awesome-human-distillation
Indexes the fast-growing Chinese 'persona distillation' scene in one place — general frameworks like nuwa-skill and immortal-skill plus dozens of ready-made …
A Chinese-language curated list of 'human distillation' projects — skills that turn a real person (a colleague, mentor, family member, or public figure) into a callable Claude Code Agent Skill using chat logs, writing, and other personal material. Organized by relationship type: workplace, academia, intimate, family, and public figures. A reference list linking ~200 external skills, not an installable skill itself.
- Find pre-built agent skills to accelerate your distillation pipeline development
- Review curated examples of human knowledge transfer patterns for AI training
- Explore proven techniques for converting expert behavior into trainable agent behaviors
Indexes the fast-growing Chinese 'persona distillation' scene in one place — general frameworks like nuwa-skill and immortal-skill plus dozens of ready-made person-to-skill projects — so you can find or evaluate persona skills without hunting across GitHub.
People exploring persona and 'digital immortality' skills — distilling themselves or others into reusable agent personas. Content and project descriptions are in Chinese.
https://github.com/mliu98/awesome-human-distillation
By mliu98
How to Get It
None — curated list; browse the linked projects at the source
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me find pre-built agent skills to accelerate my distillation pipeline development
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 721 GitHub stars; 7 contributors; last commit 3d ago; license no license.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 721 GitHub stars; 7 contributors; last commit 3d ago; license no license.