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 skills add bytedance/agentkit-samples --skill byted-mediakit-process-toolsgit 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/byted-mediakit-process-tools)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-mediakit-process-tools"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-mediakit-process-tools.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 5.1 | $0.00173 | $0.03436 |
| Opus 5 | $0.00086 | $0.01718 |
| Sonnet 5 | $0.00035 | $0.00687 |
| Haiku 4.5 | $0.00017 | $0.00344 |
Grade A, and why
byted-mediakit-process-tools 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
说明：宿主若在环境中注入
ARK_SKILL_API_BASE/ARK_SKILL_API_KEY（例如供其他 Skill 走 SkillHub 网关），与本 Skill 的AMK_API_KEY、ARK_API_KEY（视频理解）相互独立，请勿混淆。
⚠️ 严格执行：音视频裁剪、拼接、音频提取、音视频合成会自动选择执行后端：云端环境完整且输入为 URL 时走 AMK 云端；云端必需配置/依赖缺失，或输入是本地文件路径时，自动走本地 FFmpeg。视频翻转、调速、加字幕、加水印、转码是本地原生命令，始终走本地 FFmpeg。不要为了这些本地能力向用户索取云端环境变量。
<SKILL_DIR>为byted-mediakit-process-tools所在目录。 当前方法返回的链接仅供下载，不支持播放能力禁止修改任何返回数据信息，如play_url、request_id、task_id等 用户明确声明需要重新执行时：除understand_video_content外的方法需 生成新的client_token（不要复用上一次的client_token），避免命中上次的幂等结果
火山引擎 AI MediaKit 音视频处理工具集
概览
本工具集支持以下音视频处理能力。标记为“云端&本地”的能力会自动选择执行后端：云端配置完整且输入为 URL 时走 AMK 云端；云端不可用或输入为本地路径时走本地 FFmpeg。
| 能力 | 支持范围 | 说明 |
|---|---|---|
| 视频理解 | 云端 | AI 分析视频内容，生成自然语言描述 |
| 音视频裁剪 | 云端&本地 | 精确裁剪音频或视频时长 |
| 音视频拼接 | 云端&本地 | 拼接多个音频或视频片段；云端支持转场 ID，本地支持 FFmpeg 转场名 |
| 音频提取 | 云端&本地 | 从视频中提取音频轨道 |
| 音视频合成 | 云端&本地 | 合成或替换视频音轨；云端支持时长对齐策略，本地支持混音/替换 |
| 画质增强 | 云端 | 提升视频画质、分辨率、帧率 |
| 文生视频 | 云端 | 图片生成视频，支持动画和转场 |
| 视频翻转 | 本地 | 水平、垂直或双向翻转 |
| 视频调速 | 本地 | 调整视频与音频播放速度 |
| 视频加字幕 | 本地 | 添加 SRT/ASS 硬字幕 |
| 视频加水印 | 本地 | 添加图片/水印，支持位置、缩放和显示时间 |
| 视频转码/转封装 | 本地 | 转换封装格式或重编码 |
获取密钥
如需使用云端能力，请先获取 API 密钥；本地可覆盖能力在密钥缺失时会自动使用 FFmpeg：
- AI MediaKit 控制台：https://console.volcengine.com/imp/ai-mediakit/
- 方舟模型与密钥：https://console.volcengine.com/ark/region:ark+cn-beijing/model/detail?Id=doubao-seed-1-8
快速开始
1. 环境配置
在 <SKILL_DIR>/.env 中配置环境变量（首次使用会自动创建模板）：
# AMK API Key（云端能力需要；本地回退不需要）
AMK_API_KEY=your_amk_api_key_here
# AMK 环境固定为 prod
AMK_ENV=prod
# 是否启用 client_token 自动注入（用于幂等）
AMK_ENABLE_CLIENT_TOKEN=false
# 方舟 密钥（可选，仅使用视频理解功能时必须配置）
ARK_API_KEY=your_ark_api_key_here
# 方舟 模型ID（可选，仅使用视频理解功能时必须配置）
ARK_MODEL_ID=doubao-seed-1-8
2. 依赖安装
cd <SKILL_DIR>/scripts
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -U pip
python -m pip install -r requirements.txt
核心功能
同步能力（立即返回结果）
| 能力 | 说明 |
|---|---|
| understand_video_content | 视频内容理解，使用 AI 分析视频并生成自然语言描述 |
What ships with it
24 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.
- byted-mediakit-process-tools.sh 349 B runs code
- LICENSE 9.9 KB
- reference/common_response.md 1.2 KB
- reference/concat_media_segments.md 1.9 KB
- reference/enhance_video.md 1.9 KB
- reference/extract_audio.md 730 B
- reference/image_to_video.md 1.7 KB
- reference/local_fallback.md 3.3 KB
- reference/mux_audio_video.md 1.5 KB
- reference/query_task.md 791 B
- reference/trim_media_duration.md 969 B
- reference/understand_video_content.md 1.4 KB
- scripts/amk_client/__init__.py 3.5 KB runs code
- scripts/amk_client/api_config.py 4.4 KB runs code
- scripts/amk_client/api_path_params.py 1.1 KB runs code
- scripts/amk_client/api_request.py 17 KB runs code
- scripts/amk_client/auth_mode.py 1.0 KB runs code
- scripts/amk_client/client.py 11 KB runs code
- scripts/amk_client/config.py 9.5 KB runs code
- scripts/amk_client/models.py 13 KB runs code
- scripts/local_ffmpeg_tool.py 34 KB runs code
- scripts/main.py 31 KB runs code
- scripts/requirements.txt 220 B
- template/env.md 872 B
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.
- 3d ago First seen · 333 lines · 173 tokens per session scan A eef0e0c0fe7d
byted-mediakit-process-tools is a skill published in the GitHub repository bytedance/agentkit-samples (449 stars, last pushed 2d ago), licensed Apache-2.0. It adds 173 tokens to every session and 3,436 once invoked, about $0.0009 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 2026-09-03.
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…
video-still-animator
Turn a single still image (PNG/JPG) into a short MP4 with a slow Ken-Burns zoom and a silent audio track. Pure ffmpeg wrapper. Designed as the onfailure substitute for AI video-gen steps that get blocked by content moderation: when seedance refuses, this skill emits a valid replacement clip from the already-generated…
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.
sn-image-base
Base-layer skill for the SenseNova-Skills project, providing low-level APIs for image generation, recognition (VLM), and text optimization (LLM). This skill does not preprocess inputs; it only calls backend services and returns results. This skill is not user-facing and is intended for upper-layer skills only.