ByteDance MediaKit Video Processing Agent Skill

Processes, enhances, analyzes, and extracts structured insights from video assets using cloud-based AI vision and audio models.

Context cost
56.6k tokensestimated from the bundle, loaded when it triggers
Bundle
31 files · 226.3 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—v0.2.1
Servers it uses
Noneruns standalone

What it does

面向视频文件的智能处理、媒资理解、画质治理与画质检测、抽帧、隐私保护、字幕与水印处理、精彩片段与高光拆条分析生成、剧情结构化与剧本整理、场景与语义分段、画面文字识别、视频转码转封装及人像或绿幕抠像等目标。若对象和目标族已明确属于视频增强、视频分析理解、视频内容结构化、视频字幕识别或擦除、视频隐私脱敏、视频媒资探测或分发适配,但具体能力不确定,可先加载本 Skill 探索;若只说有视频而未说明业务目标,应先澄清。明确要裁剪、拼接、叠加字幕、混音、合流、调速、转场、画面旋转翻转、视频滤镜或多视频拼画面的成片编辑诉求应路由到 editing;单张图片处理应路由到 image;音频转码、人声分离或语音端点检测应路由到 audio。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

data science

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md12.4 kB · preview
--- name: byted-mediakit-video version: 0.2.1 license: MIT permissions: - shell metadata: requires: bins: - mediakit-cli cliHelp: mediakit-cli video --help product: mediakit-cli-doubao/skills domain: video capability_count: 29 ---
17# video MediaKit Skill
18
19## 使用规则
20
211. 先读取 ../byted-mediakit-shared/SKILL.md,执行统一前置检查;该 Skill 缺失时停止并报告当前 Skill 包不完整。
222. 只从下表选择 video 域工具;相似能力按各工具“能力描述”和参数边界区分。
233. 执行前按需读取对应 reference;参数与结果说明来自同一份已审核文案,完整机器合同以当前 CLI --schema 为准。
244. 缺少必填参数、鉴权环境变量或真实输入资源时,向用户索取;通用可选字段只能透传用户明确提供的值,其他可选字段可由明确意图准确确定,但不得伪造。
25
26## 澄清与跨域路由
27
28若只说有视频而未说明业务目标,应先澄清。明确要裁剪、拼接、叠加字幕、混音、合流、调速、转场、画面旋转翻转、视频滤镜或多视频拼画面的成片编辑诉求应路由到 editing;单张图片处理应路由到 image;音频转码、人声分离或语音端点检测应路由到 audio。
29
30## 工具列表
31
32| 工具 | 说明 | 支持模式 | 命令 | 参考 |
33| --- | --- | --- | --- | --- |
34| add-video-invisible-watermark | 用于视频暗水印添加。在不影响视频画面视觉质量与完整性的前提下,将一串数字信息隐藏式地嵌入视频文件中。适用于视频版权保护、内容泄露溯源、文件真实性校验等场景。 | Cloud | mediakit-cli video add-video-invisible-watermark | [reference/add-video-invisible-watermark.md](reference/add-video-invisible-watermark.md) |
35| analyze-video-highlights | 支持短剧 Miniseries 和小游戏 Game 两种分析模型,用于高光片段提取,并输出精准时间戳、高光打分、OCR 文本和画面描述,供二次开发或内容分析。 | Cloud | mediakit-cli video analyze-video-highlights | [reference/analyze-video-highlights.md](reference/analyze-video-highlights.md) |
36| analyze-video-storyline | 用于剧情故事线分析,基于大模型视频理解分析单个或多个长视频并生成结构化剧情数据。分析结果包含两部分:按时间顺序排列的剧情片段,以及基于视频片段整理和归纳出的高光故事线。 | Cloud | mediakit-cli video analyze-video-storyline | [reference/analyze-video-storyline.md](reference/analyze-video-storyline.md) |
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md501 words
Files31
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈140
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
56,435
on trigger
The instruction body and 30 supporting files, read only when the skill fires.
28.3%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

56.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

31 files, 226.3 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md12.4 kB
  • LICENSE1.1 kB
  • reference/add-video-invisible-watermark.md5.5 kB
  • reference/analyze-video-highlights.md6.4 kB
  • reference/analyze-video-storyline.md8.2 kB
  • reference/asr-subtitles.md6.1 kB
  • reference/assess-video-quality.md3.6 kB
  • reference/drama-recap-vertical.md13.1 kB
  • reference/drama-recap.md11.4 kB
  • reference/drama-script.md5.2 kB
  • reference/enhance-video-fast.md6.2 kB
  • reference/enhance-video-generative.md5.9 kB
  • reference/enhance-video.md8.1 kB
  • reference/erase-video-subtitle-pro.md10.0 kB
  • reference/erase-video-subtitle.md4.5 kB
  • reference/extract-frames.md8.0 kB
  • reference/extract-video-invisible-watermark.md3.3 kB
  • reference/face-blur-video.md6.0 kB
  • reference/generate-highlights-microdrama.md12.0 kB
  • reference/generate-highlights-minigame.md8.8 kB
  • reference/generate-highlights-movie.md10.3 kB
  • reference/martencode-video.md12.9 kB
  • reference/matte-greenscreen-video.md4.4 kB
  • reference/matte-portrait-video.md4.6 kB
  • reference/probe-video-metadata.md5.0 kB
  • reference/remux-video.md6.2 kB
  • reference/segment-scenes.md6.9 kB
  • reference/semantic-segment.md5.6 kB
  • reference/transcode-video.md11.3 kB
  • reference/video-ocr.md5.2 kB
  • reference/video-understand-router.md8.1 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 31 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# ByteDance MediaKit Video Processing · 56.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/bytedance-mediakit-video-processing/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/bytedance-mediakit-video-processing" ] && { [ ! -e .claude/skills/bytedance-mediakit-video-processing ] || { mv .claude/skills/bytedance-mediakit-video-processing "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/bytedance-mediakit-video-processing" .claude/skills/ && echo "Installed .claude/skills/bytedance-mediakit-video-processing"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ahang1598/bytedance-mediakit-video-processing

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/bytedance-mediakit-video-processing/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/bytedance-mediakit-video-processing/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/bytedance-mediakit-video-processing" ] && { [ ! -e ~/.claude/skills/bytedance-mediakit-video-processing ] || { mv ~/.claude/skills/bytedance-mediakit-video-processing "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/bytedance-mediakit-video-processing" ~/.claude/skills/ && echo "Installed ~/.claude/skills/bytedance-mediakit-video-processing" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/bytedance-mediakit-video-processing/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as byted-mediakit-video in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, bytedance-mediakit-video-processing.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version0.2.1
Publishedno release date on file
PriceFree
Referenceahang1598/bytedance-mediakit-video-processing

Versions

v0.2.1 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v0.2.1
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v0.2.1 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill