ethical-guardrail-sentinel
CommunityNon-bypassable output screening for ethical compliance
Authorrancapoly
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a non-bypassable, always-on output screening layer to ensure ethical compliance in HR workflows, detecting bias, GCG violations, and data privacy issues.
Core Features & Use Cases
- Real-time Output Screening: Screens 100% of HR outputs for ethical and compliance issues.
- Bias Detection: Identifies explicit and implicit bias in HR language.
- GCG Compliance: Matches content against the Polytron GCG Code ruleset.
- Data Privacy: Checks for PII exposure and compliance with UU PDP 27/2022.
- Use Case: Before publishing a job posting, the Skill automatically checks for any ethical or compliance issues, flagging content that requires revision.
Quick Start
Use the ethical-guardrail-sentinel skill to screen the output of the job posting 'job-posting-q3.pdf'.
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: ethical-guardrail-sentinel Download link: https://github.com/rancapoly/vault/archive/main.zip#ethical-guardrail-sentinel 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.