← 返回
AI智能 中文

Weclone Init Twin

Scaffold a digital twin persona directory with markdown templates such as profile, state, persona examples, and guardrails. Use when the user wants to initia...
使用 Markdown 模板(如 profile、state、persona 示例和 guardrails)快速构建数字孪生人格目录,适用于用户想要初始化...
xming521
AI智能 clawhub v0.1.0 1 版本 100000 Key: 无需
★ 0
Stars
📥 463
下载
💾 8
安装
1
版本
#latest

概述

WeClone Init Twin Profile

Create or refresh the markdown persona pack for a user's digital twin. This skill prepares files only. It does not draft replies.

Expected Inputs

  • A user name for template placeholders.
  • An optional target directory. Default to ai_twin/ at the repo root.
  • An optional template language. Supported values: en and zh. Default to en.
  • Explicit approval before overwriting existing persona files.

Core Workflow

  1. Check whether the target persona directory already exists.

If files already exist, do not overwrite them unless the user explicitly asks for regeneration.

  1. Scaffold the persona pack.

Run python3 skills/weclone-init-twin/scripts/init_twin_profile.py --user-name --language [output_dir].

  1. Regenerate only with explicit overwrite approval.

Add --force only when the user clearly wants to replace existing files.

  1. Hand off to reply generation.

Tell the user to fill the generated markdown templates before using $weclone-twin-reply.

Files And Resources

  • scripts/init_twin_profile.py: scaffold the default ai_twin/ persona directory from bundled templates.
  • assets/persona-pack/: starter markdown templates for profile.md, state.md, persona_examples.md, and guardrails.md, plus *.zh.md Chinese variants.

Output Contract

Return a short setup handoff with:

  • CREATED_FILES
  • TARGET_DIR
  • NEXT_STEP

版本历史

共 1 个版本

  • v0.1.0 当前
    2026-03-30 03:57 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,350 📥 317,461
content-creation

Weclone Twin Reply

xming521
根据角色设定文档、示例及实时对话上下文,构建需经审核的数字孪生回复。用于需要模仿特定用户……
★ 1 📥 475
ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,054 📥 794,329