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-vod-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-vod-process-tools)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-vod-process-tools"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-vod-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 | $0.00174 | $0.03555 |
| Opus 5 | $0.00087 | $0.01777 |
| Sonnet 5 | $0.00035 | $0.00711 |
| Haiku 4.5 | $0.00017 | $0.00356 |
Grade A, and why
byted-vod-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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Volcengine VOD Tools
前置条件
- Python：确认
python --version≥ 3.6 - 环境变量（必需，也可通过工作目录下的
.env文件配置，脚本会自动加载）：VOLCENGINE_ACCESS_KEY— 火山引擎 Access KeyVOLCENGINE_SECRET_KEY— 火山引擎 Secret KeyVOD_SPACE_NAME— VOD 空间名称
- 依赖：脚本依赖
python-dotenv
参数传入方式
所有脚本支持两种 JSON 参数传入方式：
- 内联 JSON（适合简单参数）：
python script.py '{"key":"value"}' - 文件引用（推荐，避免 shell 转义问题）：
python script.py @params.json
@ 前缀表示从文件读取 JSON 内容，文件路径相对于当前工作目录。
结果交付规则
- 提交异步任务成功后会返回异步任务id，字段为
VCCreativeId或TaskId，在给用户交付最终产物时，必须包含异步任务id - 在展示最终产物链接时，禁止随意修改链接内容
- 优先将产物链接提供给用户
工作流程
1) 识别输入视频类型（必要时先上传拿 vid://...）
后续所有处理脚本优先使用 VOD 侧资源引用：
- Vid：
vid://vxxxx（或部分脚本接受裸vxxxx并自动补vid://） - DirectUrl / FileName：
directurl://<vod_file_name>（媒体类任务用DirectUrl时会要求FileName + SpaceName）
当用户提供的是以下输入之一，需要先执行上传逻辑，拿到 Vid 后再继续：
- 本地文件路径：如
/path/to/a.mp4 http/https链接：如https://example.com/a.mp4（会走 URL 拉取上传，并轮询上传结果）
统一用 scripts/upload_media.py：
python <SKILL_DIR>/scripts/upload_media.py "<local_file_path_or_http_url>" [space_name]
脚本输出中 Source 字段即 vid://...，可直接作为后续处理输入。
安全限制：本地文件上传仅允许 workspace/、userdata/ 和 /tmp 目录下的文件。
2) 识别用户意图 → 选择对应处理脚本
根据用户需求，按以下决策树选择脚本：
| 用户意图 | 脚本 |
|---|---|
| 多个视频/音频合成一个（顺序拼接） | stitching |
| 截取视频/音频的某个时间片段 | clipping |
| 加速/慢放/变速 | speedup |
| 镜像/上下翻转/左右翻转 | flip |
| 多张图片串联生成视频 | image_to_video |
| 替换/叠加视频的背景音乐 | compile |
| 只要视频里的音频轨 | extract_audio |
| 多条音频同时叠加播放（混音） | mix_audios |
| 分离人声和伴奏/背景音 | voice_separation |
| 去除环境噪音/电流杂音/风噪 | noise_reduction |
| 模糊/低画质视频修复（压缩伪影/噪点/划痕） | quality_enhance |
| 低分辨率视频提升（如 720P→1080P） | super_resolution |
| 低帧率视频插帧提升流畅度（如 30fps→60fps） | interlacing |
| 语音识别/ASR/提取视频中的文字对白 | asr_speech_to_text |
| OCR 文字提取/识别视频中的屏幕文字 | ocr_text_extract |
| 擦除视频硬字幕 | subtitle_removal |
| 给视频添加/嵌入字幕（烧录字幕） | add_subtitle |
| 视频场景分割/智能切片 | intelligent_slicing |
| 人像抠图/人像分割 | portrait_matting |
| 绿幕抠像/绿屏抠像 | green_screen |
| AI 漫剧转绘（漫画风/3D卡通风格） | comic_style |
| 短剧高光剪辑/精彩片段提取 | highlight |
| AI 视频翻译（字幕/语音/面容翻译） | video_translation |
| 查询翻译项目状态/重启翻译轮询 | poll_translation |
| 查询翻译项目列表 | list_translation |
| AI 解说视频生成（短剧解说/二创） | drama_recap |
| AI 剧本还原（视频转结构化剧本） | drama_script |
| 查询媒资信息（Vid 详情+播放地址） | get_media_info |
What ships with it
60 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.
- LICENSE 9.9 KB
- references/00-billing-instructions.md 1.5 KB
- references/01-stitching.md 1.8 KB
- references/02-clipping.md 995 B
- references/03-flip.md 932 B
- references/04-speedup.md 1.1 KB
- references/05-image-to-video.md 1.7 KB
- references/06-compile.md 1.6 KB
- references/07-extract-audio.md 686 B
- references/08-mix-audios.md 943 B
- references/09-add-sub-video.md 1.9 KB
- references/10-voice-separation.md 1.3 KB
- references/11-noise-reduction.md 1.1 KB
- references/12-quality-enhance.md 1004 B
- references/13-super-resolution.md 1.5 KB
- references/14-interlacing.md 1023 B
- references/15-asr-speech-to-text.md 1.7 KB
- references/16-ocr-text-extract.md 845 B
- references/17-subtitle-removal.md 888 B
- references/18-add-subtitle.md 2.9 KB
- references/19-intelligent-slicing.md 1.2 KB
- references/20-portrait-matting.md 1.0 KB
- references/21-green-screen.md 1010 B
- references/22-comic-style.md 2.5 KB
- references/23-highlight.md 3.6 KB
- references/24-video-translation.md 9.6 KB
- references/25-drama-recap.md 7.4 KB
- references/26-drama-script.md 4.3 KB
- references/27-get-media-info.md 1.5 KB
- scripts/add_subtitle.py 2.1 KB runs code
- scripts/api_manage.py 53 KB runs code
- scripts/asr_speech_to_text.py 1.7 KB runs code
- scripts/clipping.py 1.6 KB runs code
- scripts/comic_style.py 5.9 KB runs code
- scripts/compile.py 2.0 KB runs code
- scripts/drama_recap.py 12 KB runs code
- scripts/drama_script.py 7.0 KB runs code
- scripts/extract_audio.py 1.5 KB runs code
- scripts/flip.py 1.5 KB runs code
- scripts/get_media_info.py 4.4 KB runs code
- scripts/green_screen.py 1.8 KB runs code
- scripts/highlight.py 5.3 KB runs code
- scripts/image_to_video.py 1.8 KB runs code
- scripts/intelligent_slicing.py 1.8 KB runs code
- scripts/interlacing.py 2.0 KB runs code
- scripts/list_translation.py 4.7 KB runs code
- scripts/log_utils.py 1.5 KB runs code
- scripts/mix_audios.py 1.5 KB runs code
- scripts/noise_reduction.py 1.6 KB runs code
- scripts/ocr_text_extract.py 1.5 KB runs code
- scripts/poll_media.py 1.5 KB runs code
- scripts/poll_translation.py 3.3 KB runs code
- scripts/poll_vcreative.py 1.3 KB runs code
- scripts/portrait_matting.py 1.9 KB runs code
- scripts/quality_enhance.py 1.8 KB runs code
- scripts/speedup.py 2.0 KB runs code
- scripts/stitching.py 2.1 KB runs code
- scripts/subtitle_removal.py 1.7 KB runs code
- scripts/super_resolution.py 2.5 KB runs code
- scripts/upload_media.py 7.3 KB runs code
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 · 269 lines · 174 tokens per session scan A f26ac7cc7390
byted-vod-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 174 tokens to every session and 3,555 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.