Agent skill

Mc Mix Intent

by jtydhr88 in jtydhr88/music-composition-skills

Mix intent as a handoff artifact (混音意图) - stating what a mix must achieve so a human engineer, a DAW, or a generative backend can all act on it, without prescribing EQ or compressor settings.

MITAuto-check passedFrontend & Design

Install Mc Mix Intent

skills CLI
$ npx skills add jtydhr88/music-composition-skills --skill mc-mix-intent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jtydhr88/music-composition-skills mc-mix-intent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jtydhr88/music-composition-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/music-composition/skills/mc-mix-intent .claude/skills/mc-mix-intent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mc-mix-intent
GitHub stars
151
Token cost
~2.2k tokens
SKILL.md length
520 words
Files
2
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Mix intent as a handoff artifact (混音意图) - stating what a mix must achieve so a human engineer, a DAW, or a generative backend can all act on it, without prescribing EQ or compressor settings.

  • Works in 9 steps: 动笔前必填 → 五个领域与声场 → 四个目标 → …
  • Writing the mixintent block of an ARR-SPEC
  • SKILL.md covers 按任务读哪几节, 边界:什么不归这个 skill 管, 1. 动笔前必填 and 2. 五个领域与声场, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mc Mix Intent is an agent skill from jtydhr88/music-composition-skills. Mix intent as a handoff artifact (混音意图) - stating what a mix must achieve so a human engineer, a DAW, or a generative backend can all act on it, without prescribing EQ or compressor settings. The five domains (time, frequency, level, stereo, depth) and the imagined sound stage, the four goals (mood, balance, definition, interest), where balance is required and where depth must be consistent instead, the two legitimate reasons to be unbalanced, why sustained pads mask far more than short percussive hits, and how…

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `reference.md`).

It sits in Frontend & Design, covering Internationalization and Performance reviews. The repository describes itself as: Professional agent skills for composing and arranging popular music. The licence is MIT.

When your agent uses it

  • Writing the mixintent block of an ARR-SPEC
  • Handing a session to an engineer
  • Deciding what a backend can actually honor
  • Diagnosing a mix that is technically clean but emotionally wrong

Example prompts

  • “/mc-mix-intent”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. 动笔前必填
  2. 五个领域与声场
  3. 四个目标
  4. 平衡:在哪三处求平衡,在哪一处不求
  5. 掩蔽:为什么问题多半出在 pad 而不是鼓
  6. 参考曲目:本库的校准手段
  7. 各后端能吃多少
  8. 与 ARR-SPEC 的字段对应
  9. 写完后必过

What it can do on your machine

Read from SKILL.md and the folder at commit 7adca0c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Mc Mix Intent loads about 2.2k tokens when it runs. Until then it costs about 229 tokens; SKILL.md has 520 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~229
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jtydhr88/music-composition-skills at commit 7adca0c, republished under its MIT licence (© jtydhr88). 520 words, ~2,244 tokens.

Download SKILL.mdSave it as .claude/skills/mc-mix-intent/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mc-mix-intent
description
Mix intent as a handoff artifact (混音意图) - stating what a mix must achieve so a human engineer, a DAW, or a generative backend can all act on it, without prescribing EQ or compressor settings. The five domains (time, frequency, level, stereo, depth) and the imagined sound stage, the four goals (mood, balance, definition, interest), where balance is required and where depth must be consistent instead, the two legitimate reasons to be unbalanced, why sustained pads mask far more than short percussive hits, and how to use reference tracks as calibration. Use when writing the mix_intent block of an ARR-SPEC, handing a session to an engineer, deciding what a backend can actually honor, or diagnosing a mix that is technically clean but emotionally wrong. Grounded in masking (low masks high), critical bands, temporal masking, localization cues and the precedence effect. 混音意图、声场、掩蔽、临界频带、平衡、参考曲目、交接。

混音意图(Mix Intent)

这个 skill 产出的是意图,不是参数。

区别很要紧:

  • "人声 3 kHz +2 dB" 是参数——只有 DAW 能执行,换个后端就废了
  • "人声必须在最密的副歌里仍然是最清楚的元素,让路的是 pad 不是吉他" 是意图—— 人类工程师能执行、DAW 能执行、文本后端能部分执行、验收时能逐项核对

本库只到意图为止。 EQ 频点、压缩比、母带链出库到混音库。

按任务读哪几节

症状/任务读
填 ARR-SPEC 的 mix_intent§2–§4,然后 §8
混音技术上干净但"不对"§3.1 情绪
不知道该不该追求平衡§4(深度是要一致,不是平衡)
声部互相盖§5 掩蔽(多半是 pad 的问题,不是鼓的)
要交给混音师§2 五领域 + §8 的交接格式
判断某个后端能吃多少§7
想找参考曲目§6

边界:什么不归这个 skill 管

不归这里归哪
EQ 频点、压缩比、混响参数、总线链、母带出库 → 声音设计与混音库
频段冲突的改写型解法(换音区、减音符、交替)mc-texture-layering(先在那儿解,解不掉才来这儿)
前景/中景/背景的结构规划mc-texture-layering §2
人声该怎么唱mc-vocal-direction
和声/double 的声像具体方案mc-vocal-direction §6.2
音色本身怎么设计mc-sound-design
鼓组内部各件的左右与高低布局mc-rhythm-section §6(本 skill 的声场图只定鼓组整体坐在哪)

★ 与 mc-texture-layering 的分界(重复一遍,因为最容易混): texture-layering 的解法是"改写",mix-intent 的解法是"改混"。 能改写解决的不要留给混音。


1. 动笔前必填

必填问法
① 情绪一句话说这首混音要传达什么。先写这条,它否决后面所有决定
② 声场图每件乐器的左右位置和前后位置(§2)
③ 主角序列逐段写:这一段谁是最清楚的元素
④ 让路关系谁给谁让、在什么时候(ducking_map)
⑤ 参考曲目至少一首,且说得出参考它的哪一个具体方面

2. 五个领域与声场

混音过程必须涉及 5 个主要领域 (p0089):

#领域
1时间(Time)
2频率(Frequency)
3电平(Level)
4立体声(Stereo)
5深度(Depth)

立体声和深度共同构成"空间(Space)" (p0089)。

声场(Sound stage):

混音应该呈现在一个想象出来的声场当中,各个乐器具有一定的**左右(立体声)**和 **前后(深度)**位置 (p0089)。

这就是交接格式的骨架——一张声场图 + 五个领域各写一句,混音师就能开工。

左右与前后各靠什么线索(Howard & Angus):

  • 声像电位器给的是声级差(p0112);声级差主要对高频定位起作用,时间差主要对低频起作用, 700 Hz–2.8 kHz 是两种线索的过渡区,定位能力最弱(p0108)。 → 低频元素的 pan 基本无效,居中即可;要一件乐器"位置明确",它得有 3 kHz 以上的成分。 失效条件:耳机监听(头中定位,p0109)。
  • 前后靠直达声与混响声的比例和时间间隔(p0261、p0264);30 ms 内到达的延迟声不被单独听出, 定位仍在先导声(优先效应,p0110);初始延时 10–20 ms 是自然的前后间隔,50 ms 就是回声(p0346)。 → 写深度只给"近/中/远"三档,不写毫秒。

宏观 vs 微观 (p0089):

针对例
宏观混音影响整个混音的元素混音的频率平衡
微观混音每一个乐器声部单独处理人声听上去是否自然

本 skill 主要写宏观——微观是混音师的手艺,不该由编曲规格单规定死。


3. 四个目标

混音有 4 个基本目标 (p0089):

#目标
1情绪(Mood)
2平衡(Balance)
3清晰(Definition)
4趣味(Interest)

评价混音时,先看它在各主要领域表现出的连贯性和吸引力,然后再分析对每个目标的完成度 (p0089)。

3.1 ★ 情绪:它有否决权

情绪指混音能否表达出音乐中含有的情感因素 (p0090)。

两个反例,都很说明问题 (p0090):

  • 深度压缩、极端均衡、吵闹的失真、军鼓过于强烈的打击感 → 毁掉一首柔美的爵士
  • 甜美的人声混响、过于和谐的鼓组、轻柔的吉他 → 毁掉一首充满愤怒的重金属

注意第二个例子:每一项单独看都是"好混音"的标志,合起来却是错的。 技术上正确不等于情绪上正确。

只擅长处理某种音乐风格的混音师,遇到其他风格时效果往往不佳 (p0090)。

对本库的意义:生成模型也是"只擅长某种风格的混音师"—— 它会把任何输入往它见得最多的那种平衡上拉。 所以 mix_intent.mood 必须写死,且在 prompt 里靠前。

3.2 清晰

清晰度代表着声音听上去是否清楚、可辨认 (p0090)。

落到规格单上就是 §1③ 的主角序列:逐段说清楚谁必须是可辨认的。

清晰度本质上包含在分离度里:一件乐器清不清晰,看它能不能被听辨出来(可懂度),也看它听着自不自然,跟响不响关系不大 (p0260)。判据可以用两个反例检验:钢琴录得像从海底传出来,或者踩镲缺了基本的高频成分,这两种情况电平都可能正常,清晰度却塌了 (p0260)。

电平和清晰度常被当成简单正比:"乐器电平越大,清晰度越高" (p0100)。但这条只在乐器本身频率健康时成立;一件频率本身有缺陷的乐器,提升电平只会让它变大,不会让它变清晰 (p0100)。诊断"这个声部不够清晰"时,先判断是响度不够还是频率有洞,再决定该不该推电平。

3.3 趣味

趣味往往来自违反平衡(见 §4.3),但违反平衡只是趣味的一种极端形式,趣味的机制更底层:耳朵会适应,声音长时间不变,注意力就会掉,只有变化才能把耳朵重新抓回来 (p0091)。主歌副歌反复、音轨加倍、配器改变,本质上都是靠制造变化撑住这份注意力 (p0091)。

混音能在编曲结构之上再叠一层变化,判据是"哪个段落有、哪个段落没有",不涉及具体参数 (p0092):

  • 某个声部只在特定乐段自动化推起来
  • 某件乐器只在特定乐段出现(例:小号只在主歌反复时进)
  • 同一件乐器换乐段换处理,让明暗随段落变化
  • 副歌把整体压得更狠,允许贝司失真
  • 军鼓在不同乐段配不同混响

风格决定该做到什么程度:氛围音乐要让人有兴趣但不能太抓耳朵;trance 靠同一主题反复,变化反而要做得更精细才不腻 (p0092)。

写法:这些变化点按段落写进 focus_by_section[],不平衡类的写进 deliberate_imbalance[](§4.3),都不要写成全曲统一的状态。


4. 平衡:在哪三处求平衡,在哪一处不求

4.1 三个求平衡的领域 (p0090)
  1. 频率平衡:缺少中高频会让混音听上去浑浊、模糊,声像也显得更远 (p0090)。判据不是补到某个具体数值,是听感一旦落到"浑浊、模糊、变远"这三个词,就说明中高频欠了。

  2. 立体声声像平衡:靠电平平衡与频率平衡两条撑起来,尽量让乐器整体上左右对称(例如吉他、沙锤、伴唱人声)(p0252)。这里说的"平衡"针对整体声像分布,不要求单件乐器必须居中,居中反而是清晰度最差的位置(见 §2 定位线索)。

  3. 电平平衡:这里指相对电平,不是绝对电平。混音评估问的是"相对于其他乐器,这件乐器有多响",不是"这件乐器本身有多响";把监听音量整体开大解决不了相对电平的问题 (p0097)。相对电平通常由乐器在这一刻的重要性决定,随歌曲进展要跟着调,例如主音吉他独奏段的电平就该比伴奏段更高 (p0098)。 代价:如果为了让相对电平整齐,把所有敲击都压到同一电平,鼓组会听起来像"鼓机",丢掉原始力度带来的音色变化,电平平衡不等于电平统一 (p0388)。

4.2 ★ 深度要"一致",不要"平衡"

深度问题要做到一致,而非平衡 (p0090)。

例:如果底鼓声像近到贴脸,而军鼓远到邻居家,会使整个鼓组产生 在深度上极其扭曲的声像布局 (p0090)。

这条容易被误读成"深度也要居中"。不是—— 深度可以整体很近或整体很远,但同一个声源组内部必须一致。

自检动作:把乐器按组(鼓组、键盘组、弦乐组)分别列出深度值, 组内差异大于组间差异 → 错了。

物理上"同一组"就是共享同一套早期反射与混响拖尾:各声像位置的早期反射可以不同, 但拖尾的衰减率必须相同(Howard & Angus p0348–0350)。

4.3 两种可以不平衡的情况 (p0090)
  1. 做出创造性的音响效果
  2. 让歌曲产生趣味

例:Delgados《The Past That Suits You Best》里,混音师 Dave Fridmann 把鼓组和人声的声像完全设置到一个声道当中,创造出立体声上不平衡但很有魅力的效果 (p0090)。

富于趣味的不平衡通常是瞬间上的处理——例如舞曲的华彩段落里把一些低频信号加倍 (p0090)。

"通常是瞬间上的"这句是关键:不平衡是事件,不是状态。 全曲不平衡是错误,某一处不平衡是手法。

写法:不平衡要写进 mix_intent.deliberate_imbalance[], 带起止小节和理由。没写小节范围的不平衡,一律当成失误。


Show full SKILL.md (223 more words)Show less

5. 掩蔽:为什么问题多半出在 pad 而不是鼓

掩蔽的核心原则:响度高的声音会掩蔽响度低的声音; 一件乐器的频率范围会掩蔽另一件乐器的频率范围 (p0038)。

但真正有用的是下面这条时间维度的推论:

  • 打击乐器(如底鼓)发声时间短,掩蔽作用较小
  • 持续发声的乐器(如锯齿波 pad)会占满频谱和立体声空间,掩蔽作用大 (p0038)
  • ★ 提升密集 pad 声部的电平,比提升底鼓电平带来更多的掩蔽; pad 掩蔽底鼓是持续发生的大问题 (p0038)

Howard & Angus 把这几条讲成了机制:

  • 掩蔽向上延展:低频容易掩蔽高频,反过来弱得多(p0239)→ pad 的低频不只盖底鼓,它往上盖住一切, 所以"pad 低频留空"是第一刀。
  • 掩蔽声所在的临界频带内,掩蔽阈只比掩蔽声低约 20 dB(p0240)→ 让路要让到位: 同频段轻 20 dB 以上才算"让",轻 3 dB 只是变糊。
  • 时间掩蔽:响声停止后 100–200 ms 内,轻的起音仍听不见;反向(后掩蔽)只有约 10 ms,几乎不存在(p0241)。 短打击音本身的响度也按时长打折——200 ms 以内的声音越短听着越轻(p0095)。 → 人声或 hook 紧跟 crash/fill 进入时,要么留出 ≥ 200 ms,要么让它的第一个音自己够响。 自检:找每个主角的进入点,前 200 ms 内有没有更响的东西刚结束。

推论(本库的用法): 诊断"糊"的时候,先查持续音,不要先查打击乐。 直觉总是指向"鼓太大了",但按这条,元凶更可能是那个一直在响的 pad 或垫底吉他。

首选解法仍然在上游:让 pad 在低频区留空(改写,mc-texture-layering), 而不是靠侧链把它压下去(改混)。侧链是解决不掉时才用的。


6. 参考曲目:本库的校准手段

6.1 六种用法 (p0051–0052)
用法说明
作为模板仿效极佳的训练方法,但**"模仿是创新最大的敌人"**;且作品类型差异会让模仿失效
作为灵感来源混音开始前播放,启迪方向
陷入困境时的突破口研究自己的混音与参考的差别
作为成品参考完成后对照频响和电平
校准耳朵到不熟悉的环境先放熟悉的参考曲,摸清扬声器/房间/座位
评估扬声器放自己真正熟悉的作品,比商家放的流行乐管用
6.2 选择与陷阱
  • 参考曲目要匹配混音类型(做弦乐混音就找含弦乐的,做 chill-out 就找同类)(p0051)
  • 存成无损格式,不要 MP3 (p0051)
  • 最好包含事先选好的片段以便快速比较;可以加入未经混音的音轨 (p0051)
  • ★ 注意母带处理的影响 (p0052):经过母带的参考曲通常动态更质密 (一致的相对电平 + 更大的压缩),且频率特性可能是按专辑里最不理想的那首改过的
  • ★ 对比前先对齐响度:等响曲线随声压级变形,音量一降,低频和高频相对中频就被抑制, 声音变薄变暗(Howard & Angus p0091);声压级 +10 dB 响度约加倍(p0094)。 响一点的那个几乎总"听起来更好"——不对齐响度,比的是音量不是混音。

最后这条对本库特别重要:仓库的度量工具从成品音频反推指标, 测到的动态范围是母带之后的。所以拿参考曲的动态值当目标会系统性偏紧—— 这也是 probe_quality 要先报 bitrate 和高频截止的原因。


7. 各后端能吃多少

后端能吃不能吃
Suno / MiniMax情绪、整体质感的形容(warm、dry、wide chorus)声场图、ducking_map、逐段深度
YuE2同上,段落粒度更细精确声像与深度
MIDI / DAW全部——直接当 direction sheet—

★ 规则:后端 profile 里标 honors: none 的项, 算照做率时必须排除,不能给 0 分。 否则一个诚实声明"我做不到声像"的后端,会比一个假装做得到的后端得分更低—— 那会把评分体系带向错误的方向。


8. 与 ARR-SPEC 的字段对应

字段本 skill 的哪一节
mix_intent.mood§3.1(一句话,且放在生成提示词的靠前位置)
mix_intent.sound_stage[]§2(每件乐器的 pan + depth)
mix_intent.focus_by_section[]§3.2 主角序列
mix_intent.ducking_map[]§5(谁给谁让、什么时候)
mix_intent.deliberate_imbalance[]§4.3(必须带起止小节 + 理由)
mix_intent.reference_tracks[]§6(必须写参考它的哪个方面)

9. 写完后必过

  • mood 写了,一句话,且不和后面的决定打架
  • 五个领域各写了一句,不是只写了频率
  • 声场图里每件乐器都有左右和前后两个值
  • 同组乐器的深度一致(鼓组内部、弦乐组内部)
  • 逐段写了谁是最清楚的元素
  • 每处不平衡都带起止小节和理由,不是全曲状态
  • 诊断"糊"时先查了持续音,不是先怪鼓
  • 每个主角的进入点前 200 ms 内,没有更响的事件刚结束(§5)
  • 低频元素的声像居中;参考曲对比时响度已对齐(§2、§6.2)
  • 能在作曲层解决的冲突,已经在 mc-texture-layering 解掉了,没堆到这儿
  • 参考曲目至少一首,写明参考它的哪个方面
  • 没有在本文件里写 EQ 频点或压缩比(那些属于混音库)

附:来源

  • Roey Izhaki《Mixing Audio》(混音指南)——§2、§3、§4、§5、§6 的主干 (6 混音涉及的领域与目标、6.1 混音的目标、2.x 掩蔽、3.4 使用参考曲目)。页码为该书页。 本库只取"领域与目标"和"参考曲目"两部分;EQ/压缩/混响/母带的实操章节 全部出库到声音设计与混音库。
  • Howard & Angus《音乐声学与心理声学》(Acoustics and Psychoacoustics)—— §2 的定位线索与优先效应、§4.2 的混响拖尾、§5 的掩蔽机制与时间掩蔽、§6.2 的等响曲线。页码为中译本页。
  • **竹内一弘《EDM 制作》**的频率平衡与 Lo-Mid 管理、各声部音量平衡——同样只取意图层, 参数整理在 reference.md。
  • 后端 profile 与 honors 的定义见 本库架构文档 §2.3。

© jtydhr88, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/music-composition/skills/mc-mix-intent of jtydhr88/music-composition-skills.

  • SKILL.md
  • reference.md

Open the folder on GitHubat commit 7adca0c

Compare with similar skills

Mc Mix Intent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Mc Mix Intent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mc Mix Intent this skilljtydhr88/music-composition-skills151—~2.2kAutomated safety check: PassMIT
Interaction Design Boarddaymade/claude-code-skills1.4k—~2.7kAutomated safety check: PassMIT
Odoo L10n Compliancesickn33/agentic-awesome-skills47k2 repos~1.1kAutomated safety check: PassMIT
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Chatbox i18n Translatorchatboxai/chatbox42k—~508Automated safety check: PassGPL-3.0
Internationalization Workflow with i18niOfficeAI/AionUi33k1 repos~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Interaction Design Board

    daymade/claude-code-skills

    Generates several distinct, clickable HTML interaction prototypes for one product surface into a Design Board and collects selection/remix feedback before implementation.

    1.4k GitHub stars~2.7k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Odoo L10n Compliance

    sickn33/agentic-awesome-skills

    Country-specific Odoo localization: tax configuration, e-invoicing (CFDI, FatturaPA, SAF-T), fiscal reporting, and country chart of accounts setup.

    47k GitHub starsUsed in 2 repos~1.1k tokens
    Frontend & DesignAuto-check passed
  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Chatbox i18n Translator

    chatboxai/chatbox

    Translates new or changed i18n keys from a Chatbox Pro diff, staged changes or a commit range, writing the locale JSON files directly with a built-in glossary.

    42k GitHub stars~508 tokensUpdated 15 days ago
    Frontend & DesignAuto-check passed
  • Standards for keeping all user-facing text translatable: read the i18n config first, use namespaced keys, reuse shared strings and follow the key naming rules.

    33k GitHub starsUsed in 1 repo~1.9k tokens
    Frontend & DesignAuto-check passed
  • Review pending AIRI translations on Crowdin in a batch, then sync them into the repository.

    50k GitHub stars~1.5k tokensUpdated today
    Frontend & DesignAuto-check passed

More from jtydhr88/music-composition-skills

All 29 skills in this repo
  • Mc AI Tell Audit

    jtydhr88/music-composition-skills

    The post-generation AI-tell audit (AI 味诊断). An agent skill from jtydhr88/music-composition-skills.

    151 GitHub stars~1.8k tokensUpdated 17 days ago
    Auto-check passed
  • Mc Arrangement Arch

    jtydhr88/music-composition-skills

    Arrangement architecture (编曲结构学) - the shape of a track over time rather than its notes.

    151 GitHub stars~3.5k tokensUpdated 17 days ago
    Auto-check passed
  • Mc Case Studies

    jtydhr88/music-composition-skills

    The corpus layer (语料层) - how real recordings are made to testify for or against the textbook rules.

    151 GitHub stars~1.6k tokensUpdated 17 days ago
    Auto-check passed
  • Mc Development

    jtydhr88/music-composition-skills

    Thematic development (乐思发展层) - what the theme is and what each section does with it.

    151 GitHub stars~4.4k tokensUpdated 17 days ago
    Auto-check passed
  • Mc Form

    jtydhr88/music-composition-skills

    Song form and section design (曲式与段落) - the terminology, the standard templates, and how to build a setsu backwards from the chorus.

    151 GitHub stars~2.2k tokensUpdated 17 days ago
    Auto-check passed
  • Mc Melody

    jtydhr88/music-composition-skills

    Melody writing (旋律法) - what a melodic line expresses and how to make it singable.

    151 GitHub stars~2.6k tokensUpdated 17 days ago
    Auto-check passed

Questions about Mc Mix Intent

What does Mc Mix Intent do?

Mix intent as a handoff artifact (混音意图) - stating what a mix must achieve so a human engineer, a DAW, or a generative backend can all act on it, without prescribing EQ or compressor settings. Mc Mix Intent is an agent skill from jtydhr88/music-composition-skills. Mix intent as a handoff artifact (混音意图) - stating what a mix must achieve so a human engineer, a DAW, or a generative backend can all act on it, without prescribing EQ or compressor settings.

When should I use Mc Mix Intent?

Mc Mix Intent fits situations like: writing the mixintent block of an ARR-SPEC; handing a session to an engineer; deciding what a backend can actually honor; diagnosing a mix that is technically clean but emotionally wrong.

How do I install Mc Mix Intent in Claude Code?

Run `npx skills add jtydhr88/music-composition-skills --skill mc-mix-intent -a claude-code`. Or copy the skill folder (plugins/music-composition/skills/mc-mix-intent in jtydhr88/music-composition-skills) into .claude/skills/mc-mix-intent in your project. Claude Code loads it when a task matches its description.

How do I install Mc Mix Intent in Codex?

Run `npx skills add jtydhr88/music-composition-skills --skill mc-mix-intent -a codex`. Or copy the skill folder (plugins/music-composition/skills/mc-mix-intent in jtydhr88/music-composition-skills) into .agents/skills/mc-mix-intent in your project. Codex loads it when a task matches its description.

Can I use Mc Mix Intent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jtydhr88/music-composition-skills --skill mc-mix-intent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mc-mix-intent, .gemini/skills/mc-mix-intent, .github/skills/mc-mix-intent and .opencode/skills/mc-mix-intent in your project.

What does Mc Mix Intent need to run?

SKILL.md names no scripts, command-line tools or credentials: Mc Mix Intent is instructions for the agent only.

Does Mc Mix Intent access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Mc Mix Intent safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Mc Mix Intent use?

Mc Mix Intent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Mc Mix Intent use?

About 2.2k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Mc Mix Intent?

Skills that share tags, products or a category with Mc Mix Intent: Interaction Design Board (daymade/claude-code-skills, 1.4k stars), Odoo L10n Compliance (sickn33/agentic-awesome-skills, 47k stars), Impeccable (bestofjs/bestofjs, 3.1k stars) and Chatbox i18n Translator (chatboxai/chatbox, 42k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mc Mix Intent?

jtydhr88 (a GitHub user) maintains it in jtydhr88/music-composition-skills, which has 151 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on September 22, 2026.

Source: jtydhr88/music-composition-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.