One-click install
npx skills add https://github.com/skytiger6724/qwen-skills --skill zeroapi-skytiger6724
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: zeroapi
Source: https://github.com/skytiger6724/qwen-skills/tree/main/zeroapi
Command: npx skills add https://github.com/skytiger6724/qwen-skills --skill zeroapi-skytiger6724

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ZeroAPI removes the manual guesswork of picking the best available LLM model for each task, eliminating wasted time and suboptimal responses while keeping throughput high.

Core Features & Use Cases

  • Automated Routing Logic: A nine-step decision tree matches SIMPLE, FAST, RESEARCH, CODE, DEEP, and ORCHESTRATE tiers to task intent and token demands.
  • Resilient Fallbacks: Follows a fallback chain when a provider is rate limited and keeps Gemini 3 Pro locked in for over 100k token workloads.
  • Operations Commands: /zeroapi status, /zeroapi sync, and /zeroapi mode <auto|manual> keep routing rules, tokens, and manual overrides transparent and controllable.
  • Use Case: Let ZeroAPI steer a mixed workload containing simple formatting, deep research, and code generation without manual provider switching.

Quick Start

Ask zeroapi to analyze the incoming request and route it automatically to the most capable model tier.

Frequently Asked Questions about zeroapi

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

FAQPage Schema
How do I automate LLM model routing for mixed workloads?

Automated LLM model routing analyzes incoming requests and matches them to the appropriate model tier using a nine-step decision tree, evaluating task intent and token demands to eliminate manual selection. This ensures optimal throughput for mixed workloads.

What happens to API requests when a provider is rate limited?

When a provider is rate limited, API requests follow a resilient fallback chain to the next available model. The system maintains continuous availability and automatically refreshes provider tokens to prevent workflow interruptions.

Can I force a specific model for high-token workloads?

Yes, context-aware triggers automatically enforce specific model locks for high-token requests. The system locks in advanced models for workloads exceeding 100k tokens to handle extensive context requirements without manual intervention.

How do I check API health and manage manual overrides?

You can check API health and manage manual overrides using operations commands like `/zeroapi status` and `/zeroapi mode manual`. These commands keep routing rules, provider tokens, and manual overrides transparent and controllable.

Does automated model selection work for code generation and deep research?

Automated model selection applies across multi-model deployments requiring automatic tier selection for coding, research, and reasoning workloads. It steers mixed workloads containing simple formatting, deep research, and code generation without manual provider switching.