Agent skill

vault-graph

Use when analyzing vault structure, finding orphan notes, discovering missing connections, identifying bridge concepts, or checking vault health from a graph perspective. Triggers on "vault graph", "map vault", "find orphans", "missing links", "vault structure", "knowledge graph".

majiayu000534★ · 1 repos on radarProfile →
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill vault-graph --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Allowed tools: BashReadAgentTodoWriteGrepGlob
Path: skills/analysis/vault-graph/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

<Purpose> Analyze the vault's wikilink structure as a directed graph. Computes PageRank (most influential concepts), betweenness centrality (bridge nodes connecting domains), orphan detection, cluster analysis, and missing-link discovery. Combines deterministic graph computation (Python/NetworkX) with intelligent interpretation (agent) to surface actionable insights. </Purpose> <Use_When> - User asks about vault structure, connections, or health - User wants to find orphan notes (unlinked, isolated) - User wants to discover missing connections between notes - User wants to identify the most important concepts in the vault - User asks "what should I link?" or "what's disconnected?" - As part of /health workflow for structural metrics - User says "map", "graph", "network", "connections", "orphans", "bridges" </Use_When> <Do_Not_Use_When> - User wants to search note CONTENT (use Grep/search_notes instead) - User wants to process a single note (use /process) - User wants tag analysis without graph structure (use /health) </Do_Not_Use_When> <Execution_Policy> - Run the Python script first — it handles all graph math deterministically - Pipe script output to the graph-analyst agent for i

What's inside
Steps it walks through
  1. Stage 1: RUN GRAPH ANALYSIS
  2. Stage 2: INTERPRET WITH AGENT
  3. Stage 3: PRESENT RESULTS
Ships with 1 file
  • metadata.json
Commands it runs
uv run "$SKILL_DIR/scripts/analyze_vault_graph.py" "." --top 20
More from claude-skill-registry
All skills →
About this skill
What does the vault-graph skill do?

Use when analyzing vault structure, finding orphan notes, discovering missing connections, identifying bridge concepts, or checking vault health from a graph perspective. Triggers on "vault graph", "map vault", "find orphans", "missing links", "vault structure", "knowledge graph".

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill vault-graph --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going