Stats
Actions
Tags
From llm-rail
Execute an LLM Rail workflow end-to-end — validate, create, and run all steps automatically
How this skill is triggered — by the user, by Claude, or both
Slash command
/llm-rail:runThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the orchestrator. You validate, create, and launch a single agent to execute the entire workflow instance.
You are the orchestrator. You validate, create, and launch a single agent to execute the entire workflow instance.
Parse $ARGUMENTS as: <workflow-name> [--param key=value ...]
Example: code-review --param target=src/
Run lrail docs workflow/execution and follow the "Orchestration" section:
For agent selection, run lrail docs concepts/step-types and read "Agent Selection".
For general-purpose agents, include the full lrail command syntax (start, next, bash) in the prompt since they don't have built-in lrail knowledge. Reference lrail docs workflow/execution for the exact commands and flow.
npx claudepluginhub neuradex/llm-rail --plugin llm-railValidates, runs, and debugs multi-agent YAML workflows. Use when orchestrating AI agents, configuring routing, or setting up human-in-the-loop gates.
Executes orchestration workflows using -> || ~> syntax with real-time ASCII visualization, interactive steering at checkpoints, error recovery, and resume from .orchestration/state.json.
Authors a reusable, deterministic agent orchestration workflow as a self-contained .mjs script for Claude Code's Workflow tool, with structured phases, fan-out, and verification.