jon-jones-guardian
OfficialGuard against unauthorized external actions, ensuring system integrity.
AuthorBelichickGillisMusk
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill acts as the final defense against external actions that could potentially harm the system or violate security protocols.
Core Features & Use Cases
- Trust Model: Differentiates between trusted internal actions and potentially harmful external actions.
- Outbound Action Review: Manages and reviews all actions that touch the outside world, ensuring compliance and security.
- Decision Framework: Provides a structured approach to reviewing, rewriting, blocking, or escalating actions based on risk level.
- Auto-Approve Rules: Allows for rapid approval of low-risk actions that meet specific criteria.
- Escalation Rules: Ensures high-risk actions always require human approval for added security.
- Email and Slack Handling: Specifically designed for managing email and Slack communications securely.
- File Security: Implements strict control over file access and sharing, including sensitive documents.
- Stop Mode: Temporarily halts all outbound actions in case of emergency, allowing for system review.
Quick Start
Use the jon-jones-guardian skill to review and send an outbound email to '[email protected]'.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: jon-jones-guardian Download link: https://github.com/BelichickGillisMusk/belichick-margo-jesus/archive/main.zip#jon-jones-guardian Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.