← All skills

safety-alignment-constitutional-ai

100 / 100 · Low risk

Fine to try.

By aicodedecode/awesome-muse-skills (GitHub) · design · 59 stars · scanned at commit faf37c0

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'safety-alignment-constitutional-ai' ] || [ -L ~/.agents/skills/'safety-alignment-constitutional-ai' ]; then echo 'A skill folder named safety-alignment-constitutional-ai already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/aicodedecode/awesome-muse-skills' "$d" && git -C "$d" checkout --quiet 'faf37c0859ebf627bfcb5225e8057d088691e0ae' -- 'skills-imported/safety-alignment-constitutional-ai' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills-imported/safety-alignment-constitutional-ai' ~/.agents/skills/'safety-alignment-constitutional-ai' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'safety-alignment-constitutional-ai' ~/.claude/skills/'safety-alignment-constitutional-ai' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for aicodedecode/awesome-muse-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/aicodedecode/awesome-muse-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/aicodedecode/awesome-muse-skills/)

Score history