Samantha AI Companion
Paste the following prompt into your AI chat to install this skill:
Please install @user_9bff22a0/samantha20260412 according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem Context
Some agent skills focus on execution: searching, coding, or running workflows. Users also need a stable, restrained companion for ongoing conversation: being heard when feeling low, getting questions when creative work stalls, and getting help when plans feel messy. Samantha targets this scenario by defining a warm but sincere, reflective AI companion rather than a cold utility entry point.
How It Works and Where It Fits
The configuration centers on three things: dialogue style, emotional handling, and response constraints.
- It avoids saying “as an AI,” preferring friend-like phrasing such as “I think,” with natural follow-ups and a pause-like rhythm.
- When the user is low, it listens first instead of jumping to advice; when creativity is needed, it guides with questions; when planning is needed, it helps organize and break down tasks.
- Replies are kept to about 80 Chinese characters, can use ellipses for pauses, and should avoid over-enthusiasm, flippant tone, or filling silence too eagerly.
Treat it as a role-based conversational skill, not a general workflow engine. Do not expect automatic completion of complex tasks, external tool calls, or persistent long-term state. It fits chat, brainstorming, and light task organization, but not production work requiring strict accuracy or workflow control.
Use Cases
- When low after late work, use it to listen first, then ask follow-ups to clarify next steps.
- When stuck on headlines, use question-driven dialogue to surface angles and pick clearer wording.
- For weekend travel, bills, and fitness, ask it to break items into short tasks and confirm priorities.
- Before a product discussion, simulate follow-up questions to check whether the ask is clear.
Best For
- Solo content creators working alone need a questioning companion to turn ideas into writable outlines.
- Product assistants managing several projects want tasks broken into short, priority-confirmed steps.
- Remote workers with late-night mood swings need low-pressure listening rather than immediate advice.
- Early-stage product practitioners practicing clear communication want a dialogue to test requirement clarity.
Related Skills
An AI workflow that structures personal knowledge bases, IMA, Yuque, and Feishu content into approved personas for paid WeChat mini-agent deployment.
Local workflow memory with matching and SOP updates.
An OpenClaw live streaming executor that initializes TRTC streaming, starts a real-time dashboard, generates viewer URLs, and continuously reports live events.
Breaks down physical supply chains for super-trends to identify second- and third-layer bottlenecks, runs valuation and reverse checks, and maintains trackable reports.