See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptWhat specific action link types should be integrated into drillable dashboard cards for pipeline anomalies?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| The embedded drill links utilize monitor, inspect, or build command actions. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Revenue Health Dashboard Skill
When to Use
- Summarizing bookings, pipeline, retention, and efficiency metrics in one place.
- Creating weekly/monthly revenue review packs with consistent layout.
- Highlighting guardrail breaches and ownership for remediation.
Framework
- KPI Stack – bookings, pipeline coverage, win rate, retention/NRR, CAC/payback.
- Segmentation Layer – tabs for region, segment, product, channel.
- Guardrail Banner – visual cues for breached vs healthy thresholds.
- Insight Tiles – annotate root cause, owner, and next action per issue.
- Drill Links – tie charts to deeper dashboards or command outputs.
Templates
- Executive summary slide with KPI dials + traffic lights.
- Detail view for pipeline vs target, retention cohorts, and efficiency metrics.
- Action tracker table embedded in the dashboard.
Tips
- Keep traffic-light rules aligned with
guardrail-scorecard to avoid confusion.
- Embed command links (monitor, inspect, build) so reviewers can dive deeper.
- Snapshot dashboards before/after remediation to track improvement.
Track record
Benchmark
14 / 22
test cases passed, vs 8 / 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/revenue-analytics/skills/revenue-health-dashboard/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1