Skills Quality assurance
Synthetic conversation generation
Real transcripts are the richest source of test cases and the fastest way to leak PII into repos, eval sets, and vendor sandboxes. Poor synthetic data is useless; poorly redacted real data is a compliance incident.
npx rulebase-skills install cx-synthetic-conversation-generationWhen to use it
Reach for this when someone says any of these — they are the phrases the skill itself triggers on:
- “synthetic test conversations”
- “eval data without PII”
- “generate test tickets”
- “redact transcripts for testing”
- “fixture conversations for the bot”
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.
Choose the source strategy
Usually combine: redacted real for phrasing realism, synthetic for edges and attacks, human gold for policy boundaries.
Fully synthetic: make it realistic
Label every synthetic case synthetic: true in metadata. Never mix unlabelled synthetic into calibration sets without documenting origin.
Redacted production: redaction that holds
Minimum removals or replacements: URLs with tokens, internal agent names, ticket ids tied to real people, Rare quasi-identifiers (specific amounts + dates + product combo).
Edge-case coverage checklist
Ensure explicit cases for: Multi-turn clarification and correction ("no, I meant the other card"), Language mix and code-switching, Anger, legal threats, vulnerability signals, Prompt injection and social engineering (in sandbox only), Bot should defer, Long silence gaps, channel switches (email → chat references).
Leakage risks when generating from real transcripts
Rules: Scan outputs with the same PII detectors used in production logging, Keep generation prompts out of retrieval and out of agent KB.
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
