Claudish Integration Skill

Query Claudish for OpenRouter model recommendations in JSON.

278|29|Updated Nov 4, 2025
One-click install
npx skills add https://github.com/MadAppGang/claude-code --skill claudish-integration-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Claudish Integration Skill
Source: https://github.com/MadAppGang/claude-code/tree/main/skills/claudish-integration
Command: npx skills add https://github.com/MadAppGang/claude-code --skill claudish-integration-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides standardized patterns for Claude Code agents and commands to query Claudish for OpenRouter model recommendations. Instead of maintaining duplicate model lists, agents should query Claudish as the single source of truth for model data.

Core Features & Use Cases

  • Pattern 1: Query All Models (JSON) to get a complete model list
  • Pattern 2: Filter by Category to fetch coding/reasoning/vision models
  • Pattern 3: User Overrides from CLAUDE.md to customize recommendations
  • Pattern 4: Graceful Fallback to Embedded Defaults if Claudish is unavailable
  • Pattern 5: Version Detection to ensure JSON output support

Quick Start

Use Claudish for dynamic model selection when performing code reviews or proxy-model tasks; fetch top models in JSON and pick the best fit.

Frequently Asked Questions about Claudish Integration Skill

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

FAQPage Schema
How do I query OpenRouter models dynamically instead of maintaining hardcoded lists?

Query Claudish to retrieve OpenRouter model recommendations as a single source of truth. Claudish provides JSON output with model metadata including pricing, categories, and context sizes, eliminating duplicate model maintenance across agents.

Can I filter OpenRouter models by category like coding or reasoning?

Yes. Claudish supports category filtering to fetch specialized model subsets. Query by category parameter to retrieve only coding, reasoning, vision, or other categorized models matching your agent's requirements.

What happens if Claudish is unavailable when my agent requests models?

The Skill provides graceful fallback to embedded defaults. Agents automatically revert to hardcoded model lists if Claudish is unreachable, ensuring command-driven workflows continue uninterrupted.

How do I override model recommendations for my specific workflow?

Define custom model selections in CLAUDE.md. User overrides take precedence over Claudish defaults, allowing agents to respect local preferences while maintaining dynamic discovery for unmapped models.

Does this work with multi-model validation workflows that need model metadata?

Yes. The Skill supports command-driven agents performing proxy delegation and multi-model validation. Retrieve model metadata via Claudish JSON to compare pricing, context sizes, and capabilities across models.

How do I ensure my agent's Claudish integration supports JSON output?

Use version detection to verify JSON output support before querying. The Skill includes version checks to confirm Claudish compatibility, preventing failures from outdated or incompatible API versions.