Structure for capturing qualitative + quantitative win/loss insights with consistent tagging.
SkillScore91Maintained
Automatic
◆Sales & GTM pack
Last verified 8/23/2026
What it changes
Passed 20 of 22 test cases with the skill, and 15 of 22 without it.
Without skill68%
With skill91%
Checks it passed that the model alone missed
Show driver trendlines over time.
Display revenue impact breakdown per loss driver.
Provide drop-down selection menus for key deal fields.
and 4 more in the full report
5 fixed15 passed either way2 still failing0 broke
Pass-rate lift
+23 pp
Tokens
-8%
Agent turns
0%
Response time
-18%
Model gemini-3.6-flashMeasured 8/23/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
Our operations team wants to manually export CSVs weekly to update win/loss records. What automated workflow trigger command pairs with the win/loss dataset for continuous synchronization?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommend pairing with the run-win-loss-program command for automatic updates.
Missed
Passed
case-11 · 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
Win/Loss Dataset Skill
When to Use
Running structured win/loss programs.
Aligning qualitative interviews with CRM metrics.
Sharing insights across product, sales, pricing, and marketing teams.
Framework
Data Model – deal metadata (segment, region, product, stage), outcome, competitor, primary driver, secondary driver, confidence.