awesome-ai-persona-skills
Provides 100+ pre-built persona skill sets that accelerate prompt engineering by offering tested personality archetypes across professional, entertainment, a…
A Chinese-language collection of 100+ 'persona distillation' skills that turn real or fictional personalities — celebrities, novelists, classical texts, anime characters, workplace and emotional-support roles — into importable agent skills, plus original multi-agent 'advisor team' sets (e.g. 20 Tianya forum legends, famous film directors). Content and documentation are in Chinese.
- Train customer support bot with professional communication persona
- Generate historical figure responses for educational content
- Build anime character dialogue for entertainment applications
Provides 100+ pre-built persona skill sets that accelerate prompt engineering by offering tested personality archetypes across professional, entertainment, and emotional domains. Reduces iteration time when building Claude agents with specific behavioral patterns.
Chinese-speaking users who want ready-made persona and roleplay skills for Claude or compatible agents — writing-style emulation, entertainment characters, emotional-companion and workplace roleplay scenarios.
https://github.com/momozi1996/awesome-ai-persona-skills
By momozi1996
How to Get It
See repository README — skills are markdown files you import directly into your agent (no single install command)
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me train customer support bot with professional communication persona
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): 546 GitHub stars; 1 contributors; last commit 87d ago; license MIT.
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.
- Single maintainer. Consider the risk if this person stops maintaining the project.
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): 546 GitHub stars; 1 contributors; last commit 87d ago; license MIT.