Skip to content
SkillModel-led1,893 tokens in use

tag-taxonomy

Keeps Obsidian wiki tags consistent by auditing them against a canonical vocabulary, mapping aliases, and choosing tags for new pages.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing tag-taxonomy costs

40tokens idle
1,893tokens 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

shelldetected

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
  • Frontmatter8/15
  • Structure23/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • 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 170

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

tag-taxonomy treats a taxonomy file in your vault as the source of truth for tags. It lists canonical tags, aliases, a cap of five tags per page and known renames, and the skill reads it before any tagging work.

It runs in four modes: audit the current tags, normalize pages to the canonical forms, tag a new page, and add a new tag to the vocabulary. Reserved visibility tags are reported separately and never rewritten.

What You Get

  • A tag audit report with totals, non-canonical tags, unknown tags and over-tagged pages
  • Pages rewritten so alias tags use their canonical form
  • Tag suggestions for a new page: one or two domain tags, one type tag and optional project tags
  • New canonical tags appended to the taxonomy file in the right section
  • Separate reporting of visibility tags that mark public, internal or sensitive pages

Common Use Cases

  • Cleaning up tag sprawl such as nextjs, next-js and react across a growing vault
  • Choosing consistent tags while ingesting new sources
  • Deciding whether a repeated unknown tag deserves a place in the vocabulary

What Makes It Unique

The vocabulary lives in one file inside the vault that you own, with aliases and migration notes, so the same rules apply to every skill that tags pages. It handles reserved visibility tags as their own group: they do not count toward the five-tag limit, only one is allowed per page, and normalization leaves them untouched. Changes to unknown tags always wait for your answer.

Under The Hood

The skill is instructions for the agent. It reads the taxonomy file and page frontmatter in the vault, and edits page frontmatter and the taxonomy file when you approve normalization or additions. It runs the obsidian-wiki command line tool through the shell to log the operation and refresh the index and hot cache, and runs the qmd command when a QMD collection is configured. It does not fetch web pages or call remote APIs.

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