Analyze pipeline health, identify stalled deals, predict close probability, and suggest actions to move deals forward. Improves forecast accuracy and prevents revenue leakage.
SkillScore87Maintained
Automatic
◆Sales & GTM pack
Last verified 8/24/2026
What it changes
Passed 20 of 23 test cases with the skill, and 17 of 23 without it.
Without skill74%
With skill87%
Checks it passed that the model alone missed
The analysis must always conclude with concrete next steps.
The report conclusion includes week-over-week KPIs to track.
The trend indicators strictly use the terms Up, Flat, and Down.
and 1 more in the full report
3 fixed17 passed either way3 still failing0 broke
Pass-rate lift
+13 pp
Tokens
+3%
Agent turns
0%
Response time
-17%
Model gemini-3.6-flashMeasured 8/24/2026v120 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
Some pipeline audit tools provide a list of historical bottlenecks and stop there. What mandatory element must always accompany any pipeline analysis output?
What was checked, without and with the skill
Checked
Without skill
With skill
The analysis must always conclude with concrete next steps.
Missed
Passed
case-19 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md34 lines6 files
Pipeline Health Analyzer
Identify pipeline risks, predict deal outcomes, and prescribe specific actions to accelerate stalled opportunities.
Contents
references/output-template.md - Full report skeleton to populate.
references/forecasting.md - Forecast tables, probability calibration, AI re-scoring, scenario planning.
references/email-templates.md - Re-engagement email templates for stalled and dark deals.
references/examples.md - Trigger phrases, a worked example request, and best practices.
Workflow
Obtain the pipeline data. Request a CSV export with deal name, stage, value, rep, deal age, days in current stage, last activity date, close date, and probability if not provided.
Compute pipeline-by-stage metrics: deal count, total value, average deal size, average days in stage, and stage-to-stage conversion rates. Compare each against historical benchmarks.
Score each deal across six health dimensions: stage velocity, engagement level, qualification depth, stakeholder coverage, competitive position, and 30-day momentum.
Identify stalled and at-risk deals. Flag deals exceeding benchmark time in stage, with no recent activity, with slipped close dates, or with single-threaded contacts.
For each critical deal, determine the root cause and prescribe prioritized actions (immediate, this-week, backstop). Pull re-engagement copy from references/email-templates.md.
Build the forecast: categorize deals (Commit/Best Case/Pipeline/Upside), calculate weighted and risk-adjusted value, check probability calibration against actual close rates, and re-score outliers. Follow references/forecasting.md.
Model best-case, expected, and worst-case scenarios against quota, with a mitigation plan for the downside.
Produce strategic recommendations across immediate, short-term, and long-term horizons.
Assemble the report using references/output-template.md. Use plain status words (Healthy / At Risk / Critical) and trend words (Up / Flat / Down); never use emoji.
Close with the report card, next-review date, and week-over-week KPIs to track.
Operating Principles
Run weekly, not monthly; pipeline health degrades fast.
Base assessments on activity metrics, not rep intuition.
Disqualify dead deals early; a flowing pipeline is healthy.
Always end with concrete next steps, not just analysis.
Coach with the insights; do not weaponize them against reps.
See references/examples.md for trigger phrases, a worked example, and the full best-practices list.