← ClaudeAtlas

obsidian-graph-auditlisted

Diagnose Obsidian Graph view health and clean up over-connection — identify render-only edges (dashboards as topics, log files), mega-categories, broken refs, and false categories that are inflating the graph. Use whenever the user reports the graph feels tangled, overconnected, hairball-like, or noisy, even if they don't explicitly say "audit". Triggers include "why is my graph a hairball", "audit my graph", "graph cleanup", "find graph noise", "too many connections", "graph feels tangled", "what shouldn't be on the graph", "my graph is overconnected", "graph is a mess", "what to exclude from the graph", "why are unrelated notes connected".
lexbritvin/obsidian-skills-pack · ★ 2 · Data & Documents · score 75
Install: claude install-skill lexbritvin/obsidian-skills-pack
# Obsidian Graph Audit A diagnostic workflow for an Obsidian graph that feels tangled, overconnected, or visually noisy. Operates well on Kepano-style vaults (with `categories:` and `topics:` in frontmatter) but the patterns generalize. This skill **diagnoses and recommends**. It does not silently apply fixes. The deliverable is a report — pain points, ranked by impact, with proposed actions the user can approve, modify, or skip. Mitigation scripts exist (later in this file) but only run after the user explicitly confirms a specific action. Color tweaks and filter changes are out of scope — see the `obsidian-graph` skill for styling. ## When to use User says: - "Graph is a hairball / spaghetti / mess" - "Too many connections, can't read it" - "Why is X linked to Y? They aren't related" - "Help me clean up the graph" - "Find what's making the graph noisy" - "What should I exclude from the graph?" ## Prerequisites The diagnostic one-liners below use `rg` (ripgrep), `awk`, `find`, and `python3`. All are common on macOS and Linux except `rg`, which usually requires `brew install ripgrep` or equivalent. If `rg` is not available, substitute `grep -c` (for counts) or `grep -E` (for patterns) — slightly slower on large vaults but otherwise equivalent. ## Core insight A node draws visual attention proportional to its **degree** (number of edges). High-degree nodes are one of: - **Real semantic hubs** — coordinating concepts (epics, MOCs, topics-of-many-notes). Keep. - **Rende