ByteDance MediaKit Audio Agent Skill

Extracts standardized audio metadata and separates vocal tracks from background audio using MediaKit CLI.

Context cost
6.7k tokensestimated from the bundle, loaded when it triggers
Bundle
6 files · 26.7 kBtext throughout, nothing executable
Licence
MITthe author’s own terms
Last change
—v0.2.1
Servers it uses
Noneruns standalone

What it does

面向音频文件或视频中的音轨,处理语音边界定位、音频媒资信息探测、音频转码与码流封装适配、人声与背景声分离等目标。若对象和目标族已明确属于音频内容理解、音频转码、音频格式治理或音轨分离,但具体做法不确定,可先加载本 Skill 探索;若只说有音频而未说明业务目标,应先澄清。音频裁剪、拼接、调速、淡入淡出、混音、从视频抽取音轨或音视频合流等编辑合成诉求应路由到 editing;字幕生成、视频理解、视频增强等应路由到 video。

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.

content

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.md3.1 kB · preview
--- name: byted-mediakit-audio version: 0.2.1 license: MIT permissions: - shell metadata: requires: bins: - mediakit-cli cliHelp: mediakit-cli audio --help product: mediakit-cli-doubao/skills domain: audio capability_count: 4 ---
17# audio 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 audio 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若只说有音频而未说明业务目标,应先澄清。音频裁剪、拼接、调速、淡入淡出、混音、从视频抽取音轨或音视频合流等编辑合成诉求应路由到 editing;字幕生成、视频理解、视频增强等应路由到 video。
29
30## 工具列表
31
32| 工具 | 说明 | 支持模式 | 命令 | 参考 |
33| --- | --- | --- | --- | --- |
34| detect-voice-activity | 用于语音端点识别。自动定位音频或视频文件中有效语音的起止时间。将人声和静音、背景噪声等无效片段区分开来。返回包含所有有效人声片段起止时间戳的列表。 | Cloud | mediakit-cli audio detect-voice-activity | [reference/detect-voice-activity.md](reference/detect-voice-activity.md) |
35| probe-audio-metadata | 探测输入音频 URL,输出标准化媒资元信息,用于获取音频元信息。 | Cloud | mediakit-cli audio probe-audio-metadata | [reference/probe-audio-metadata.md](reference/probe-audio-metadata.md) |
36| separate-voice | 用于人声背景声分离,可将音频或视频文件中的人声与背景音精准分离,输出为两个独立的音频文件。 | Cloud | mediakit-cli audio separate-voice | [reference/separate-voice.md](reference/separate-voice.md) |
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md139 words
Files6
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.

≈120
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
6,555
on trigger
The instruction body and 5 supporting files, read only when the skill fires.
3.3%
of a 200k window
Ten skills this size would take about 33% of the window before you open a file.
050k100k150k200k context window

6.7k 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

6 files, 26.7 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md3.1 kB
  • LICENSE1.1 kB
  • reference/detect-voice-activity.md4.4 kB
  • reference/probe-audio-metadata.md4.6 kB
  • reference/separate-voice.md4.7 kB
  • reference/transcode-audio.md8.8 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 6 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 Audio · 6.7k 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-audio/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/bytedance-mediakit-audio" ] && { [ ! -e .claude/skills/bytedance-mediakit-audio ] || { mv .claude/skills/bytedance-mediakit-audio "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/bytedance-mediakit-audio" .claude/skills/ && echo "Installed .claude/skills/bytedance-mediakit-audio"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add ahang1598/bytedance-mediakit-audio

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-audio/ 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-audio/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/bytedance-mediakit-audio" ] && { [ ! -e ~/.claude/skills/bytedance-mediakit-audio ] || { mv ~/.claude/skills/bytedance-mediakit-audio "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/bytedance-mediakit-audio" ~/.claude/skills/ && echo "Installed ~/.claude/skills/bytedance-mediakit-audio" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/bytedance-mediakit-audio/ 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-audio in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, bytedance-mediakit-audio.

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-audio

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