#
ENJA

rlm

MCP Server

richardwhiteii/rlm

The Recursive Language Model (RLM) pattern enables processing massive contexts exceeding standard token limits by recursively chunking, processing via sub-queries, and aggregating results.

49 6MITUpdated 2026-04-21
View on GitHubOpen source file

Overview

This skill provides a structured workflow for handling files over 100KB, multi-file codebases, or large log files by managing them as external variables. It utilizes map-reduce, filtering, and hierarchical processing techniques through dedicated MCP tools, leveraging either the Claude SDK (Haiku 4.5) or local Ollama instances for scalable execution.

Capabilities

  • ▸Load large datasets and texts into isolated context memory
  • ▸Inspect context structure and preview contents safely
  • ▸Chunk data using line, character, or paragraph strategies
  • ▸Filter contexts using regular expressions
  • ▸Perform single or parallel batch sub-queries using Claude SDK or Ollama
  • ▸Store and aggregate intermediate analysis results

Best for

Analyzing massive codebases or multiple files simultaneously, Processing and summarizing multi-megabyte log files for error patterns, Extracting specific insights or answering questions across large research document sets

Works with

Claude Code
Evoa Score breakdown= Σ (score × weight)
74
Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%70 → +10.5

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%36 → +4.3

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%45 → +3.6

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total73.7 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

Processes large user files locally or via the configured provider API. Ensure sensitive internal files are sent only to trusted providers or processed locally via Ollama.

Categories

CodingData ScienceResearchAutomation

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.