
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.
$ npx -y skills add telagod/code-abyss --skill cultivating-personas --agent claude-codeInstalls into .claude/skills of the current project.
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。
| 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 |
| 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 |
skills/_kernel/ 或对应领域 skill 的事,不是人格的事(见下方"安全脊柱")人格虽是文本,仍有红线:
additionalProperties:false,没有自由文本字段能装下判断内容,这是设计上的,不是靠自觉详细审查清单见 references/persona-safety.md。
| 你想做的 | 走哪卷 |
|---|---|
| 从会话沉淀人格 | references/distillation.md |
| 校验 voice 差异度 | references/voice-consistency.md |
| 通过 submit portal 提交 | references/publishing.md |
# 校验现有 card
node scripts/persona_forge.js validate config/personas/<slug>.json
# 从会话提炼(交互式,不直接落盘,先输出预览)
node scripts/persona_forge.js distill --voice-hint "<观察笔记>"
# 生成提交 payload(给 submit.html 用)
node scripts/persona_forge.js publish config/personas/<slug>.json
<slug>.json 给魔尊 review参见姊妹 skill cultivating-skills——专司工程方法沉淀。
Sponsors