Knowledge Base Audit Skill

A help center silently rots: articles go stale, gaps let tickets through, duplicates confuse search, and nobody notices until deflection drops. This skill audits it — scoring health, mapping gaps against your actual top ticket drivers (so you write what reduces volume, not what's easy), and flagging stale/ duplicate/unfindable content — then hands back a prioritised backlog of what to fix and create.

Required Inputs

Ask for these only if they aren't already provided:

• The KB — the article list/structure (titles, sections; or a sample if large).
• Top ticket drivers — the most common support topics/questions (the single most useful input — it's what should be documented).
• Signals if available — article views, search terms with no results, "was this helpful?" ratings, last-updated dates.
• The goal — reduce ticket volume, improve self-serve, onboard a new product area?

Output Format

KB Audit: [help center]

1. Health scorecard — a quick read across: coverage (are top topics documented?), freshness (how much is stale), findability (titles/search-friendly?), quality (answer-first, scannable?), structure (organised, no duplication). RAG per dimension.

Dimension	Status	Note

2. Coverage gaps (priority) — cross-reference top ticket drivers against existing articles. The gaps where high ticket volume meets no/poor article = the highest-ROI things to write. Rank them.

3. Fix list — existing articles that are stale (outdated steps/screenshots), duplicate/overlapping (consolidate — they split search authority), hard to find (bad title, missing search terms), or low-quality (answer buried, not scannable).

4. Prioritised backlog — combine create + fix, ranked by :