Skills CX operations
Agent experience audit
When quality or handle time slips, the default fix is more training. Often the binding constraint is the job itself: six systems per ticket, a macro that stopped working, an approval that requires a manager who is offline, a KB article that contradicts policy. Agents compensate with workarounds; WFM sees occupancy; customers see inconsistency.
npx rulebase-skills install cx-agent-experience-auditWhen to use it
Reach for this when someone says any of these — they are the phrases the skill itself triggers on:
- “agent experience audit”
- “why is handle time so high”
- “tooling friction”
- “agents switching systems”
- “shadow an agent”
- “we need more training”
How it works
The method, in the order the skill runs it. The full procedure — tables, worked examples and the edge cases — is in the skill itself.
Step 1: pick representative work
Do not audit from memory or a tour from engineering.
Step 2: shadow protocol
For each session, the observer records without coaching.
Step 3: classify friction
Bucket findings so fixes have owners.
Step 4: prioritise fixes
Rank by volume × severity × fixability: Volume, Severity, Fixability.
Step 5: validate with data where possible
Shadow finds hypotheses. Confirm with: Handle time decomposition by driver, Escalation reason codes, Macro usage logs, Assist / chat-to-peer rate, Repeat contact on strata with high hop count.
Step 6: close the loop
After a fix ships, re-shadow the same driver sample. Audits that end at a slide deck do not change agent experience.
Related skills
Free and open source, and vendor-neutral — it reads the conversations from whichever helpdesk you already run. Browse all 149 skills · connect your helpdesk over MCP · source on GitHub
