Agent skill · Business & Finance

model-configuration

AI model configuration patterns for this project. Single source of truth for model definitions. Triggers on "MODEL_CONFIG", "model", "pricing", "capabilities", "auto router", "gateway".

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill model-configuration-planetaryescape-blah-chat --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 9 KB
Bundled scripts: none
Path: skills/ai-llm/model-configuration-planetaryescape-blah-chat/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Model Configuration Single source of truth for AI model definitions. **Never hardcode model IDs as strings**. ## Critical Anti-Pattern ```typescript // ❌ NEVER DO THIS const response = await generateText({ model: "gpt-4", // Hardcoded string ... }); // ✅ ALWAYS DO THIS import { MODEL_CONFIG } from "@/lib/ai/models"; const response = await generateText({ model: getModel(MODEL_CONFIG["openai:gpt-5.1"].id), ... }); ``` ## MODEL_CONFIG Structure Every model has standardized config: ```typescript // From apps/web/src/lib/ai/models.ts "openai:gpt-5.1": { id: "openai:gpt-5.1", // Full model identifier provider: "openai", // Creator/vendor name: "GPT-5.1", // Display name description: "Latest flagship...", // Technical description contextWindow: 256000, // Max tokens pricing: { input: 1.25, // $/MTok input output: 10.0, // $/MTok output cached: 0.125, // $/MTok cached (optional) reasoning: 3.5, // $/MTok reasoning output (optional) }, capabilities: [ "thinking", // Extended reasoning "vision", // Image understanding "function-calling" // Tool use ], knowledgeCutoff: "November 2025", userFriendlyDescription: "...", // Plain-language for users bestFor: "...", // Use case guidance } ``` ##

What's inside
Steps it walks through
  1. Critical Anti-Pattern
  2. MODELCONFIG Structure
  3. AUTOMODEL Pattern
  4. Pricing Configuration
  5. Capabilities Flags
  6. Gateway Configuration
  7. Host Order Fallbacks
  8. Reasoning Config
  9. Pro Model Tier System
  10. Internal-Only Models
  11. Experimental Models
  12. Key Files
  13. Common Operations
  14. Adding a new model
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the model-configuration skill do?

AI model configuration patterns for this project. Single source of truth for model definitions. Triggers on "MODEL_CONFIG", "model", "pricing", "capabilities", "auto router", "gateway".

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill model-configuration-planetaryescape-blah-chat --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.

Keep going