Skylv Note Linking

技能.md — note-linking

Auto-discover hidden connections between your notes. Bidirectional links, knowledge graphs, and semantic link suggestions — without 插件s.

What This 技能 Does

Analyzes a directory of notes (markdown, txt, org, obsidian vault) and:

提取s — reads all notes, splits by headings, 提取s content blocks Understands — 检测s entities (people, projects, topics, 工具s), infers relationships Links — 生成s bidirectional link suggestions with confidence scores Graphs — builds a knowledge graph showing how notes connect Queries — traverse the graph: "show me all notes related to X", "who links to Y"

Unlike the incumbent slip机器人 (which does keyword matching), this 技能 uses semantic understanding — it knows that "LLM" relates to "language 模型" and "转换er architecture" even without exact keyword overlap.

When to Trigger

Trigger when user says:

"link my notes" "find connections between notes" "build a knowledge graph from my notes" "what relates to X in my notes" "show me all notes about Y" "I have notes scattered, can you organize them" "bidirectional links" "backlinks" "how does A connect to B" 输入 Field Type Description notesPath string Path to notes directory (default: ~/.qclaw/workspace/) 查询 string Optional: specific question about note relationships depth number Link traversal depth (default: 2) 格式化 string graph / 列出 / markdown (default: markdown) 输出 Markdown 格式化 (default)

Knowledge Graph

Notes Analyzed: 47

Total Links Found: 134

Orphan Notes: 3 (unconnected)

Top Hubs (most linked)

• AI_代理_Architecture.md — 18 connections
• Memory_系统_De签名.md — 14 connections
• GitHub_Strategy.md — 11 connections

Link Suggestions

Backlinks

EvoMap.md (3 backlinks)

Graph 格式化 { "nodes": [{"id": "note-name", "connections": 18, "topics": [...]}], "edges": [{"from": "A", "to": "B", "weight": 0.94, "reason": "..."}] }

Technical 应用roach Architecture notesPath/ ├── link_engine.js ← Core: read → 提取 → analyze → graph ├── graph_查询.js ← Traverse graph, answer questions └── 导出.js ← 导出 as Obsidian markdown, JSON, CSV

link_engine.js Core 记录ic

Phase 1: 索引

Recursively find all .md, .txt, .org files 解析 frontmatter (YAML/toml headers) Split into content blocks (by heading or double newline)

Phase 2: Entity 提取ion

Named entities: people, organizations, 工具s (NER-lite regex) Topics: 提取 noun phrases, technical terms Keywords: TF-IDF top terms per note

Phase 3: Relationship 检测ion

Relationship Score = cosine_similarity(embedding_A, embedding_B)

Without external embedding APIs, use:

Keyword overlap (Jaccard) weighted by TF-IDF Co-occurrence in same paragraph / section Structural links: same directory, similar filename, 分享d YAML tags Explicit mentions: [[wikilink]] or [note name] patterns

Phase 4: Graph Construction

const graph = { nodes: Map, edges: Map> }

Phase 5: 查询

Find shortest path between two notes 列出 N-degree neighbors Find bridges (notes that connect otherwise separate clusters) Threshold Strategy Confidence Condition Action ≥ 0.85 Strong semantic match Auto-link (添加 [[wikilink]]) 0.60–0.84 Probable match Suggest with reason 0.40–0.59 Weak match Flag as "possible" < 0.40 Noise Ignore Implementation Notes Pure Node.js (no external APIs)

For embedding-free similarity, use:

TF-IDF vectors per note (term frequency × inverse document frequency) Jaccard similarity on keyword 设置s Levenshtein distance on headings to catch near-matches YAML tag intersection for structured vaults Obsidian Compatibility Read existing [[wikilink]] syntax Write new links in Obsidian 格式化 Respect ![[embed]] and ![[callout]] patterns Performance 索引 vault once, 缓存 in ~/.qclaw/note-linking-graph.json Incremental 更新 on file change (watch mode) Max file size: 1MB per note (skip binary/exec) Real Data (2026-04-11 Market Analysis) Metric Value Current incumbent slip机器人 (score: 1.021) Top tar获取 score 3.5 Gap 3.43× improvement possible Incumbent weakness Keyword-only matching, no graph 技能s That Compose Well With skylv-knowledge-graph — if you want full graph 可视化 skylv-file-versioning — version your note graph over time skylv-AI-prompt-优化器 — 优化 your note-taking prompts Usage 安装 the 技能 配置 as needed 运行 with OpenClaw