constitutional-ai-prompts SKILL.md skillA

constitutional-ai-prompts from a5c-ai/babysitter is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add a5c-ai/babysitter/constitutional-ai-prompts@git:20260601.da7723a

Pins git:20260601.da7723a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
a5c-ai/babysitter
Path
library/specializations/ai-agents-conversational/skills/constitutional-ai-prompts/SKILL.md
Versions recorded
5
Latest version
git:20260601.da7723a, committed Jun 1, 2026
First version recorded
Mar 25, 2026
Size
1,578 bytes
Repository stars
1,896
License
MIT

Constitutional AI and safety guardrail prompts for aligned LLM behavior.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add a5c-ai/babysitter/constitutional-ai-prompts@sha256:8c02b57e43c0411d

The line at the top of this page pins the label git:20260601.da7723a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_huyu6es6tenjhdwn.svg)](https://markdownregistry.com/a/art_huyu6es6tenjhdwn)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Mar 25, 2026 and Jun 1, 2026, about one every 17 days.

versioncommittedcommitsizeaudit
git:20260601.da7723a latest2026-06-01 da7723a 1,578 BA view · diff
git:20260507.44b06c02026-05-07 44b06c0 1,642 BA view · diff
git:20260507.50823d82026-05-07 50823d8 1,621 BA view · diff
git:20260507.313363d2026-05-07 313363d 1,377 BA view · diff
git:20260325.a6b3a882026-03-25 a6b3a88 1,268 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1578 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

a5c-ai/babysitter · 1,896 stars · license MIT · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_huyu6es6tenjhdwn
GET https://markdownregistry.com/api/v1/resolve?ref=a5c-ai/babysitter/constitutional-ai-prompts
GET https://markdownregistry.com/api/v1/blob/8c02b57e43c0411d3319f17d951d8cc0f281ab9aef99ebfc3bac9487c74faf26

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from a5c-ai/babysitter

assimilate-popular-workflows SKILL.md skill
a5c-ai/babysitter · .claude/skills/assimilate-popular-workflows/SKILL.md · This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover…
git:20260607.b14b456 · audit A · 1,896 stars
babysit-babysitter-issues SKILL.md skill
a5c-ai/babysitter · .claude/skills/babysit-babysitter-issues/SKILL.md · This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues"…
git:20260405.b203853 · audit A · 1,896 stars
catalog-babysitter-users SKILL.md skill
a5c-ai/babysitter · .claude/skills/catalog-babysitter-users/SKILL.md · Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated…
git:20260412.50978ad · audit A · 1,896 stars
fix-failing-pipelines SKILL.md skill
a5c-ai/babysitter · .claude/skills/fix-failing-pipelines/SKILL.md · This skill should be used when the user asks to "fix pipelines", "fix CI", "check staging pipelines", "fix failing…
git:20260405.8e12d42 · audit A · 1,896 stars
process-builder SKILL.md skill
a5c-ai/babysitter · .claude/skills/process-builder/SKILL.md · Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the…
git:20260602.7530e23 · audit A · 1,896 stars
retrospect-external-babysitter-run SKILL.md skill
a5c-ai/babysitter · .claude/skills/retrospect-external-babysitter-run/SKILL.md · For a repository in the babysitter-users catalog, locate its babysitter processes and any committed runs…
git:20260412.82342d6 · audit A · 1,896 stars
babysit SKILL.md skill
a5c-ai/babysitter · .codex/skills/babysit/SKILL.md · Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called…
git:20260528.95a7c5d · audit A · 1,896 stars
AGENTS.md AGENTS.md file
a5c-ai/babysitter · AGENTS.md
git:20260602.ef3cb8f · audit A · 1,896 stars
CLAUDE.md CLAUDE.md file
a5c-ai/babysitter · CLAUDE.md
git:20260602.ef3cb8f · audit A · 1,896 stars
agent-dispatch SKILL.md skill
a5c-ai/babysitter · library/methodologies/automaker/skills/agent-dispatch/SKILL.md
git:20260601.da7723a · audit C · 1,896 stars
code-review-gate SKILL.md skill
a5c-ai/babysitter · library/methodologies/automaker/skills/code-review-gate/SKILL.md
git:20260601.da7723a · audit C · 1,896 stars
feature-intake SKILL.md skill
a5c-ai/babysitter · library/methodologies/automaker/skills/feature-intake/SKILL.md
git:20260601.da7723a · audit C · 1,896 stars

Every file in a5c-ai/babysitter

Browse by kind, by grade A, or by owner.