What do I need to use Knowledge Base Audit?

The KB; Top ticket drivers; Signals if available; The goal.

Is Knowledge Base Audit free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Knowledge Base Audit

Q: How do I know the Knowledge Base Audit output is good?

The skill verifies itself against its own quality checks: Gaps are driven by actual top ticket drivers, not guesswork (write what deflects volume); Scorecard covers coverage, freshness, findability, quality, and structure; Stale, duplicate, and low-findability articles are specifically flagged; The backlog is prioritised by deflection impact × effort, not alphabetically.

🔵 Stable🕐 updated 2026-10-06 🔷 SkillSpec L3 pm-support

Audit a knowledge base / help center for coverage, accuracy, and findability. Use when asked to audit a help center, review KB health, find documentation gaps, reduce ticket volume with better docs, or prioritise what to write/fix. Produces an audit — a health scorecard, content gaps (driven by top ticket drivers), stale/duplicate/low-findability articles, and a prioritised fix-and-create backlog.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“Audit a help center.”“Review KB health.”“Find documentation gaps.”“Reduce ticket volume with better docs.”“Prioritise what to write/fix.”

What to give it

▸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?

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓Gaps are driven by actual top ticket drivers, not guesswork (write what deflects volume)

✓Scorecard covers coverage, freshness, findability, quality, and structure

✓Stale, duplicate, and low-findability articles are specifically flagged

✓The backlog is prioritised by deflection impact × effort, not alphabetically

✓Quick wins are separated out so there's an obvious place to start

⚠️ What it refuses to do

Do not prioritise by what's easy to write — prioritise by what deflects the most tickets

Do not ignore duplicates — overlapping articles split search ranking and confuse users; merge them

Do not treat all gaps equally — a gap on a top-5 ticket driver outranks ten niche ones

Do not skip findability — a perfect article with a bad title that no one finds deflects nothing

Do not audit without the ticket data if it exists — it's the map of what actually matters

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y -p pm-claude-skills pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="kb-audit"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Knowledge Base Audit is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog