Claude Hemat
Skill by axellageraldinc
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/axellageraldinc/claude-hematWhat This Skill Does
Claude Hemat is an intelligent model orchestration skill for OpenClaw that optimizes task performance by dynamically selecting the appropriate Anthropic Claude model. It implements a hierarchical decision-making framework, ensuring that simple tasks are handled by the efficient Haiku 4.5, while complex analytical, coding, and reasoning tasks are escalated to the more powerful Sonnet 4.5 and Opus 4.6 models via the sessions_spawn command. This skill acts as a traffic controller, minimizing latency and cost while maximizing output quality.
Installation
To integrate Claude Hemat into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/axellageraldinc/claude-hemat
Use Cases
- Automated Workflow Routing: Automatically determines if a request requires rapid response (Haiku) or deep analytical synthesis (Opus).
- Development Assistance: Uses Sonnet 4.5 for complex code generation, debugging, and software architectural planning.
- Complex Research: Employs Opus 4.6 to handle multifaceted queries requiring deep reasoning, long-form content generation, or critical decision support.
- Reporting & Analysis: Utilizes Sonnet 4.5 to break down data into insights, comparative reports, and logical explanations.
Example Prompts
- "Look up the current status of the project server and report back quickly." (Haiku 4.5)
- "Analyze this provided codebase, explain the bottlenecks in the data ingestion module, and rewrite the logic for better performance." (Sonnet 4.5)
- "Conduct an exhaustive research study on global market trends for renewable energy in 2025 and provide a critical analysis of investment risks." (Opus 4.6)
Tips & Limitations
- Model Defaults: Always remember that Haiku 4.5 is the fallback. Avoid forcing Sonnet or Opus for simple tasks to keep operational speed high.
- Transparency: The skill requires clear output of the model currently in use. Ensure your system prompts accommodate this reporting requirement.
- Limitations: Do not attempt coding or heavy reasoning with Haiku 4.5; the skill is programmed to escalate these tasks to maintain output integrity. Always revert to the default model after completing specialized tasks to ensure resource efficiency.
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-axellageraldinc-claude-hemat": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: code-execution, external-api