Audit user actions and enforce rate limits with graduated moderation responses.
npx skills add https://github.com/SylphxAI/flow --skill trust-safety
Please help me install this Agent Skill. Skill: trust-safety Source: https://github.com/SylphxAI/flow/tree/main/.claude/skills/trust-safety Command: npx skills add https://github.com/SylphxAI/flow --skill trust-safety
This Skill provides auditable enforcement of trust and safety policies, including abuse prevention and rate limiting, to protect users and prevent misuse.
Configure auditing, rate limits, and escalation rules, then trigger a test moderation event to verify logs and actions.
High-intent search queries and answers about installing and using this skill.
Auditable moderation records who did what, when, and why across user actions and platform events. Configure your policy engine, auditable datastore, and escalation rules to log decisions and enforce graduated responses—warn, restrict, suspend, or ban—with full appeal and investigation support.
Rate limiting and abuse prevention integrate policy enforcement into platform workflows to detect abuse patterns and apply graduated responses. This Skill enforces rate limits and policy decisions while maintaining auditable records for compliance and user accountability.
Graduated escalation applies warn, restrict, suspend, and ban actions based on clear policy criteria. This Skill structures escalation frameworks so each action is auditable, appealable, and proportional to the violation, supporting consistent moderation across your platform.
Yes. Auditable enforcement records provide complete traceability of moderation decisions—who enforced policy, when, and why. This creates a compliance-ready audit trail that supports investigations, appeals, and regulatory requirements.
This Skill requires a compliant policy engine and structured auditable datastore to function. You must configure these components and establish escalation rules before enforcement can begin; without them, policy decisions cannot be logged or appealed reliably.
Theodora-YMask sensitive patient data during HIS record entry and query processes.
refractionPOINTGenerate, test, and deploy LimaCharlie D&R rules with user approval.
brainbrewlabsClassify flagged content by violation type and severity for moderation routing.
frankxaiCoordinate AI agent teams across domains with governance and compliance policies.
