skills.rest
adrianwedd
adrianweddCOMMUNITY
Explore all skills by this author →
Website𝕏@adrianweddGitHub

RLM (Recursive Language Model) Skill

Process arbitrarily long contexts via recursive language modeling with BM25 search.

1|Updated Jan 14, 2026
Search Tags:#document processing#code analysis#llm#context window#bm25#rlm#large documents
One-click install
npx skills add https://github.com/adrianwedd/rlm-mcp --skill rlm-recursive-language-model-skill
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: RLM (Recursive Language Model) Skill
Source: https://github.com/adrianwedd/rlm-mcp/tree/main/skills
Command: npx skills add https://github.com/adrianwedd/rlm-mcp --skill rlm-recursive-language-model-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the processing of documents that exceed standard language model context windows by employing a recursive, environment-based approach, allowing for analysis of arbitrarily large text inputs.

Core Features & Use Cases

  • Handles Large Contexts: Processes inputs far exceeding typical token limits.
  • Efficient Search & Chunking: Utilizes BM25 search and flexible chunking strategies for targeted analysis.
  • Session-based Management: Manages documents, artifacts, and analysis within a session.
  • Use Case: Analyze an entire codebase, a large corpus of research papers, or extensive log files that would otherwise be impossible to process due to size constraints.

Quick Start

Use the RLM skill to load all Python files in the 'src' directory and then search for all function definitions.

Frequently Asked Questions about RLM (Recursive Language Model) Skill

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

FAQPage Schema
How do I process large documents that exceed the LLM context window?▼

To process large documents exceeding the LLM context window, use recursive language model processing to treat prompts as external environment objects, enabling analysis of arbitrarily large text inputs.

How do I analyze an entire codebase when the file sizes hit token limits?▼

Analyzing an entire codebase past token limits requires on-demand chunking and BM25 search to extract targeted information, storing artifacts with span provenance for large-scale document analysis.

Does recursive language model processing support concurrent operations for large-scale document analysis?▼

Yes, recursive language model processing supports concurrent operations and session-based document management, making it suitable for production environments handling large-scale document analysis.

What is the best way to search for specific function definitions across a large corpus of research papers?▼

The best way to search across a large corpus of research papers is using BM25 search combined with flexible chunking strategies to isolate and retrieve targeted text spans for analysis.

When do I need span provenance and artifact storage for document processing?▼

You need span provenance and artifact storage when processing extensive log files or large documents recursively, ensuring traceable text origins and managed artifacts within a session.

Related Skills

Explore More Software Engineering Skills→
swyxioswyxio
154

summarize-anything

Summarize long-form text into 17 output formats using recursive map-reduce chunking.

Community
Intermediate
delta-and-betadelta-and-beta

analyst-data-export

Export Braze data from dashboard CSVs and Export API responses into analyzable datasets.

Community
Advanced
Yogi-076Yogi-076

prose

Orchestrate and execute OpenProse programs for multi-agent workflows.

Community
Advanced
brainqub3brainqub3
13

rlm

Execute recursive language model loops for long-context tasks via a local Python REPL.

Official
Advanced