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.