,1268,1390,1460,1466 'marker':2173 'match':2096 'mathematical/algorithmic':525 'matrix':617 'may':2777 'mean':2613 'medium':905,1527 'might':1089 'migrat':1160,1847,1978,2322,2332,2348 'mini':95,124,144,644,803,825,857,969,998,1013,1152,1189,1340,1358,2380,2581,2710,2717,2764,2801,2835,3001 'minim':316,1533 'minimal/moderate/extensive':268 'miss':2035 'mission':33 'mm':1483,1845 'modal':590,752,1451,1538 'mode':30,248,1495,2270,2476,2535,2543,2550 'model':2,13,25,53,67,88,128,169,250,558,586,598,600,604,610,615,618,904,910,954,963,1008,1048,1079,1112,1116,1148,1184,1203,1210,1230,1235,1246,1248,1256,1267,1270,1273,1275,1282,1287,1294,1311,1328,1341,1355,1375,1382,1402,1409,1468,1503,1505,1564,1568,1601,1628,1647,1664,1671,1707,1740,1747,1760,1768,1775,1780,1786,1803,1815,1831,1836,1839,1851,1854,1858,1912,1921,1932,1951,1953,1992,2016,2048,2064,2080,2094,2106,2136,2210,2282,2298,2329,2343,2567,2593,2608,2685,2691,2767,2794,2821,2852,2861,2866,2872,2905,2908,2926,2929,2937,2940,2952,2961,2973,2977,2985 'model-recommend':1 'moder':343,564,660,689,703,717,743,832,1515,1534 'move':329 'multi':270,509,519,589,669,751,1450,1537 'multi-mod':588,750,1449,1536 'multi-phas':518 'multi-step':508 'multi-turn':269,668 'multimod':2965 'multipl':374,2237,2242 'multipli':155,619,1016,1065,1183,1276,1411,1570,1610,1630,1649,1945,2055,2382,2440,2505,2609,2612,2854,2899,2938,2943 'name':1249,1569,1629,1648,1787,1840,1954,2930,2941,2962 'need':267,276,412,574,2103,2358,2408,2925 'new':563 'note':1128,2033,2231,2262 'notic':1825 'o3':121,790,878,1149,1170,2696,2860,2998 'o4':123,802,1151,2709,3000 'o4-mini':122,801,1150,2708,2999 'octob':2688,2953,2990 'off':76,1640,1659,2003,2429 'one':1939,1947 'one-lin':1946 'one-sent':1938 'open':1770 'openai':2805 'oper':561 'optim':11,220,370,383,514,531,681,800,1258,2486 'option':60,202,1625,1626,1645,1789,2047 'opus':109,727,850,876,922,932,950,1028,1318,2448,2813,2857 'orm':2485 'output':1453,1955 'outstand':731 'overrid':1095,1732 'p':1800 'pars':236,2028 'past':2153 'path':80,185,196,1161,1474,1848,1979,2177,2186 'pattern':305,334,360,393,423,453,466,481,512,725,2264,2465,2922 'per':1608,2253 'perform':73,369,456,474 'period':2791 'perspect':2517 'phase':233,520,602,1041,1551,2347 'placehold':2155 'plan':421,425,442,641,2323,2356,2542,2549,2604,2624,2870 'plan.agent.md':2545 'polici':2865 'pool':2890 'potenti':1819 'practic':459 'precondit':78 'prefer':320,1091 'premium':154,585,1115,2405,2626,2635,2646,2656,2667,2677 'premium/month':175,180,976,986 'present':2000 'preview':788,2397,2766,2775,2787,2790 'primari':294,1042,1543,1566,1643,1662,1670,1931,2041 'priorit':977,2331,2410 'prioriti':221,993,1093,1898,1984,2139 'priorityfactor':218 'pro':113,171,176,205,212,213,216,741,848,920,929,948,974,984,1194,1204,1488,1489,2229,2616,2618,2818 'problem':391 'problem-solv':390 'product':2793 'prompt':7,32,1478,2881 'prompt.md':37,85,189,243,2192 'provid':61,1056,1159,1752,1970,2065,2088,2241,2256,2346,2430,2596 'purpos':42 'python':2369 'qualiti':224,451,622,1021,1098,1679,1956,2007,2020,2143,2510,2600,2725,2933 'queri':1400,1877,1880,2917,2921 'question':1406 'quick':652,1926 'rate':1680,1681,1682,1684,1685,1686,1688,1689,1690,1693,1694,1695,2895 'rational':62,1058,1251,1288,1594,1726,1941,2399,2458,2521,2587 're':1919 're-evalu':1918 'read':234,238,433,548,1347,2026,2553 'read-on':432,547,1346,2552 'readabl':2166 'readi':2149 'real':286,754 'real-tim':285,753 'reason':262,373,408,507,524,534,584,623,667,698,710,798,811,852,1310,1518,1683,1727,1729,2314,2406,2442,2461,2507,2529,2707 'recognit':467 'recommend':3,10,26,48,1039,1043,1074,1163,1180,1220,1233,1242,1247,1279,1286,1308,1447,1469,1565,1567,1644,1663,1711,1713,1757,1767,1785,1814,1853,1891,1907,1952,1961,2049,2115,2119,2161,2211,2252,2260,2377,2434,2435,2501,2569 'recommended/not':2077 'recommended/situational':2078 'refactor':308,358,368,382,682 'refer':593,1326,1416,1927,1991,2611 'relat':195,1325,2269 'renam':328 'repetit':303,2386,2404 'replac':1164,1852,2342,2698,2713,2730,2743,2753 'report':1455,1461,1470,2108,2164,2335 'request':1609,2184,2204,2633,2636,2644,2647,2654,2657,2665,2668,2675,2678,2942 'requests/month':2565 'requir':18,45,182,261,273,538,594,936,1420,1525,1856,2111,2459 'research':422,426,443,738,2547 'respons':653,768,2912 'rest':501,2489 'restrict':2590 'result':1808 'retriev':1407 'review':364,386,450,457,471,737,2415,2419 'robust':709 'rollback':2355 'root':400 'rough':1615 'runcommand':570 'runtask':572 'runtest':571 'scaffold':355 'scalabl':2423 'scale':367,385 'scannabl':2168 'scenario':1086,1637,1656,1733,1734,1741 'scope':77 'search':551,1349,2556 'section':1465,2112 'secur':454,473,2424 'select':131,138,605,816,1103,1113,1121,1134,1342,1708,1720,1739,1746,1761,1784,1922,2074,2822,2829,2851,2878,2904,2907,2970,2974 'sensit':956 'sentenc':1940 'separ':2251 'sept':136,2824 'sequenti':527,533,581,1306 'sequential-think':580,1305 'shift':1799 'shortcut':1797 'show':1756,1778,2906 'side':2303,2305 'side-by-sid':2302 'simpl':302,307,324,650,786,1514,2362,2402 'simple/moderate/complex/advanced':260,2040 'simple/repetitive':822 'singl':1046 'situat':1714 'size':899,2884 'skill' 'skill-model-recommendation' 'slow':730,793 'small':900,1526 'small/medium/large':277 'solv':392 'sonnet':100,103,106,148,151,686,700,714,836,842,866,872,888,896,943,1023,1034,1154,1313,1337,1428,1438,2274,2437,2467,2513,2704,2727,2733,2738,2746,2772,2807,2810,2841,2845,3003 'source-github' 'special':278,478 'specif':882,1057,1137,1236,1404,1581,1586,1591,1636,1655,1753,1892,1958,2123,2206,2313 'specifi':252,1145,1228,1265,1272,1298,1504,1508,1810,1903,2097,2326 'speed':222,620,784,995,1096,1687,2005,2141,2409 'speed-crit':783 'speed/cost/quality/balanced':1904 'stabl':2792 'standard':495,1957 'start':819 'status':1413,2776,2949 'step':405,407,510,1976,2023,2163 'step-by-step':404 'stop':2182,2193 'straightforward':314 'strategi':1913 'strength':68,1578,1579,1584,1589 'strong':2518 'structur':1456,1459,2170 'style':2373 'subject':2768 'subscript':160,209,1071,1175,1485,1576,1606,1889,1982,2061,2133,2221,2320,2559,2869 'subscriptionti':204,959 'success':2025,2117 'suffici':2384 'suggest':1075,1351,2017 'suitabl':51,559,1109,1710 'summari':1491,1886,2113,2257 'support':440,1329,1430,1445,1702,2959,2966 'switch':1284,1792 'system':361,2420 'systemat':398 'tabl':2171,2258,2306 'target':240 'task':16,65,258,290,295,304,480,637,651,684,712,787,820,992,1051,1107,1138,1261,1452,1509,1511,1541,1583,1588,1593,1598,1619,1668,1676,1725,1935,2036,2042,2200,2364,2400,2605,2885 'tdd':486,504 'templat':2918 'term':1911 'test':341,485,503,2337 'think':465,526,582,1307,2740 'tie':1059,1959 'tier':161,210,961,1072,1176,1179,1195,1205,1486,1577,1607,1890,1897,1983,2062,2134,2222,2321,2539,2577,2589,2615,2875 'time':287,755 'timelin':1166,1987,2955 'tl':1928 'token':902,2457 'tool':249,541,550,569,578,1241,1250,1290,1299,1301,1321,1344,1499,1500,1804,1811,1817,2091,2098,2555 'topic':1401,1436,1879,1881,2928,2939,2950,2960,2971 'topic-agent-skills' 'topic-agents' 'topic-awesome' 'topic-custom-agents' 'topic-github-copilot' 'topic-hacktoberfest' 'topic-prompt-engineering' 'trade':75,377,1082,1639,1658,2002,2069,2428 'trade-off':74,376,1081,1638,1657,2001,2068,2427 'transform':517,532 'tree':818,1055,2053 'trigger':2175 'troubleshoot':399,416 'turn':271,670 'two':2297 'type':291,1476,2197,2375,2886 'unavail':2867 'uncertainti':1378 'understand':40 'unlimit':172,177,1199,2628,2629 'unread':2181 'unsur':1425 'up-to-d':1367,2010,2495 'updat':1222,1751,1857,1949,2086,2147,2981 'usag':553,1214,1423,1614,2617,2619 'use':979,1384,1394,1433,1635,1654,1766,1838,1874,1930,2100,2215,2234,2301,2451,2492,2638,2640,2649,2651,2659,2661,2670,2672,2682,2684,2919 'user':206,1069,1736,1743,1902,2059,2156,2240,2279,2540 'valid':460,476,573,2022,2089,2185 'variant':3005 'verif':411,1391,1806,1870,1876,2102,2924 'verifi':1293,2093,2218 'view':2488,2915 'vision':596,625,935,1324,1440,1701,2958,2964 'vision-cap':595 'vision-rel':1323 'vs':134,1097,1099,1124,1763,1974,2006,2008,2142,2144,2341 'warn':1140,2081 'wcag':484,500 'whether':1426,1717 'window':275 'winner':2311 'workflow':229,511,521,1550 'workspac':194 'workspace-rel':193 'write':335,353,560 'x':762,778,806,1018,1020,1277,1278,1571,1572,1611,1612,1631,1632,1650,1651,1943,1944,2286,2394,2482,2631,2642,2663,2712,2742,2752,2760,2786 'y':2288 'yaml':1239,1244,1950,2090 'yes':883,937,1539 'yes/no':1703,1704,1705 'yyyi':1482,1844 'yyyy-mm-dd':1481,1843","prices":[{"id":"eb53979f-a5e8-4c46-bca9-013ae6a7a1ff","listingId":"3177b4a7-f56c-4c8e-a78c-6d831e78b66c","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"github","category":"awesome-copilot","install_from":"skills.sh"},"createdAt":"2026-04-18T20:26:04.240Z"}],"sources":[{"listingId":"3177b4a7-f56c-4c8e-a78c-6d831e78b66c","source":"github","sourceId":"github/awesome-copilot/model-recommendation","sourceUrl":"https://github.com/github/awesome-copilot/tree/main/skills/model-recommendation","isPrimary":false,"firstSeenAt":"2026-04-18T21:50:16.318Z","lastSeenAt":"2026-05-18T18:52:17.632Z"},{"listingId":"3177b4a7-f56c-4c8e-a78c-6d831e78b66c","source":"skills_sh","sourceId":"github/awesome-copilot/model-recommendation","sourceUrl":"https://skills.sh/github/awesome-copilot/model-recommendation","isPrimary":true,"firstSeenAt":"2026-04-18T20:26:04.240Z","lastSeenAt":"2026-05-07T22:40:18.638Z"}],"details":{"listingId":"3177b4a7-f56c-4c8e-a78c-6d831e78b66c","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"github","slug":"model-recommendation","github":{"repo":"github/awesome-copilot","stars":33270,"topics":["agent-skills","agents","ai","awesome","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"license":"mit","html_url":"https://github.com/github/awesome-copilot","pushed_at":"2026-05-18T01:26:59Z","description":"Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.","skill_md_sha":"d864639647267ba0fd9821a1be9c0a1e0049985a","skill_md_path":"skills/model-recommendation/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/github/awesome-copilot/tree/main/skills/model-recommendation"},"layout":"multi","source":"github","category":"awesome-copilot","frontmatter":{"name":"model-recommendation","description":"Analyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and cost-efficiency"},"skills_sh_url":"https://skills.sh/github/awesome-copilot/model-recommendation"},"updatedAt":"2026-05-18T18:52:17.632Z"}}