rlm-skill

Community

Process massive docs beyond context with RLM.

Authordanielsimonjr
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables processing content that exceeds traditional language model context windows by loading data into a Python runtime, chunking intelligently, and synthesizing results across chunks.

Core Features & Use Cases

  • Auto-chunking detects document structure (markdown headers, code blocks, JSON) and selects an optimal chunking strategy.
  • Pre-filtering with keyword/regex reduces unnecessary LLM calls before processing chunks.
  • Hierarchical aggregation recursively combines results to enable analysis of very large contexts, including directories and codebases.
  • Multi-format ingestion supports PDF, DOCX, HTML, JSON/JSONL, CSV, YAML, XML, archives, and 30+ code/text extensions.
  • Directory processing enables cross-file analysis and coherent summaries across many files.

Quick Start

Run the RLM processor on a large file, for example: python rlm_processor.py path/to/large_document.txt "What are the key findings?"

Dependency Matrix

Required Modules

pdfplumberpython-docxbeautifulsoup4PyPDF2

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: rlm-skill
Download link: https://github.com/danielsimonjr/claude-skills/archive/main.zip#rlm-skill

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.