Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器clawhub未标认证来源可访问clear审计提醒

sh-lawschool-video-autopilotsh 法学院视频自动驾驶仪

Agent Skill

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

总安装

8,339

周安装

344

GitHub Stars

公开资料未说明

下载量

2,724
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sh-lawschool-video-autopilot(sh 法学院视频自动驾驶仪)
来源仓库:https://github.com/vanishedzhou/sh-lawschool-video-autopilot
安装命令:
openclaw skills install sh-lawschool-video-autopilot
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install sh-lawschool-video-autopilot

简介

sh-lawschool-video-autopilot 用于自动播放律师云学院的在线法律课程视频。

  • 适合在 OpenClaw 中批量观看培训视频列表时使用。
  • 通过安装命令 openclaw skills install sh-lawschool-video-autopilot 集成。
  • 使用前应确认目标网站访问权限及是否符合平台使用政策。
  • 适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

SKILL.md

name
lawschool-video-autopilot
description
Automate online law course video watching on 律师云学院 (lawschool.lawyerpass.com). Use when a user needs to automatically play through a list of training videos, handle course enrollment ("选修并学习"), detect video completion, switch to the next course, and send progress notifications. Supports both 培训计划 (training plan) courses and 课程广场 (course square) free-choice courses. Requires Chrome browser connected via OpenClaw Browser Relay.

律师云学院视频自动播放

Automates video playback across multiple courses on lawschool.lawyerpass.com using the browser tool (Chrome profile via Browser Relay) and a persistent state file + cron job for long-running monitoring.

Architecture

  • State file (video_state.json): tracks progress, current video, queue
  • Cron job (video-check-loop): fires every 8 minutes, checks video status, switches when done
  • Browser tool: profile=chrome, targetId from state file

Quick Start

  1. Read references/workflow.md for the full step-by-step procedure
  2. Read references/known-issues.md for critical gotchas before starting

Key Facts

  • Site: https://lawschool.lawyerpass.com
  • Course list page: /course/list
  • Course detail URL: /course/detail?courseId=<id>
  • Card selector: app-lesson-card.square-item
  • Video element: document.querySelector('video')

Getting courseId (critical)

Course cards use Angular Router — no href on <a> tags. Intercept history.pushState:

let captured = '';
const orig = window.history.pushState.bind(window.history);
window.history.pushState = function(s, t, url) { captured = url; orig(s, t, url); };
[...document.querySelectorAll('app-lesson-card.square-item')]
  .find(c => c.textContent.includes('课程标题关键词'))
  ?.querySelector('a')?.click();
return captured; // returns "/course/detail?courseId=d5b19f94..."

Then navigate to https://lawschool.lawyerpass.com + captured path.

Enrollment Gate (⚠️ critical)

Some courses from 课程广场 require enrollment before video appears:

// Step 1: Check and click enrollment button
const btn = [...document.querySelectorAll('button, a, [class*=btn]')]
  .find(el => el.textContent.includes('选修并学习'));
if (btn) { btn.click(); return 'clicked_enroll'; }
return 'no_enroll_btn';

If clicked → wait 3s → confirm dialog:

const confirm = [...document.querySelectorAll('button, [class*=btn], [class*=confirm]')]
  .find(el => el.textContent.match(/确定|确认|OK/));
confirm?.click();

Wait 3s more, then video.play().

Video Status Check

const v = document.querySelector('video');
if (!v) return JSON.stringify({ found: false, url: location.href });
return JSON.stringify({
  found: true,
  ct: Math.round(v.currentTime),
  dur: Math.round(v.duration),
  paused: v.paused,
  ended: v.ended,
  url: location.href
});

Completion condition: ended === true OR ct >= dur - 3

Note: Some videos stop with ended=false but ct === dur — always check both.

Cron Job Setup

{
  "schedule": { "kind": "every", "everyMs": 480000 },
  "sessionTarget": "isolated",
  "payload": { "kind": "agentTurn", "timeoutSeconds": 120 }
}

⚠️ Do NOT use everyMs < 300000 (5 min) — causes API rate limit errors.

State File Schema

See references/state-schema.md for the full video_state.json schema. Use scripts/lawschool_init_state.py to generate an initial state file.

Notifications

Use message tool on every video complete and every video start:

  • Complete: ✅ 播完:{title}({done}/{total})
  • Start: ▶ 开始:{title},{duration},第{done+1}/{total}门
  • All done: 🎉 全部{total}门完成!

Reference Files

FileWhen to read
references/workflow.mdFull step-by-step setup and monitoring loop
references/state-schema.mdState file fields and update rules
references/known-issues.mdBefore starting — critical gotchas

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

93.67%
按下载量换算2,552

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills