See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
PromptAfter resolving a major compliance finding raised during a customer council, what three key elements must be logged in the wrap-up evaluation phase?
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| Logs operational outcomes. | Passed | Passed |
|---|
| Logs lessons learned. | Passed | Passed |
|---|
| Evaluates whether additional listening is required. | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Closed-Loop Playbook Skill
When to Use
- After synthesizing VoC insights that require cross-functional action.
- During QBRs or ELT reviews to show status of customer commitments.
- Whenever audit trails are required for compliance or customer councils.
Framework
- Intake – capture insight ID, driver, severity, customer(s), and evidence link.
- Routing – assign accountable owner, supporting squad, and due date.
- Action Plan – define mitigation plan, success criteria, and measurement method.
- Communication – schedule updates to customers, exec sponsors, and internal stakeholders.
- Retrospective – log outcomes, lessons, and whether additional listening is needed.
Templates
- Action register (spreadsheet/Notion/Jira) with status automation.
- Customer commitment digest template for AM/CS teams.
- SLA matrix by issue severity and customer tier.
Tips
- Integrate with ticketing/project systems to avoid duplicate tracking.
- Highlight blockers early; exec sponsors can unblock resources fast.
- Close the loop with customers even when timelines slip—transparency builds trust.
Track record
Benchmark
16 / 22
test cases passed, vs 15 / 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/voice-of-customer/skills/closed-loop-playbook/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1