constitutional-ai-prompts
Constitutional AI and safety guardrail prompts for aligned LLM behavior
Resources
1Install
npx skillscat add a5c-ai/babysitter/constitutional-ai-prompts Install via the SkillsCat registry.
About this skill
This skill provides constitutional AI principles and safety guardrail prompts to guide large language models toward aligned, harmless responses. It addresses the challenge of ensuring AI systems follow ethical guidelines while remaining helpful, by offering critique-revision patterns, refusal templates, and red-team testing prompts. Developers should use it when implementing content moderation systems or designing AI agents that require built-in safety mechanisms and principled response frameworks.
SKILL.md
Constitutional AI Prompts Skill
Capabilities
- Design constitutional AI principles
- Implement self-critique and revision prompts
- Create harmlessness guidelines
- Design refusal patterns for unsafe requests
- Implement red-team testing prompts
- Create ethics-aware response frameworks
Target Processes
- system-prompt-guardrails
- content-moderation-safety
Implementation Details
Constitutional Patterns
- Critique-Revision: Self-evaluate and improve responses
- Principle Adherence: Follow defined ethical principles
- Harmlessness Focus: Prioritize safe responses
- Helpfulness Balance: Balance helpfulness with safety
- Transparency: Acknowledge limitations
Configuration Options
- Constitutional principles list
- Critique prompts
- Revision guidelines
- Refusal templates
- Escalation triggers
Best Practices
- Define clear constitutional principles
- Balance helpfulness and safety
- Test with adversarial inputs
- Document refusal patterns
- Regular principle review
Dependencies
- langchain-core
Categories
Install
npx skillscat add a5c-ai/babysitter/constitutional-ai-prompts Install via the SkillsCat registry.