zeroapi
Route tasks to the best AI model across paid subscriptions (Claude, ChatGPT, Codex, Gemini, Kimi) via OpenClaw gateway. Use when user mentions model routing, multi-model setup, "use Codex for this", "delegate to Gemini", "route to the best model", agent delegation, or has OpenClaw agents configured with multiple providers. Do NOT use for single-model conversations or general chat.
Why use this skill?
Optimize your OpenClaw workflow with ZeroAPI. Intelligently route tasks across Claude, ChatGPT, Gemini, and Kimi to ensure your projects use the best AI for the job.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/dorukardahan/zeroapiWhat This Skill Does
ZeroAPI is the sophisticated routing engine for the OpenClaw AI ecosystem, designed to intelligently distribute tasks across your specific collection of AI subscriptions. Rather than relying on a single model for every request, ZeroAPI analyzes the nature of your input—whether it is code generation, complex reasoning, or rapid-fire data retrieval—and delegates the workload to the optimal provider, such as Claude, ChatGPT (Codex), Gemini, or Kimi.
This skill eliminates the 'one-size-fits-all' bottleneck. By maintaining a tiered architecture, ZeroAPI ensures that high-intelligence tasks are handled by Deep-tier models like Claude Opus 4.6, while simple queries are routed to ultra-fast Gemini Flash-Lite models, drastically improving your workflow efficiency and cost-effectiveness across your subscriptions.
Installation
To integrate ZeroAPI into your OpenClaw environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/dorukardahan/zeroapi
Once installed, the skill will initiate a setup wizard. Follow the prompts to audit your current AI subscriptions (Claude, ChatGPT, Gemini, Kimi). The skill will map your available services to the internal OpenClaw tiers. We strongly recommend running openclaw models status immediately after setup to verify that all API connections are active and authenticated before routing begins.
Use Cases
Use ZeroAPI when your workflow demands multi-model capabilities. Ideal scenarios include:
- Software Development: Routing complex debugging tasks to Codex, while using Kimi for multi-agent orchestration of file changes.
- Scientific Research: Assigning long-context data analysis to Gemini 3 Pro while using Claude for final report synthesis and logical reasoning.
- Automation Scaling: Automatically switching between low-latency models for simple chatbot pings and high-intelligence models for critical planning tasks.
Example Prompts
- "Route this architectural design request to the most intelligent reasoning model available."
- "Use Codex for this Python refactoring task and delegate the documentation generation to Gemini."
- "OpenClaw, setup a multi-model workflow where Claude handles the planning and Kimi manages the task execution."
Tips & Limitations
- Model Availability: If a model is marked as 'missing' or 'auth_expired' in
openclaw models status, ZeroAPI will automatically skip that tier. Ensure your environment variables are updated to keep routing paths open. - Avoid Over-Routing: Do not use this skill for simple, single-turn general conversations, as the classification overhead may introduce unnecessary latency.
- Benchmark Reliance: The routing logic is optimized based on standard benchmarks like SWE-bench and TAU-2. If you find a specific model is underperforming on your unique dataset, you may need to manually override the default assignment in the provider-config.md file.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-dorukardahan-zeroapi": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api
Related Skills
research-reprompter
Transform rough research questions into executable USACF research prompts. Use when user says "research", "research this", "investigate", "deep dive", "researcher", or pastes a research topic. Generates complete multi-agent swarm configuration with algorithm selection, claude-flow commands, and adversarial review.
ralph-security
Comprehensive security audit with 100 iterations (~30-60 min). Use when user says 'security audit', 'ralph security', 'weekly security check', 'audit this project', 'new project security review', or 'check for vulnerabilities'. Covers OWASP Top 10, auth, secrets, infrastructure, and code quality.
skeall
Agent Skills (SKILL.md) builder, auditor, and improver for cross-platform LLM agents. Use for "skeall", "build a skill", "create skill", "improve skill", "audit skill", "skill review", or any SKILL.md question. Follows agentskills.io standard.
humanizer-enhanced
Advanced AI text humanizer for blog content. Detects and removes 34 AI writing patterns, adds personality/soul, and handles crypto/Web3 specific tells. Use when user says /humanizer, "humanize this", "remove AI patterns", "make it sound human", or asks to clean up blog posts, articles, or drafts. Features: 28 base patterns from Wikipedia's "Signs of AI writing", 6 crypto/Web3 specific patterns, severity scoring (HIGH/MEDIUM/LOW), stat attribution fixer, soul/personality injection, batch mode.
traktor
Extract all assets and content from websites including images, SVGs, fonts, videos, and page structure. Parallel agents with thorough scraping coverage. Triggers: "extract assets", "scrape website", "download site assets", "get all images from", or "/traktor url". Supports multiple URLs.