crm-production-investigation-guidelines Audit report.

Warnings

• SKILL.md does not define an explicit output format or required deliverable for investigation results, which may lead to inconsistent reports.
• There is no explicit safety/limitations section stating that destructive actions require human approval or that the agent should only perform read-only investigation steps.
• The skill is explicitly a sample tied to a fictional CRM, so it cannot be used directly for real applications without adaptation.
• Low GitHub adoption signal
• Quality score needs review
• GitHub adoption: 42 GitHub stars
• Stars/forks activity: 42 stars, 38 forks; issue activity unavailable in current metadata

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.