lat.md
1st1/lat.md
lat.md maintains a structured knowledge graph of a codebase using interconnected markdown files, linking design intent and architecture directly to source code and tests.
1.8k 114MITUpdated 2026-08-12
86
GreatOverview
This skill provides instructions and workflows for integrating lat.md into a repository to solve the scalability issues of flat documentation files like AGENTS.md. By establishing bi-directional links between markdown knowledge sections, source code symbols, and test specifications, agents and humans can maintain high-context design documentation, perform semantic searches, and enforce synchronization using the lat CLI and validation checks.
Capabilities
- ▸Knowledge graph management in markdown
- ▸Bidirectional code and documentation linking
- ▸Semantic and fuzzy search across project documentation
- ▸Test specification enforcement with code mention checks
- ▸Automated link and reference validation via CLI
Best for
Grounding AI coding agents in the actual architecture and design decisions of a project rather than relying on guesswork., Enforcing bidirectional traceability between architecture/test specifications in markdown and actual code implementations via @lat comments., Navigating and searching large codebases semantically or structurally using the lat CLI or MCP server integration.
Works with
Claude CodeCursorGitHub CopilotCodexChatGPTGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
86Task usefulness20%88 → +17.6
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%41 → +4.9
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%100 → +15.0
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%83 → +6.6
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 total86.2 / 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 tool can utilize hosted LLM API keys for remote embeddings if configured, but operates entirely offline by default using a local WebAssembly embedding model.
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.