Confluence Labels and Taxonomy Audit
Audit Confluence labels for spelling variants, near-duplicates and unused tags, and propose a small controlled vocabulary.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.
I want to tidy the labels (tags) in my Confluence space [SPACE_NAME]. I will paste a list of every label with the number of pages that use it: [LABEL_LIST]. Our teams use Confluence mainly for [USE_CASES], and the people who add labels are [LABEL_USERS]. Group the labels into: Spelling or plural variants of the same idea, Near-duplicates with different wording, Labels used only once or twice, Labels so generic they filter nothing, and Healthy labels. Show a table with the columns Label, Pages, Group and Proposed action (merge into X, drop, keep, rename). Report counts per group and the percentage of labels that are variants or singletons, showing the arithmetic. Then propose a controlled vocabulary of no more than 20 labels, each with a one-line definition and an example of a page that should carry it, plus a naming rule (lowercase, hyphens, singular). Base everything on the list pasted. Do not guess the meaning of an odd label; put it in a question list for the people who use it. Mention that bulk label editing may need an admin or an add-on and mark that with [VERIFY] for our Confluence version. No labels should be removed automatically; give a reviewed change list instead.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.
See an example result (fictional data)
Invented sample of 40 labels. | Label | Pages | Group | Action | | onboarding | 22 | Healthy | Keep | | on-boarding | 3 | Spelling variant | Merge into onboarding | | onboard | 1 | Singleton | Merge into onboarding | | important | 57 | Too generic | Drop, ask owners what they meant | | q3-offsite | 1 | Singleton | Keep only if still used | Counts: variants 6, singletons 11, generic 3, healthy 20. Variants or singletons: 17 of 40 = 42.5%. Proposed vocabulary starts with: onboarding (new-starter material), policy (rules people must follow), template (copy and reuse). Question for users: what did "important" mean to you?
Illustrative only, made-up data. Your results will differ and must be reviewed.