agentsclimarketplace

Obsidian graph traversal

Skill richfrem/agent-plugins-skills/plugins/obsidian-wiki-engine/skills/obsidian-graph-traversal

repo for reusable plugins and skills

Install
npx -y skills add richfrem/agent-plugins-skills --skill obsidian-graph-traversal

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Semantic link traversal for Obsidian Vaults. Builds an in-memory graph index from wikilinks and provides instant forward-link, backlink, and multi-degree connection queries. Use when exploring note relationships or finding orphaned notes.

SKILL.md

2.4 KB, as published. Nobody here has run it

Dependencies

This skill requires Python 3.8+ and standard library only. No external packages needed.

To install this skill's dependencies:

pip-compile ./requirements.in
pip install -r ./requirements.txt

See ./requirements.txt for the dependency lockfile (currently empty — standard library only).

Obsidian Graph Traversal

Status: Active Author: Richard Fremmerlid Domain: Obsidian Integration Depends On: obsidian-markdown-mastery (WP05, obsidian-parser)

Purpose

This skill transforms static vault notes into a queryable semantic graph. It answers questions like "What connects to Note X?" and "What are the 2nd-degree connections of Concept A?" — instantly, without rescanning the vault.

Performance Target: < 2 seconds for deep queries across 1000+ notes.

Available Commands

Build the Graph Index

python ./graph_ops.py build --vault-root <path>

Get Forward Links (outbound)

python ./graph_ops.py forward --note "Note Name"

Get Backlinks (inbound)

python ./graph_ops.py backlinks --note "Note Name"

Get N-Degree Connections

python ./graph_ops.py connections --note "Note Name" --depth 2

Find Orphaned Notes

python ./graph_ops.py orphans --vault-root <path>

Architecture

In-Memory Graph Index

  • On build, every .md file in the vault is parsed using the obsidian-parser
  • Wikilinks are extracted; embeds (![[...]]) are filtered out
  • A bidirectional adjacency map is built: {source: [targets], ...} and {target: [sources], ...}
  • The index is cached as .graph-index.json at the vault root
  • Invalidation uses file mtime — if a file changed since last build, only that file is re-indexed

The Primary Agent as Librarian

The graph index enables the agent to:

  • Detect blind spots: Orphaned notes indicate areas where agents act without historical context
  • Resolve conflicts: If two agents update the same note, the graph shows the impact radius
  • Enforce schema: Frontmatter metadata (status, trust_score) tracked across linked notes

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.