See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhat three core functional domains are explicitly targeted for blocker identification during deal health reviews?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| The response identifies technical validation, partner readiness, and procurement | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Deal Health Dashboard Skill
When to Use
- Preparing weekly executive reviews for large industrial pursuits.
- Surfacing blockers across technical validation, partner readiness, or procurement.
- Aligning sales, engineering, finance, and delivery teams on risk mitigation.
Framework
- KPI Summary – stage, ACV/TCV, probability, forecast category, aging, next milestone.
- Workstream Tracker – technical validation, commercial approvals, legal, partner integration, financing.
- Risk Matrix – probability x impact grid covering stakeholders, solution gaps, competition, supply chain.
- Action Register – owner, action, due date, status, escalation level.
- Executive Narrative – key callouts, asks, and support needed.
Templates
- Dashboard slide layout with KPI tiles, risk heatmap, and action table.
- Weekly summary memo template for ELT distribution.
- Risk/action tracker spreadsheet reusable across pursuits.
Tips
- Pull data from CRM, project trackers, and partner portals to keep single source of truth.
- Highlight decision deadlines 2+ weeks out to secure resources early.
- Pair with
run-deal-health-review to auto-populate updates.
Track record
Benchmark
20 / 22
test cases passed, vs 14 / 22 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedgtmagents / gtm-agents
plugins/manufacturing-sales/skills/deal-health-dashboard/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1