Coordinate end-to-end RAG solutions across weave skills with weave-cli.
npx skills add https://github.com/Maximilien-ai/weave-cli-skills --skill weave-planner
Please help me install this Agent Skill. Skill: weave-planner Source: https://github.com/Maximilien-ai/weave-cli-skills/tree/main/skills/weave-planner Command: npx skills add https://github.com/Maximilien-ai/weave-cli-skills --skill weave-planner
Plan and orchestrate end-to-end RAG solutions across multiple weave skills, turning high-level requirements into a concrete execution plan.
Provide your RAG requirements and let weave-planner generate a full orchestration plan.
High-intent search queries and answers about installing and using this skill.
To plan an end-to-end RAG architecture, weave-planner coordinates requirements gathering, architecture design, and execution across weave-setup, weave-ingest, weave-search, weave-eval, and weave-stack. It transforms high-level requirements into a concrete orchestration plan with parallelism management and deployment guardrails.
Coordinating parallel workflows across RAG agents is managed by weave-planner through safe handoffs and parallelism management. It orchestrates multiple weave skills to enable concurrent execution while maintaining governance for lifecycle iteration and evaluation feedback.
Yes, you can use weave-planner to guide production deployment for RAG solutions. It provides governance for lifecycle iteration, evaluation feedback, and production deployment, ensuring safe transitions from architecture design to live environments.
To gather requirements for a RAG project, weave-planner orchestrates the collection of high-level needs and transforms them into a phased execution plan. This includes architecture decisions and coordination across setup, ingest, search, eval, and stack components.
Yes, weave-planner supports phased execution planning for RAG pipelines. It breaks down end-to-end solutions into distinct phases, managing parallelism and guardrails across weave-setup, weave-ingest, weave-search, weave-eval, and weave-stack for iterative development.
ouakarDocument production AI/ML stack usage, LLM calls, pipelines, and cost drivers.
ajmeyers42Generate validated ES|QL queries and synthetic datasets via Vulcan integration.
Maximilien-aiDeploy and manage RAG infrastructure stacks with weave-cli across local and cloud runtimes.
Tnemo65Design production-grade LLM systems for scalable, safe deployment.
