Use when validating automation builds before launch or after significant changes.
SkillScore86Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/23/2026
What it changes
Passed 19 of 22 test cases with the skill, and 16 of 22 without it.
Without skill73%
With skill86%
Checks it passed that the model alone missed
Recommends purging test data regularly to avoid reporting noise
Recommends documenting kill switches or rollback mechanisms during debugging
Specifies verifying API or webhook calls, CRM updates, data enrichment, and scoring
and 3 more in the full report
4 fixed15 passed either way2 still failing1 broke
Pass-rate lift
+14 pp
Tokens
-1%
Agent turns
0%
Response time
-20%
Model gemini-3.6-flashMeasured 8/23/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
Our marketing team recently updated our nurture campaign logic, but we are seeing lead routing errors and broken merge fields in production. What structured testing framework should we follow to investigate these failures and execute regression tests, and what safety mechanisms should we establish during debugging?
What was checked, without and with the skill
Checked
Without skill
With skill
Outlines a 5-pillar framework spanning unit tests, integration tests, content QA, compliance, and performance
Missed
Passed
Recommends documenting kill switches or rollback mechanisms during debugging
Missed
Passed
Recommends purging test data regularly to avoid reporting noise
Missed
Passed
case-02 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md31 linessingle file
Workflow Testing & QA Skill
When to Use
Any new automation or major revision prior to go-live.
Regression testing after data, asset, or logic changes.
Investigating deliverability, conversion, or routing anomalies.
Framework
Unit Tests – confirm each branch, wait step, and action path with seed contacts.