cross-linking
について
クロスリンキングスキルは、双方向のウィキリンクを追加して相互接続された知識グラフを維持するためのガイダンスを提供します。このスキルは、コンテンツの作成や更新時に使用し、人物、プロジェクト、ツールなどの関連ページへのリンクを設定することで、情報の発見性を向上させます。具体的には、リンク対象の指定、構文の一貫性の強制、そして初出時にリンクを確実に追加することを定めています。
クイックインストール
Claude Code
推奨/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/cross-linkingこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストールします
ドキュメント
Cross-Linking
Maintain bidirectional links for discoverability and graph navigation.
What to Link
Always Link
| Content Type | Link To | Example |
|---|---|---|
| People | Person profile | [[Alice Smith]] not "Alice" |
| Projects | Project README | [[AGI-Assistant]] |
| Tasks | Task file | [[Integrate-Zep-Memory]] |
| Meetings | Meeting note | [[2026-01-12 Weekly Sync]] |
| Tools/Tech | Research entry | [[Zep]], [[LangChain]] |
On First Mention
Link concepts, tools, and references on their first appearance in a document.
Link Syntax
Basic Wikilink
[[Page Name]]
With Display Text
[[Page-Name|Display Text]]
[[Team/Alice-Smith|Alice]]
With Relative Path
[[../Team/Alice-Smith|Alice Smith]]
[[../../04-Knowledge/AI-Ecosystem/Zep|Zep]]
Finding Related Content
By Topic
Search for related pages in the same category:
- AI tools →
04-Knowledge/AI-Ecosystem/ - Projects →
03-Projects/ - Team →
01-Team/
By Tag
Find pages with similar tags:
#project/agi-assistant
#topic/ai
#team/member
By Existing Links
Check what the page already links to, then find related pages that should also be linked.
Linking Checklist
When creating/editing content:
- People mentioned? → Link to profiles in
01-Team/ - Projects referenced? → Link to project READMEs
- Tasks discussed? → Link to task files
- Tools/tech mentioned? → Link to AI-Ecosystem entries
- Related knowledge? → Link to relevant research pages
- Meetings referenced? → Link to meeting notes
Bidirectional Linking
Obsidian automatically creates backlinks, but for better navigation:
- Link from new page to existing related content
- Consider updating related pages to link back (for important connections)
Common Link Targets
Team
- Link to team member profiles in
Database/People/
Projects
- Link to project documentation in
Projects/orDatabase/Projects/
AI Ecosystem Categories
[[Agent-Frameworks]][[LLM-Providers]][[Developer-Tools]][[MCP-Ecosystem]][[Vector-Databases]]
Example
Before:
Alice is working on the authentication integration for our web app project.
After:
[[Alice Smith]] is working on the [[OAuth]] integration for our [[Web App]] project.
GitHub リポジトリ
関連スキル
content-collections
メタThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
creating-opencode-plugins
メタThis skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.
evaluating-llms-harness
テストThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
sglang
メタSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.