Agent SkillsAgent Skills
NeverSight

gemini-rlm-min

@NeverSight/gemini-rlm-min
NeverSight
123
27 forks
Updated 5/2/2026
View on GitHub

Minimal implementation of Recursive Language Models (RLM) using Gemini 2.0 Flash and a local Python REPL. Enables processing of massive contexts via the Gemini CLI.

Installation

$npx agent-skills-cli install @NeverSight/gemini-rlm-min
Claude Code
Cursor
Copilot
Codex
Antigravity

Details

RepositoryNeverSight/skills_feed
Pathdata/skills-md/starwreckntx/irp__methodologies-/gemini-rlm-min/SKILL.md
Branchmain
Scoped Name@NeverSight/gemini-rlm-min

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

npx agent-skills-cli list

Skill Instructions

name: gemini-rlm-min description: Minimal implementation of Recursive Language Models (RLM) using Gemini 2.0 Flash and a local Python REPL. Enables processing of massive contexts via the Gemini CLI. version: 1.0.0 category: cross-model allowed-tools:

  • Read
  • Write
  • Edit
  • Bash triggers:
  • "gemini rlm"
  • "gemini context"
  • "large document gemini"
  • "gemini cli"

Gemini RLM (Minimal)

Purpose: Provide a lightweight, CLI-based implementation of the Recursive Language Model architecture using Google's Gemini models. This skill allows for processing extremely large documents by orchestrating chunking, sub-LLM processing, and synthesis entirely via a Python script and the Gemini API.

Architecture

Based on arXiv:2512.24601 - Recursive Language Models.

ComponentImplementationModel
Root LLMgem_rlm.py (Orchestrator)Gemini 2.0 Flash
Sub-LLMgem_rlm.py (Chunk Processor)Gemini 2.0 Flash
External Environmentscripts/rlm_repl.pyPython 3

Prerequisites

  • Environment Variable: GEMINI_API_KEY must be set in your shell environment. 
    export GEMINI_API_KEY="your_api_key_here"

Usage

The primary entry point is the gem_rlm.py script.

Syntax

${SKILLS_ROOT}/gemini-rlm-min/gem_rlm.py --context <path_to_large_file> --query <"your query"> [options]

Options

  • --chunk-size: Size of chunks in characters (default: 50000)
  • --overlap: Overlap between chunks in characters (default: 0)

Examples

Analyze a large log file:

export GEMINI_API_KEY="AIza..."
${SKILLS_ROOT}/gemini-rlm-min/gem_rlm.py --context ./large_logs.txt --query "Identify all security exceptions and their timestamps"

Summarize a book:

${SKILLS_ROOT}/gemini-rlm-min/gem_rlm.py --context ./mobydick.txt --query "Summarize the relationship between Ahab and Starbuck" --chunk-size 100000

How It Works

  1. Initialization: The script initializes a persistent Python REPL (rlm_repl.py) and loads the large context file into memory.
  2. Chunking: The context is split into manageable chunks (e.g., 50k chars) using the REPL.
  3. Sub-LLM Processing: The script iterates through each chunk, sending it to gemini-2.0-flash-exp with a prompt to extract relevant information.
  4. Synthesis: The extracted findings from all chunks are aggregated and sent to the Root LLM (also Gemini 2.0 Flash) to generate the final answer.

File Structure

gemini-rlm-min/
β”œβ”€β”€ SKILL.md              # This definition file
β”œβ”€β”€ gem_rlm.py            # Main CLI Orchestrator
β”œβ”€β”€ scripts/
β”‚   └── rlm_repl.py       # Persistent REPL environment
└── state/                # Runtime state storage (chunks, pickle files)

Integration with IRP

This skill serves as a high-speed, low-overhead alternative to the full rlm-context-manager when:

  • Quick analysis is needed via CLI.
  • The context needs to be processed entirely by Gemini models.
  • Minimal dependencies are preferred (no complex agent setup required).

More by NeverSight

View all
eresidency
124

Guide remote founders through Estonian e-Residency, company formation, banking, accounting, and getting paid with stablecoins.

seo
124

Master SEO orchestrator with 23 specialized sub-skills across 8 categories. Comprehensive SEO analysis for any website or business type. Performs full site audits, single-page deep analysis, technical SEO checks (crawlability, indexability, Core Web Vitals with INP), schema markup, content quality (E-E-A-T framework), image optimization, sitemap analysis, site architecture planning, AI search optimization (GEO for ChatGPT, Perplexity, AI Overviews), backlink analysis, keyword research, SERP tracking, and AI visibility monitoring. Industry detection for SaaS, e-commerce, local business, publishers, agencies. Triggers on: "SEO", "audit", "schema", "Core Web Vitals", "sitemap", "E-E-A-T", "AI Overviews", "GEO", "technical SEO", "content quality", "page speed", "structured data", "site architecture", "metadata", "AI SEO", "backlinks", "link building", "keywords", "keyword research", "SERP", "AI visibility".

youmind-image-generator
124

Generate AI images from text prompts β€” one API key for GPT Image, Gemini, Seedream, and 10+ models. No juggling subscriptions. Images saved to your YouMind knowledge board. Use when user wants to "generate image", "create image", "AI image", "text to image", "η”Ÿζˆε›Ύη‰‡", "AI η”Ÿε›Ύ", "η”»εƒη”Ÿζˆ", "GPT image", "Gemini image", "Seedream", "DALL-E", "Midjourney".

seo-content
124

Content optimization for SEO: on-page scoring (0-100), E-E-A-T analysis, title/meta optimization, heading structure, keyword density, SERP preview, content readability, featured snippet optimization, content gap and decay detection, pre-publish checklists. USE FOR: - "optimize this page", "content score", "on-page SEO", "page score" - "title tag", "meta description", "heading structure" - "E-E-A-T", "content quality", "content audit" - "pre-publish checklist", "before I publish" - "content gap", "what content should I create" - "keyword density", "content optimization" - "SERP preview", "how does this look in Google" - "featured snippet", "position zero" - "content decay", "stale content", "refresh content" - "readability", "Flesch-Kincaid" Uses firecrawl to scrape pages for analysis. Multi-client: stores results in .seo/clients/{client}/content/