RLM REPL Environment

What problem does it solve?

This Skill provides a persistent Python REPL environment that enables recursive prompting and batched sub-LM queries, helping teams reason over large inputs without losing context.

Core Features & Use Cases

• Persistent context is exposed via a global context variable containing the original input.
• The llm_query(prompt) function enables recursive delegation to sub-LMs for chunked analysis.
• Signaling completion with FINAL() or FINAL_VAR() ensures explicit, verifiable outputs.
• Print statements reveal intermediate results with truncation to support iterative reasoning.
• The workflow supports batching and error-handling guidance to manage large contexts safely.

Quick Start

Start the REPL, inspect the available tools, and use llm_query() to delegate tasks in batches. When a result is ready, call FINAL() or FINAL_VAR() to emit the answer.