constitutional-ai

github:zechenzhangAGI/claude-ai-research-skills · first committed 2025-11-08 · source · badge

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.

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

6 commits to this file on GitHub (newest first).

2025-11-20 · commit 0a9ded4 · Standardize skill metadata: Add category tags and update authors
2025-11-20 · commit 72c8b2c · Trigger upload of remaining 26 skills
2025-11-20 · commit 85a6d14 · Trigger upload of remaining 12 skills with large file fix
2025-11-20 · commit f38509b · Sync first 20 skills to Orchestra marketplace
2025-11-19 · commit bd4461f · Standardize YAML frontmatter for all 54 skills
2025-11-08 · commit 766daad · Add 5 post-training and safety alignment skills

Archived snapshots