Delegate prompts to external LLMs like Gemini or Kimi via stdin.
npx skills add https://github.com/pablontiv/praxis --skill delegate-pablontiv
Please help me install this Agent Skill. Skill: delegate Source: https://github.com/pablontiv/praxis/tree/main/.claude/skills/delegate Command: npx skills add https://github.com/pablontiv/praxis --skill delegate-pablontiv
This Skill allows you to offload complex or lengthy tasks to other AI models like Gemini or Kimi, preserving Claude's token quota and leveraging specialized AI strengths.
Ask the delegate skill to use gemini to evaluate the tradeoffs of Flux CD versus ArgoCD for a small homelab Kubernetes cluster.
High-intent search queries and answers about installing and using this skill.
You can delegate tasks to Gemini or Kimi by sending direct prompts or file-based inputs via stdin. This preserves Claude's token quota while routing tasks to external models based on their specific strengths.
Yes, verification mode allows you to get a second opinion on Claude's work from another AI. You can delegate the existing output to an external model to cross-review and validate the analytical results.
Multi-LLM delegation intelligently routes tasks based on model strengths. It selects Gemini for deep analysis and Kimi for parallel research or tool usage, matching task characteristics like context window size to the appropriate model.
Yes, delegating large codebase security reviews to Gemini saves Claude tokens. The task processes entirely on the external model, leveraging its large context window for thorough analysis without consuming your local quota.
The best way to pass large files for multi-LLM delegation is through file-based input via stdin. This method transfers extensive data directly to the external model, avoiding manual prompt length limits and ensuring complete context delivery.
You should avoid LLM delegation for tasks requiring deep integration with your current local environment or when external models lack the necessary tool usage capabilities for your specific software engineering workflow.
WaterplanAIManages multi-account Google Workspace services via a CLI with orchestration and permissions.
ClaudioCeppi83Integrate Oracle engine AI into CLI workflows for prompt and file handling.
zachmayerOrchestrate parallel multi-model reviews across Codex, Gemini, and two Claude configurations.
majunbaoTranscribe local audio files to text using the Whisper CLI.
