Use to design, run, and synthesize customer feedback programs tied to journey stages.
SkillScore77Maintained
Automatic
◆Customer Success pack
Last verified 8/23/2026
What it changes
Passed 16 of 21 test cases with the skill, and 12 of 21 without it.
Without skill59%
With skill77%
Checks it passed that the model alone missed
Includes stage and persona tracking labels
Pairs every insight with a recommended experiment
Recommends rotating research participants quarterly
and 6 more in the full report
7 fixed10 passed either way2 still failing3 broke
Pass-rate lift
+18 pp
Tokens
-7%
Agent turns
0%
Response time
-15%
Model gemini-3.6-flashMeasured 8/23/2026v117 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
We are setting up an initial research architecture for evaluating our SaaS trial-to-paid conversion flow. Most teams just set up a survey form and blast it to all active users. Outline the formal initial program design structure required before launching data collection.
What was checked, without and with the skill
Checked
Without skill
With skill
Defines sample size target and participant incentive structure
Missed
Passed
Identifies target personas and journey touchpoints
Passed
Passed
case-03 · 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.md25 linessingle file
Voice of Customer System Skill
When to Use
Planning journey discovery projects or validating hypotheses.
Building continuous feedback loops (surveys, interviews, community, support mining).
Translating VOC findings into prioritized journey actions.
Framework
Program Design – define objectives, personas, touchpoints, sample size, and incentives.
Channel Mix – select qualitative (interviews, live sessions) and quantitative (NPS, CES, product usage) data sources per stage.
Signal Processing – tag insights by emotion, friction type, segment, and impact.