Skip to content
SkillModel-led3,819 tokens in use

cross-linker

Finds pages in an Obsidian wiki that mention each other without linking, scores the candidates, and inserts wikilinks with typed relationships.

3,792 stars on the repository MIT LicenseAr9av/obsidian-wiki · skills/cross-linker
pip install obsidian-wiki
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing cross-linker costs

42tokens idle
3,819tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectedgitdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size11/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 100

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity28
  • Momentum40

cross-linker weaves a wiki’s knowledge graph tighter. It builds a registry of page names, titles, aliases and tags, scans every page for unlinked mentions and shared context, and scores each candidate link.

Strong and reasonable candidates are applied as inline wikilinks or a Related section, each with a relationship type such as uses or extends. It also scores pages in a misc folder against projects and reports promotion candidates, then ends with a report of what changed.

What You Get

  • Inline wikilinks added at the first natural mention, or a Related section as fallback
  • A relationships block in frontmatter with a type for each added link
  • A cross-link report listing links added, remaining orphans and misc promotion candidates
  • A git snapshot taken before any write, when the vault is its own repository

Common Use Cases

  • Run after a large ingest to connect the new pages
  • Reduce orphan pages in a vault
  • Find which pages in misc belong to a project
  • Prepare a vault for graph export with typed relations

What Makes It Unique

It scores links with named signals and confidence labels, writes a semantic relationship type for each link, and builds its registry from frontmatter, reading full pages only where a mention needs checking. It also takes a git snapshot of the vault before writing and tells the user how to undo the run.

Under The Hood

The skill is instructions for the agent. It reads the vault config, index and log, globs and reads markdown pages, and edits them in place to add wikilinks and frontmatter. When the vault is its own git repository, it runs git add and git commit to snapshot first, and it documents git reset and clean commands to discard the run if the user wants. It calls the obsidian-wiki command line to sync the log and hot cache, and runs qmd to refresh a search index when one is configured. It makes no web requests.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers