long-context

Name: long-context
Availability: InStock
Author: qredence

Chunk large documents and codebases for Daytona RLM workspace processing.

51|6|Updated Feb 7, 2026

Search Tags:#context #delegation #sandbox #chunking #dspy #rlm

Ready to run

npx skills add https://github.com/Qredence/fleet-rlm --skill long-context-qredence

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: long-context
Source: https://github.com/Qredence/fleet-rlm/tree/main/src/fleet_rlm/scaffold/skills/long-context
Command: npx skills add https://github.com/Qredence/fleet-rlm --skill long-context-qredence

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Process documents and codebases exceeding a single context window using canonical dspy.RLM variable mode in the Daytona REPL.

Core Features & Use Cases

Large-input chunking and context routing to appropriate sandboxes for heavy tasks.
Optional pre-chunking and semantic chunking to preserve structure and relevance.
Guardrails and reusable patterns for exact quote retrieval and delegated RLM workflows.

Quick Start

Chunk a large document or codebase into bounded pieces and route processing through the Daytona RLM sandbox.

Frequently Asked Questions about long-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I process large codebases that exceed LLM context window token limits?▼

To process large codebases exceeding context limits, you can chunk documents into bounded pieces and route processing through a sandbox. This enables staged execution by delegating tasks to fit within workspace constraints.

What is semantic chunking for long-form documents?▼

Semantic chunking for long-form documents splits large inputs into bounded pieces while preserving structural relevance. This allows staged processing of text that exceeds token limits without losing contextual meaning.

Can I use dspy.RLM variable mode for delegated processing in a sandbox?▼

Yes, dspy.RLM variable mode is supported for delegated processing within a sandbox environment. It provides guardrails and reusable patterns for safe, traceable execution of routed tasks.

What's the best way to retrieve exact quotes from documents that exceed context limits?▼

The best way to retrieve exact quotes from oversized documents is applying pre-chunking strategies with guardrails. This delegates retrieval tasks to bounded pieces within the workspace for traceable results.

Does chunking large inputs require a specialized workspace environment?▼

Chunking large inputs requires routing to an appropriate workspace for heavy tasks. The Daytona RLM workspace provides the necessary sandboxing environment to execute delegated processing safely.