#
ENJA

llm-wiki-compiler

atomicstrata/llm-wiki-compiler

A knowledge compiler CLI tool that transforms raw source documents into interlinked, citation-traceable markdown wikis for humans and AI agents.

1.9k 190MITUpdated 2026-08-12

Overview

The llm-wiki-compiler implements the Karpathy LLM Wiki pattern by moving knowledge extraction from query time to compile time. It features configurable lifecycle profiles, hybrid retrieval, built-in trust gates, a local viewer, and MCP integration to manage persistent, auditable knowledge bases.

Capabilities

  • Raw source to structured wiki compilation
  • Configurable Lifecycle Profiles (CLP) with custom entities and relations
  • Hybrid semantic and BM25 retrieval with graph expansion
  • Model Context Protocol (MCP) server integration
  • Built-in health evaluation, linting, and freshness repair
  • Multiple export formats including JSON-LD, GraphML, Marp, and llms.txt

Best for

Compile research papers, notes, PDFs, and web pages into typed, interlinked wiki pages., Expose compiled knowledge bases to AI agents through an MCP server with citation tracing., Maintain audit-ready project documentation with automated linting, freshness checks, and review queues.

Works with

Claude CodeCursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
85
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%100 → +15.0

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%35 → +4.2

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%84 → +6.7

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

Compatibility5%100 → +5.0

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 total84.9 / 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

The skill operates locally and compiles user-provided source files into markdown wikis. It interacts with local file systems and external LLM providers based on user configuration.

Categories

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.