Build LLM-powered agents with declarative **YAML or programmatic Python workflows.
npx skills add https://github.com/MadaraUchiha-314/sherma --skill sherma
Please help me install this Agent Skill. Skill: sherma Source: https://github.com/MadaraUchiha-314/sherma/tree/main/skills/sherma Command: npx skills add https://github.com/MadaraUchiha-314/sherma --skill sherma
sherma provides a unified framework to build LLM-powered agents using declarative YAML or programmatic Python, with multi-agent orchestration, skills, hooks, and A2A integration.
It enables rapid agent composition, tool loading from skills, human-in-the-loop interrupts, remote hooks, A2A communication, and flexible graph topologies for single or multi-agent systems.
Describe the agent you want to build, and I will generate a sherma workflow.
High-intent search queries and answers about installing and using this skill.
You can build multi-agent workflows with LLMs by defining agent compositions using declarative YAML or programmatic Python. This framework enables rapid construction of single or multi-agent systems with flexible graph topologies and tool loading from skills.
Yes, human-in-the-loop interrupts are supported natively for LLM agents. You can configure interrupt mechanisms within your declarative YAML or Python workflows to pause agent execution and await human input before proceeding.
A2A communication and remote hooks are fully supported by this agent framework. These integrations allow your LLM-powered agents to communicate with each other and trigger external remote hooks during multi-agent orchestration workflows.
The best way to orchestrate single and multi-agent systems with flexible graph topologies is by using a unified framework that supports declarative YAML definitions. This approach allows rapid agent composition, skill loading, and direct A2A integration.
Yes, a SKILL.md frontmatter containing a name and description is required to define agent workflows. You may also include optional scripts, references, and assets to further configure the behavior of your LLM-powered agents.
sigitpoerwoDefine and maintain agent skills with SKILL.md YAML frontmatter.
quanganh208Build modular AI agents with Google ADK Python for orchestration and multi-agent coordination.
jonnabioBuild LLM-powered applications with RAG, tool calling, and memory management.
NicolaiLassenBuild multi-agent orxhestra trees from declarative YAML configuration.
