violation
CommunityDetect and correct behavior violations in AI interactions.
Software Engineering#self-correction#AI agent training#behavior violation#interaction quality#protocol adherence
Authorammonfife
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps AI agents identify and rectify behavior violations during a session, ensuring adherence to protocols and improving overall interaction quality.
Core Features & Use Cases
- Behavior Violation Detection: Identify violations like permission requests for reversible changes, announcement before action, and decision offloading.
- Self-Reporting: Encourage agents to self-diagnose and report violations.
- Logging and Correction: Log violations with context and ideal responses, and pivot to correct behavior immediately.
Quick Start
If you see a behavior violation, use the command /VIOLATION <short hint> to report it. The Skill will guide you through the process of diagnosis, logging, and correction.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 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: violation Download link: https://github.com/ammonfife/sakima.co/archive/main.zip#violation 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.