bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/bytedance/agentkit-samples/video-breakdown-skillnpx skills add bytedance/agentkit-samples --skill video-breakdown-skillgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bytedance/agentkit-samples/video-breakdown-skill)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/video-breakdown-skill"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/video-breakdown-skill.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00084 | $0.00587 |
| Opus 5 | $0.00042 | $0.00293 |
| Sonnet 5 | $0.00017 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
video-breakdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
视频分镜拆解 (Video Breakdown)
概述
视频分镜拆解技能通过本机 FFmpeg 将视频自动拆解为逐帧分镜，提供每个镜头的关键帧图片和时间信息。无需外部后端服务。
前置要求
- 本机安装 FFmpeg：
brew install ffmpeg
使用步骤
方式一：视频 URL 直接处理
python scripts/process_video.py "https://example.com/video.mp4"
方式二：本地文件上传后处理
# 1. 上传本地视频到 TOS
python scripts/video_upload.py "/path/to/video.mp4"
# 2. 用返回的 video_url 处理
python scripts/process_video.py "<video_url>"
环境变量
| 变量名 | 必需 | 描述 |
|---|---|---|
FFMPEG_BIN |
否 | FFmpeg 路径，默认 ffmpeg |
FFPROBE_BIN |
否 | FFprobe 路径，默认 ffprobe |
VOLCENGINE_ACCESS_KEY |
上传时需要 | 火山引擎 Access Key |
VOLCENGINE_SECRET_KEY |
上传时需要 | 火山引擎 Secret Key |
DATABASE_TOS_BUCKET |
否 | TOS 存储桶名称 |
DATABASE_TOS_REGION |
否 | TOS 区域，默认 cn-beijing |
输出格式
{
"task_id": "xxx",
"duration": 30.5,
"resolution": "1920x1080",
"segment_count": 12,
"segments": [
{
"index": 1,
"start": 0.0,
"end": 3.0,
"frame_paths": ["path/to/frame.jpg"]
}
]
}
故障排除
| 问题 | 解决方案 |
|---|---|
| FFmpeg not found | 安装 FFmpeg: brew install ffmpeg |
| 上传失败 | 检查 AK/SK 配置和 TOS 存储桶 |
| 视频下载失败 | 确认 URL 有效且可公开访问 |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 71 lines · 84 tokens per session scan A 8d8df61a7faa
video-breakdown is a skill published in the GitHub repository bytedance/agentkit-samples (446 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 587 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotifyplayer. Use when the user asks to play music, search for a song, skip a track, pause playback, check what is currently playing, control Spotify, list audio devices, or manage a Spotify queue from the terminal.
srt-from-script
Build an SRT subtitle file from a 3-shot short-drama script (ai-video-script OUTPUT FORMAT). Reads each SHOTN block's DURATIONS + VOICEOVER, emits cumulative-timestamped SRT cues. Pure text-processing, no LLM, no network. Used by meta-short-drama between merge and the final subtitle-burn step.
omh-image-cards
This is a Hermes-native img-summary workflow skill.