Skip to content

a5c-ai/babysitter / library/specializations/ai-agents-conversational/skills/constitutional-ai-prompts

constitutional-ai-prompts

Verified

Constitutional AI and safety guardrail prompts for aligned LLM behavior

FileKindSize
README.mdmarkdown573 B
SKILL.mdskill md1.5 KB
---
name: constitutional-ai-prompts
description: Constitutional AI and safety guardrail prompts for aligned LLM behavior
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep
graph:
  domains: [domain:software-engineering]
  specializations: [specialization:ai-agents-conversational]
  skillAreas: [skill-area:prompt-engineering, skill-area:safety-redteaming]
  roles: [role:ml-engineer, role:backend-engineer]
  workflows: [workflow:ml-model-lifecycle, workflow:feature-development]

---

# 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

1. **Critique-Revision**: Self-evaluate and improve responses
2. **Principle Adherence**: Follow defined ethical principles
3. **Harmlessness Focus**: Prioritize safe responses
4. **Helpfulness Balance**: Balance helpfulness with safety
5. **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
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall