Agent skill

Mc Modulation

by jtydhr88 in jtydhr88/music-composition-skills

Modulation (转调) - moving between keys and making the seam sound intended rather than accidental.

MITAuto-check passed

Install Mc Modulation

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

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

GitHub CLI
$ gh skill install jtydhr88/music-composition-skills mc-modulation --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-modulation .claude/skills/mc-modulation && 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-modulation
GitHub stars
150
Token cost
~2.1k tokens
SKILL.md length
567 words
Files
2
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Modulation (转调) - moving between keys and making the seam sound intended rather than accidental.

  • Works in 9 steps: 动笔前必填 → 近亲调与远隔调 → ★ 缓冲和弦:本 skill 的核心概念 → …
  • A section needs to change key
  • SKILL.md covers 按任务读哪几节, 边界, 1. 动笔前必填 and 2. 近亲调与远隔调, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mc Modulation is an agent skill from jtydhr88/music-composition-skills. Modulation (转调) - moving between keys and making the seam sound intended rather than accidental. Closely related versus distant keys, the cushion chord and its announcement ladder from smoothest to most impactful, degree thinking, the three tools that keep a modulation feeling unified, what each interval distance expresses, a six-step decision flow including the return trip, and a warning about the one modulation generative models reach for by default. Use when a section needs to change key, when a key lift feels…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `reference.md`).

The repository describes itself as: Professional agent skills for composing and arranging popular music. The licence is MIT.

When your agent uses it

  • A section needs to change key
  • A key lift feels cheap
  • A modulation sounds accidental
  • Planning a bright-to-dark

Example prompts

  • “/mc-modulation”

Workflow steps

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

  1. 动笔前必填
  2. 近亲调与远隔调
  3. ★ 缓冲和弦:本 skill 的核心概念
  4. 距离决定性格
  5. 六步决策流程
  6. ★ 套路警戒线:最后一遍副歌上行半音
  7. 场景 → 手法
  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 Modulation loads about 2.1k tokens when it runs. Until then it costs about 178 tokens; SKILL.md has 567 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~178
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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). 567 words, ~2,076 tokens.

Download SKILL.mdSave it as .claude/skills/mc-modulation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
mc-modulation
description
Modulation (转调) - moving between keys and making the seam sound intended rather than accidental. Closely related versus distant keys, the cushion chord and its announcement ladder from smoothest to most impactful, degree thinking, the three tools that keep a modulation feeling unified, what each interval distance expresses, a six-step decision flow including the return trip, and a warning about the one modulation generative models reach for by default. Use when a section needs to change key, when a key lift feels cheap or abrupt, when a modulation sounds accidental, when planning a bright-to-dark or dark-to-bright switch, or when returning to the home key. 转调、升key、离调、同主调、平行调、近亲调、远隔调、缓冲和弦。

转调(Modulation)

转调的全部难点不在"转到哪",在"接缝听起来是不是有意为之"。

这个 skill 的核心是一个概念——缓冲和弦(クッション), 以及一把刻度尺——它有多大声地宣告"我要转调了"。

按任务读哪几节

任务读
决定转到哪个调§2 亲疏关系 + §4 距离与性格
接缝生硬§3 缓冲和弦
想转得不着痕迹§3.2 宣告刻度的最低两档
想转得有冲击§3.2 的最高两档
转完了回不来§5 第 6 步
担心升 key 太俗★ §6
按场景选手法§7
查具体手法(50 条)reference.md

边界

不归这里归哪
不转调的调外和弦(副属、借用、裏和弦)mc-harmony §6——★ 那是"离调",不是转调
和弦进行本身mc-progressions
转调点放在曲式的哪里mc-modulation §5(六步流程第 1 步定位置)与 §6
转调时旋律怎么接mc-melody §3(大跳的准备)+ §6(收束)
50 条具体手法的谱例reference.md

★ 离调 vs 转调:插一个 E7 再回到 C,是离调(mc-harmony); 插一个 E7 之后后面一直待在 A 大调,才是转调(本 skill)。 判据是"之后有没有留下来",不是"用了什么和弦"。


1. 动笔前必填

必填问法
① 目标调具体到调名,并算出与原调的音程关系
② 为什么要转抬升?明暗切换?世界切换?"因为该转了"不是理由
③ 宣告强度要不着痕迹还是要冲击(§3.2 的五档里选一档)
④ 回程还回不回来?怎么回?★ 这条最常被漏

1.1 转调的四个目的(黄虎威 p0010–0013)

表现内容与刻画形象;发展材料(同一片断在不同调上重复是"节约材料,事半功倍");色彩对比; ★ 适应人声或乐器的音域、音区、音色。第四条以前不在本 skill 的问题清单里,而它最实际:歌手唱不上去,转调就是答案,不必找别的理由。 从属调性天然不稳定、要求回到基本调性,这就是推动力;回程先转到基本调的属调最宜引出主调,正如属和弦最宜引出主和弦(p0011)。

2. 近亲调与远隔调

常用调共 24 个(12 大 + 12 小)。以 Key=C 为例,六种近亲调:

关系例性格
同主调C ↔ Cm同一个主音的大小调;明暗对比可以拉得很狠
平行调(= 关系大小调)C ↔ Am同调号,几乎所有和弦共通;轻轻一碰就换了情绪
属调(上行纯五)C → G音阶只差 1 个音,共同和弦多,最平滑
属调的平行调C → Em与 G 同调号
下属调(下行纯五)C → F与属调对称,同样平滑
下属调的平行调C → Dm与 F 同调号

远隔调:以上之外的全部。气氛剧变,用得好能造出戏剧性发展。 半音关系与三全音关系都属于远隔调。


2.1 三级关系的定量划分(黄虎威)

"近亲"与"远隔"可以数出来(p0013–0017),距离按五度圈上最近的一边算:

关系调号差共同的自然音三和弦
近关系1 个4 个
较远关系2 个2 个
远关系3–6 个0 个
最远6 个0 个

共同三和弦的个数就是缓冲和弦(§3)能挑的材料有多少。零个共同和弦的转调,缓冲只能靠等音或换调(§4.1)。

2.2 五声调式的转调

五声调式换宫系统只有两条路,变宫为角上五度、清角为宫下五度,连续两次到大二度(黄虎威 p0041–0042、p0063–0064)。 ★ 近关系的五声转调在旋律层面无痕,一个宫系统的七个自然音能写出本调与两个近关系调的五声旋律而不出任何变化音(p0040–0041), 所以转调感全靠和声承担,和声里必须让新调号的那个音出现(p0045)。体系与同主音四变体见 mc-melody reference §3.0。

2.3 什么不算转调(防止过度分析)

出现副属、扩展属、相关 II-7、调式转换、替代属、过渡和弦时,一般不能分析为转调;只停留一小节的和弦按原调级数解释更好 (陈云强《爵士和声》p0257)。与 §5 的"之后有没有留下来"是同一条判据的两面:没留下来的不是转调,是离调。

2.4 歌里的转调三法(Kachulis)

平行调转调(同主音换调式色彩,G 混合利底亚到 G 多利亚,用来标记歌词故事的转折);关系调转调(枢纽和弦在两调里级数不同,把预期的和弦换成另一调的、然后留在那); 惊叹调转调(V 之后直接进新调)。三法都比黄虎威那套粗,但它们绑着歌词用,lw-song-intent 定了转折点在哪,转调就落在那。

3. ★ 缓冲和弦:本 skill 的核心概念

3.1 它是什么

一个让转调听起来平滑的过渡和弦。

最常见的就是目标调的 V 或 V7,插在转调前的最后 1–2 拍, 跨小节线解决成 V7→I(属进行)。

★ 这个 V7 在原调里通常是个调外和弦(III7、IV7、VI7 等)—— 那正是"要换色了"的信号。

3.2 宣告刻度:它有多大声说"我要转调了"

从最轻到最重:

档缓冲和弦效果
1V(三和弦)最平滑,宣告最低
2V7含三全音,推力更强
3♭II7(裏和弦)注入外来音,宣告最强,自带爵士味
4dim / aug(V7(♭9)/V7(♭13) 的替身)音响独特,冲击最大
5IV(onV) 型分数和弦(如 F/G)★ 没有三音(导音)→ 调性感被模糊 → 反而"可以飞去任何调"

★ 第 5 档是特例:它不是"更响",而是另一个方向—— 前四档是"明确地宣告",第 5 档是"让人听不出原来在哪个调"。 要偷偷转就用它。

3.3 级数思维

把每个和弦都想成罗马数字级数:调变了,级数不变。 这是一个换算习惯,不是一条带条件的判据,所以只有这一句: 它在 §3.4 工具①(整段进行原样平移)、§3.5"共同和弦怎么取"(同一和弦在前后两调的级数换算)、 以及 §5 第 3 步(算出目标调的 V7)里被反复用到——具体怎么用、有什么代价,见那几处。

3.4 保持统一感的三件工具

转调最大的风险是"听起来像换了一首歌"。三条对策:

  1. 整段进行原样平移(同一个进行移调,级数完全不变)
  2. 一条クリシェ线贯穿两个调(低音/内声部/顶音的半音级进)
  3. ★ 用共同音当顶音,让旋律带着走过转调

3.5 缓冲和弦的九条做法(黄虎威)

§3 讲缓冲和弦是什么,这一节是各种具体接法,按从近到远排:

做法要点页
共同和弦怎么取几个相邻和弦都共同时,只把紧靠转调和弦的最后一个算共同和弦;它在前后两调的级数一般不同、功能可能相同p0033–0034
特征音提前或推迟共同和弦里可以提前渗进后调的特征音(常以经过音"闯入"),也可以推迟到后面再追认。★ 这是一个真正的旋钮:旋律先转和声追认与和声先转旋律后跟听感完全不同p0034–0035、p0049–0050
半音转调后调是大调,共同和弦里含后调自然 VI 级音,进转调和弦时该音降半音;后调是小调,含后调自然 VII 级音,进转调和弦时升半音成导音p0037–0039
中间调把共同三和弦扩成一个临时调性中心(前后加它的属功能),再转向后调。远关系拆成两跳就靠它p0057–0059
增三和弦作共同和弦十二平均律只有四个音响互异的增三和弦;任一个连同两个等和弦能解决到十二个调。捷径:选一个含后调主和弦一两个和弦音的增三和弦见黄书增三和弦章
属七与增六互为等和弦前调属七当后调增五六 → 低半音的调;前调增五六当后调属七 → 高半音的调。半音上下转调的另一条路p0120–0121
单声部转调只用一个持续单音或单声部完成转调,段落接缝的极简过渡p0145–0153
小三度循环沿同方向连续小三度换调,第四次回到原调;大三度循环低音加大二度经过音生成全音音阶p0163–0164
小代大、大代小预期的主和弦被降低或升高三音。总接在前调属功能之后,功能联系太紧,一般不构成换调,但色彩对比鲜明,是一个低成本的假转调p0167–0168

轴心音(p0061):贯穿前后两调、同时是两调调式骨干音的那个音(如前调属音兼后调下属音),§3.4 第 3 条"用共同音当顶音"的可操作版:先找轴心音,再往上挂旋律。

4. 距离决定性格

方向性格
上行半音尾奏前的标准升 key,情绪抬升。★ 见 §6
下行半音远隔调的冲击,却不需要任何特殊技巧
上行全音汹涌;经过 dim 和弦会更悲壮
下行全音邻调;自然生成漂亮的**"终曲感"**/分量感
上行小三度大调 = 华丽壮大;小调 = 微妙的换色
下行小三度大调 = 明亮又安定;积极清爽
同主调直接的明暗切换(对比),或渐变的上色
平行调最平滑的明暗切换
属调/下属调共同和弦最多,全部之中最平滑
三全音距离最远;架好桥就是最有戏剧性的

Show full SKILL.md (218 more words)Show less
4.1 换调:不架桥,直接搬

**换调(调性对置)**不做缓冲,两个调直接对置,只要色彩对比(黄虎威 p0156–0164)。配对规则: 材料不同的换调放在乐段级的大结构之间;材料相同的换调放在乐句、乐节、乐汇级的小结构之间,结构短、印象未散,对比才突出。 色彩梯度:近关系功能性强、对比弱 → 三度关系最富色彩 → 调号差 5 个"突然而新颖" → 差 6 个"最突然、关系最疏远"。 §6 说的末段上行半音,就是换调里最被用滥的那一格。

5. 六步决策流程

  1. 定目标调与方向:想去哪(副歌升 key?明暗切换?最后一程的高潮?),算出音程关系
  2. 查方向索引(reference.md §1):找出该方向的手法,按想要的宣告强度挑
  3. 算出目标调的 V7:这是万用缓冲。要更有型换裏和弦;要更冲击用 dim/aug 替身; 要偷偷转用 IV(onV) 型分数和弦
  4. 选统一策略:整段平移?クリシェ线贯穿?共同音留在顶部?(选一个或组合)
  5. 安排落点:缓冲和弦放在转调前最后 1–2 拍,跨小节线解决到新调的 I (或 IIm7/IVm 这样的二五入口)
  6. ★ 规划回程:把新调的 I 变成属七(I→I7),或变成原调的 IIm, 借副属/二五一回家

第 6 步最常被漏。 转出去回不来的结果是后半首都别扭, 而且 20 条自查查不出来——这是一条只能靠自检的规则。


5.1 完备转调的四步,与转调特征音

六步是设计流程,这四步是诊断:接缝出问题时逐一查(黄虎威 p0032–0036)。

  1. 显示前调
  2. 出现共同和弦
  3. 出现转调和弦
  4. 肯定后调(正格全终止)

实际作品要么走全四步,要么合并或取消某几步,极端是两调主和弦直接对置(那就是 §4.1 的换调)。

★ 转调特征音(p0035):转调和弦里要出现前调没有、后调独有的音,通常就是两调调号相异的那个(C 到 G 是升 F,C 到 F 是降 B); 后调是和声大调则看降 VI 级,和声小调则看升 VII 级。它是"到底转过去没有"的检查项:特征音没出现过,听众不会知道你转了。

6. ★ 套路警戒线:最后一遍副歌上行半音

这是流行音乐里被用得最狠的一个手法,也是生成模型的默认动作。

在"epic / emotional / final chorus"这类提示下,后端高概率自己给你升半音。

判据同 mc-progressions §3:

你是"选择"了它,还是"默认"落进了它?

6.1 四条替代方案(都能达到"最后一程更强")
替代为什么有效
下行全音得到"终曲感"与分量,而不是廉价的抬升。方向反了,效果反而更重
上行小三度华丽壮大,比半音更有事件感
不转调,改编制★ 多数时候这才是正解——升 key 往往是在补编曲没做够的功课(→ mc-arrangement-arch §6)
同主调切换大转小或小转大,情绪变化比升半音大得多
6.2 如果仍然要升半音

至少做到这两条之一:

  • 用 §3.2 的第 4 档(dim/aug)或第 5 档(分数和弦)改变宣告方式,别用最俗的 V7
  • 让升 key 与一个编制事件同时发生(撤掉某件乐器、加进一件新的), 这样听众记住的是那个事件而不是那半音

★ 自检动作:在 ARR-SPEC 的 form[].note 里写一句为什么在这里转调。 写不出来就别转。


7. 场景 → 手法

场景推荐手法编号(见 reference.md)
整段副歌升 key(尾奏前的标准做法)10、15、41
大サビ(最后的高潮副歌)再炸一次15、09、21
主歌 → 副歌豁然开朗(暗→明)05、12、17、23、36、39
明亮的 A/B 段 → 忽然深沉的副歌(明→暗)16、30、34、40
尾奏的终曲感/华丽收尾02、08、24、31、33、43
间奏/solo 段的世界切换27、40
前奏与 A 段用对比的调30、35、45、48
时髦的爵士味20、21、49
不突兀的渐进明暗上色36、37
多调之旅/华丽的副歌进行44、47、50

8. 与 ARR-SPEC 的字段对应

字段说明
meta.key原调。转调后的调不改这里
form[].harmony★ 转调段的级数以新调为准,并在 note 里写明"此段 Key=X"
form[].harmony_letters字母记号自然反映新调
form[].note★ 转调理由写在这里(§6 的自检动作)
lint #9"至少一段含调外和弦或转调标记"——转调满足这一条

9. 写完后必过

  • 说得出为什么要在这里转调,不是"该转了"
  • 缓冲和弦的宣告强度是选的,不是默认用了 V7
  • 用了 §3.4 三件统一工具中的至少一件
  • ★ 规划了回程(或明确决定不回来,并写明)
  • 若是"最后副歌升半音",过了 §6 的警戒线检查
  • 转调段的级数记号以新调为准,且 note 里标了新调
  • 旋律在转调点上的大跳有准备(→ mc-melody §3.3)

附:来源

  • 日式包 jp-modulation——§1–§5、§7 与 50 条手法。 底本为日本转调实务书。
  • ⚠ 黄虎威《转调法》—— 这本是中文乐理体系的转调专著。 预计差异在:黄书从共同和弦入手(古典路径),日式从缓冲和弦/属进行入手(流行路径)。
  • 斯波索宾《和声学教程》——转调的古典严格版本。
  • 50 条手法的方向索引与类型索引在 reference.md。

© 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-modulation of jtydhr88/music-composition-skills.

  • SKILL.md
  • reference.md

Open the folder on GitHubat commit 7adca0c

Compare with similar skills

Mc Modulation 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 Modulation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mc Modulation this skilljtydhr88/music-composition-skills150—~2.1kAutomated safety check: PassMIT
Configuring Hsm For Key Storagemukul975/Anthropic-Cybersecurity-Skills34k—~984Automated safety check: PassApache-2.0
Es Modulesthedaviddias/Front-End-Checklist74k—~482Automated safety check: PassMIT
OmniRoute API Keysdiegosouzapw/OmniRoute74k—~1.2kAutomated safety check: PassMIT
Move Code Qualitydavila7/claude-code-templates32k2 repos~3.2kAutomated safety check: PassMIT
Splitting Oversized ModulesPostHog/posthog40k—~2.2kAutomated safety check: PassCustom licence

Similar skills

  • Configuring Hsm For Key Storage

    mukul975/Anthropic-Cybersecurity-Skills

    Configures Hardware Security Modules for cryptographic key storage using the PKCS11 standard interface, covering key generation, signing, encryption, and key management on physical HSMs and SoftHSM2…

    34k GitHub stars~984 tokensUpdated 1 mo ago
    SecurityAuto-check passed
  • Es Modules

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Use ES modules (import/export).

    74k GitHub stars~482 tokensUpdated yesterday
    Auto-check passed
  • OmniRoute API Keys

    diegosouzapw/OmniRoute

    Documents the OmniRoute REST endpoints for creating, listing, updating, regenerating and deleting API keys, with per-key scopes, spending limits, expiry and device lists.

    74k GitHub stars~1.2k tokensUpdated today
    Backend & APIsAuto-check passed
  • Move Code Quality

    davila7/claude-code-templates

    Analyzes Move language packages against the official Move Book Code Quality Checklist.

    32k GitHub starsUsed in 2 repos~3.2k tokens
    DevelopmentAuto-check passed
  • Official

    Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior.

    40k GitHub stars~2.2k tokensUpdated today
    Frontend & DesignAuto-check passed
  • OmniRoute Key and OAuth CLI

    diegosouzapw/OmniRoute

    Command reference for managing OmniRoute API keys and provider OAuth connections from the terminal: create, list, rotate, revoke and inspect limits.

    74k GitHub stars~621 tokensUpdated today
    Backend & APIsAuto-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.

    150 GitHub stars~1.8k tokensUpdated 15 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.

    150 GitHub stars~3.5k tokensUpdated 15 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.

    150 GitHub stars~1.6k tokensUpdated 15 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.

    150 GitHub stars~4.4k tokensUpdated 15 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.

    150 GitHub stars~2.2k tokensUpdated 15 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.

    150 GitHub stars~2.6k tokensUpdated 15 days ago
    Auto-check passed

Questions about Mc Modulation

What does Mc Modulation do?

Modulation (转调) - moving between keys and making the seam sound intended rather than accidental. Mc Modulation is an agent skill from jtydhr88/music-composition-skills. Modulation (转调) - moving between keys and making the seam sound intended rather than accidental.

When should I use Mc Modulation?

Mc Modulation fits situations like: A section needs to change key; A key lift feels cheap; A modulation sounds accidental; planning a bright-to-dark.

How do I install Mc Modulation in Claude Code?

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

How do I install Mc Modulation in Codex?

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

Can I use Mc Modulation 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-modulation -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-modulation, .gemini/skills/mc-modulation, .github/skills/mc-modulation and .opencode/skills/mc-modulation in your project.

What does Mc Modulation need to run?

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

Does Mc Modulation 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 Modulation 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 Modulation use?

Mc Modulation 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 Modulation use?

About 2.1k tokens (SKILL.md is roughly 8.3k 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 Modulation?

Skills that share tags, products or a category with Mc Modulation: Configuring Hsm For Key Storage (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Es Modules (thedaviddias/Front-End-Checklist, 74k stars), OmniRoute API Keys (diegosouzapw/OmniRoute, 74k stars) and Move Code Quality (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mc Modulation?

jtydhr88 (a GitHub user) maintains it in jtydhr88/music-composition-skills, which has 150 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.