← Back to Skills Marketplace
44
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install auto-agent-4974
Description
Provides a step-by-step tutorial on building personal AI agents based on 2026 Bilibili resources, covering entry to advanced development.
README (SKILL.md)
Skill: auto_agent_4974\r
\r
【搭建智能体】2026B站最新保姆级Agent智能体搭建教程，从入门到实战全搞定！手把手教你打造个人专属智能体，彻底搞懂AI智能体开发，学会直接薪资翻倍！\r
\r
功能范围\r
- 【搭建智能体】2026B站最新保姆级Agent智能体搭建教程，从入门到实战全搞定！手把手教你打造个人专属智能体，彻底搞懂AI智能体开发，学会直接薪资翻倍！\r
- Auto-generated from B站: BV1jAVh6UEmZ\r \r
归属管理\r
- 归属核心:
learn-expand\r - 源文件:
auto_agent_4974.py\r \r
触发场景\r
- 用户说"agent"\r
- 用户说"【搭建智能体】2026B站最新保姆级Agent智能体搭建教程，从入门到实战全搞定"\r \r Base directory: file:///C:\Users\pc.config\opencode\skills\auto_agent_4974\r \r
B站学习\r
学习时间: 2026-06-01 21:01\r \r
- 沧海九粟: 🧲 Claude Code 自动：长程任务的保障 Auto Mode\r
- 二一的笔记: 一口气搞懂 Notion Custom Agent（测评与教程）\r
- 智能体老王: AI给自己写工具？字节团队出品 MUSE-Autoskill 让Agent实现技能自进化，推动skills成为可复用的知识资产\r \r
B站学习 (第1轮)\r
学习时间: 2026-06-02 09:20\r \r
- AIlazy俊: 66K 星的 Caveman：让 Agent 少废话，还能省 tokens\r https://www.bilibili.com/video/BV1hdV96rEiV\r
- 沧海九粟: 🧲 Claude Code 自动：长程任务的保障 Auto Mode\r https://www.bilibili.com/video/BV1Ky9yBzEBY\r
- 二一的笔记: 一口气搞懂 Notion Custom Agent（测评与教程）\r https://www.bilibili.com/video/BV16eAGzbENv\r \r
B站学习 (第2轮)\r
学习时间: 2026-06-02 09:33\r \r
- AIlazy俊: 66K 星的 Caveman：让 Agent 少废话，还能省 tokens\r https://www.bilibili.com/video/BV1hdV96rEiV\r
- 沧海九粟: 🧲 Claude Code 自动：长程任务的保障 Auto Mode\r https://www.bilibili.com/video/BV1Ky9yBzEBY\r
- 二一的笔记: 一口气搞懂 Notion Custom Agent（测评与教程）\r https://www.bilibili.com/video/BV16eAGzbENv\r
Usage Guidance
Review before installing. This does not show clear malware behavior, but it can execute code from a specific local Windows directory and save what the user passes into it. Install only if you understand and trust the local D:\\coze-local\\db learn module, are comfortable with local knowledge-base retention, and can tolerate the broad "agent" trigger.
Capability Assessment
Purpose & Capability
The stated purpose is a tutorial/resource skill about building AI agents, but the Python entry point imports a local KnowledgeBase component and persists the invocation parameter; that storage behavior is not clearly disclosed in the tutorial-style skill text.
Instruction Scope
The trigger phrase includes the broad word "agent", which can activate the skill during ordinary discussions about agents rather than only when the user asks for this specific tutorial.
Install Mechanism
The artifact contains only SKILL.md and one Python file, with no declared dependency or packaged learn module; the code instead relies on an absolute Windows path under D:\\coze-local\\db.
Credentials
Prepending an absolute local path to sys.path before importing learn.KnowledgeBase is broader and less portable than the disclosed tutorial function, and it could run whatever module exists at that local path.
Persistence & Privilege
The run function stores the user-supplied parameter or default tutorial text into a local knowledge base, then closes it; there is no clear user-facing retention notice, opt-in, scope, or deletion guidance.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install auto-agent-4974 - After installation, invoke the skill by name or use
/auto-agent-4974 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
auto-agent-4974 v1.0.0
- 发布首个版本，整合B站2026年最新Agent智能体搭建全流程教程，适合入门到实战。
- 支持手把手引导用户打造个人专属AI智能体，覆盖技能自进化、任务保障等核心知识点。
- 收录多位B站作者的实用Agent开发经验与视频，包含Notion Custom Agent、Caveman Agent等内容。
- 用户可通过关键词“agent”或教程名称直接触发技能学习和应用。
Metadata
Frequently Asked Questions
What is Auto Agent 4974?
Provides a step-by-step tutorial on building personal AI agents based on 2026 Bilibili resources, covering entry to advanced development. It is an AI Agent Skill for Claude Code / OpenClaw, with 44 downloads so far.
How do I install Auto Agent 4974?
Run "/install auto-agent-4974" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Auto Agent 4974 free?
Yes, Auto Agent 4974 is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Auto Agent 4974 support?
Auto Agent 4974 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Auto Agent 4974?
It is built and maintained by 534422530 (@534422530); the current version is v1.0.0.
More Skills