algorithmic-art
Generate deterministic SVG algorithmic artwork. Invoke when the user asks for geometric,…
Performs deep AI-powered analysis and understanding of long-form videos (up to 3 hours, 10GB) using Volcengine LAS large language models. Video analysis, video comprehension, and video summarization — generates comprehensive video summaries, video recaps, chapter breakdowns,
$ npx -y skills add bytedance/agentkit-samples --skill byted-las-long-video-understand --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/byted-las-long-video-understandContext preview
The summary Claude sees to decide when to auto-load this skill.
Performs deep AI-powered analysis and understanding of long-form videos (up to 3 hours, 10GB) using Volcengine LAS large language models. Video analysis, video comprehension, and video summarization — generates comprehensive video summaries, video recaps, chapter breakdowns,
name: byted-las-long-video-understand version: "1.0.1" description: "Performs deep AI-powered analysis and understanding of long-form videos (up to 3 hours, 10GB) using Volcengine LAS large language models. Video analysis, video comprehension, and video summarization — generates comprehensive video summaries, video recaps, chapter breakdowns, event timelines, key moments, and structured content indexing. Supports behavior detection, action detection, video annotation, video tagging, and video content recognition. Enables intelligent video question answering — ask questions about video content and get AI answers. Handles long meeting recordings, lecture videos, webinars, surveillance and security footage, movies, tutorials, and any long video that needs detailed understanding. Async processing with submit-poll workflow. Use this skill when the user wants to analyze or understand long videos (up to 3h/10GB) with LLM-based deep comprehension, summarize video content or generate recaps, extract chapters/key moments/timelines from videos, do video Q&A (ask questions about video content), detect actions/behaviors in videos, review meeting recordings/lectures/webinars, or get structured video descriptions."
基于大模型提供多维度、精细化的视频结构化理解。支持小时级(最大 3h)视频的全局理解、事件与行为识别、视频问答、高效摘要及结构化输出。
本 skill 主要采用:
> 详细参数与接口定义见 [references/api.md](references/api.md)。
复制此清单并跟踪进度:
执行进度: - [ ] Step 0: 前置检查 - [ ] Step 1: 初始化与准备 - [ ] Step 2: 预估价格 - [ ] Step 3: 提交异步任务 - [ ] Step 4: 轮询任务状态 - [ ] Step 5: 结果呈现
在接受用户的任务后,**不要立即开始执行**,必须首先进行以下环境检查: 1. **检查 `LAS_API_KEY` 与 `LAS_REGION`**:确认环境变量或 `.env` 中是否已配置。
2. **检查输入路径**:
3. **确认无误后**:才能进入下一步。
**环境初始化(Agent 必做)**:
# 执行统一的环境初始化与更新脚本(会自动创建/激活虚拟环境,并检查更新) source "$(dirname "$0")/scripts/env_init.sh" las_long_video_understand workdir=$LAS_WORKDIR
> 如果网络问题导致更新失败,脚本会跳过检查,使用本地已安装的 SDK 继续执行。
# 提前检查视频格式(避免参数错误) ./scripts/check_format.sh <local_path> # 本地使用 ffprobe 获取时长(无需上传即可预估价格) duration_sec=$(ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:noprint_section=1 <local_path>)
计算预估价格并等待用户确认后,再执行上传:
# 用户确认后,上传到 TOS lasutil file-upload <local_path>
上传成功后返回 JSON,取其中的 `tos_uri`(格式 `tos://bucket/key`)传给算子作为输入路径。
本 skill 按 token 计费,由于视频长且分析复杂,提交前无法精确预估费用。
1. 查阅 [references/prices.md](references/prices.md) 的说明。 2. 说明此任务产生的 token 量可能会非常大(特别是对于长视频)。 3. **将计费单价告知用户并强制暂停执行**,明确等待用户回复确认。在用户明确回复"继续"、"确认"等同意指令前,**绝对禁止**进入下一步(执行/提交任务)。提示:预估仅供参考,实际以火山账单为准。计费说明请参考 [Volcengine LAS 定价](https://www.volcengine.com/docs/6492/1544808)。
构造 `data.json`:
{
"video_url": "<url>",
"query": "请总结这个视频的主要内容",
"fps": 1.0,
"model_name": "doubao-seed-2-0-lite-260215"
}执行命令:
data=$(cat "$workdir/data.json") lasutil submit las_long_video_understand "$data" > "$workdir/submit.json" task_id=$(cat "$workdir/submit.json" | jq -r '.metadata.task_id') echo "Task ID: $task_id"
# 获取任务状态 lasutil poll las_long_video_understand "$task_id" > "$workdir/poll.json" cat "$workdir/poll.json" | jq -r '.metadata.task_status'
⚠️ **异步任务与后台轮询约束**:
mkdir -p "./output/${task_id}"
./scripts/poll_background.sh ${task_id} "./output/${task_id}" & disown脚本特性:
# 获取任务状态 lasutil poll las_long_video_understand "$task_id" > "$workdir/poll.json" cat "$workdir/poll.json" | jq -r '.metadata.task_status'
**处理结果**:
使用脚本自动生成结果展示(自动包含计费声明):
./scripts/generate_result.md.sh ${task_id} "./output/${task_id}" <estimated_price>**手动处理**:
# 解析最终摘要
cat "$workdir/poll.json" | jq -r '.data.final_summary'
# 可选:保存 clips 详情到本地
cat "$workdir/poll.json" | jq '.data.clips' > "./output/${task_id}/clips_detail.json"**向用户展示**: 1. 使用生成的 markdown 展示 2. 呈现视频的 `final_summary`(最终摘要) 3. 如果有精彩片段问答或特定 query 回答,结合 `clips` 提取并展示 4. 自动包含计费声明 ✅
欢迎来到 AgentKit 代码工坊(Samples)仓库! AgentKit 是火山引擎推出的企业级 AI Agent 开发平台,为开发者提供完整的 Agent 构建、部署和运维解决方案。平台通过标准化的开发工具链和云原生基础设施,显著降低复杂智能体应用的开发部署门槛。 本代码库包含了一系列示例和教程,帮助您理解、实现和集成 AgentKit 的各项功能到您的应用中。
Generate deterministic SVG algorithmic artwork. Invoke when the user asks for geometric,…
Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution…
根据文字描述生成视频,一个生成图片和视频的工作流技能。依赖 skills: byted-web-search, image-generate, video-generate。注意:此…
Manage AgentKit skills, SkillHub/skillhub, skill centers, and skill spaces. Use this skill…
Upload files or directories to TOS-compatible object storage for Volcano Engine or BytePlus…
根据用户的功能需求,完成与 VeADK-Go 相关的功能; 包括:直接根据需求生成 Agent;将Enio Agent转换为VeADK-Go Agent。