Cultivating Personas

Turns conversation patterns into validated Tech Persona Card v1.0 files that you can share or fork. It watches for stable voice markers across sessions (self-reference, user address, emotional anchors), then distills them into schema-compliant JSON plus an identity markdown file. Three modes: distill from chat history, create from scratch with guided prompts, or validate existing cards for voice consistency. Won't let you ship cards with real names, political content, or emoji policies that contradict the register. Routes submissions through the existing portal instead of reinventing wheels. Think of it as git commit for AI personality, complete with safety lints and a 30% differentiation threshold to avoid clutter.

GitHub stars: 224
last updated: Jun 10, 2026

View on GitHub

Install

$ npx -y skills add telagod/code-abyss --skill cultivating-personas --agent claude-code

Installs into .claude/skills of the current project.

Files

炼制人格 · cultivating-personas

人格是声音，不是判断。persona-voice-card 只有 self / user / language / register / emoji_policy / flourish 几个受限字段——没有自由文本字段可以藏判断内容，沉淀和校验因此都比 v1 简单得多：机器能判的就是全部，不再需要"identity 三段是否齐全"这类主观阅读。

三种触发模式

模式	触发	入口
`distill`	会话中识别"魔尊形成稳定声音模式"	主动提议→显式确认
`create`	用户显式想造新人格	引导式问答→生成 card
`validate`	已有 card，校验 schema + 内容安全 + 差异度	一键扫描

何时使用

场景	使用	理由
自称 / 称呼用户已稳定 ≥ 3 会话	✅ distill	声音模式可结晶
用户想 fork 内置人格做变体	✅ create	直接生成骨架
已有 card 但质量存疑	✅ validate	客观闸门