minimax-music
- Repo stars 2
- Author updated Live
- Author repo claude-marketplace
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @111pointer111 · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Required · Vendor-specific
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: minimax-music
description: 高质量歌词必须同时满足：叙事性 + 意象性 + 韵律感 + 情感共鸣 检查标准：有没有具体的时间/地点/人物/物品？有没有直接说"心痛/悲伤"？ 用具体物品和动作替代抽象情绪词： skills…
category: other
runtime: Python
---
# minimax-music output preview
## PART A: Task fit
- Use case: 高质量歌词必须同时满足：叙事性 + 意象性 + 韵律感 + 情感共鸣 检查标准：有没有具体的时间/地点/人物/物品？有没有直接说"心痛/悲伤"？ 用具体物品和动作替代抽象情绪词： skills/minimax-music/ ├── settings.example.yaml # 配置模板 requires Vendor-specific API key; runs on Python. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “核心方法论 / AI 音乐生成三大规律 / 歌词四轴法则” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “高质量歌词必须同时满足：叙事性 + 意象性 + 韵律感 + 情感共鸣 检查标准：有没有具体的时间/地点/人物/物品？有没有直接说"心痛/悲伤"？ 用具体物品和动作替代抽象情绪词： skills/minimax-music/ ├── settings.example.yaml # 配置模板 requires Vendor-specific API key; runs on Python. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “核心方法论 / AI 音乐生成三大规律 / 歌词四轴法则” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; requires Vendor-specific API keys.
## Running Rules
- read files, write/modify files; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “核心方法论 / AI 音乐生成三大规律 / 歌词四轴法则”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: minimax-music
description: 高质量歌词必须同时满足：叙事性 + 意象性 + 韵律感 + 情感共鸣 检查标准：有没有具体的时间/地点/人物/物品？有没有直接说"心痛/悲伤"？ 用具体物品和动作替代抽象情绪词： skills…
category: other
source: 111pointer111/claude-marketplace
---
# minimax-music
## When to use
- 高质量歌词必须同时满足：叙事性 + 意象性 + 韵律感 + 情感共鸣 检查标准：有没有具体的时间/地点/人物/物品？有没有直接说"心痛/悲伤"？ 用具体物品和动作替代抽象情绪词： skills/minimax-music/ ├── se…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “核心方法论 / AI 音乐生成三大规律 / 歌词四轴法则” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; requires Vendor-specific API keys.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "minimax-music" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 核心方法论 / AI 音乐生成三大规律 / 歌词四轴法则
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, write/modify files | may access external network resources
guardrails -> requires Vendor-specific API keys + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}MiniMax AI 音乐生成 Skill
核心方法论
AI 音乐生成三大规律
- 约束叠加 > 单一描述：同时给 2-3 个相互制约的风格条件，AI 会做出更精确的创造性选择
- Hook-First：先设计副歌记忆点（≤7字，具体画面），再倒推全曲结构
- 迭代比一次到位更可靠：固定 tempo+mood+song length，每次只改一个变量
歌词四轴法则
高质量歌词必须同时满足：叙事性 + 意象性 + 韵律感 + 情感共鸣 检查标准：有没有具体的时间/地点/人物/物品？有没有直接说"心痛/悲伤"？
克制原则
用具体物品和动作替代抽象情绪词：
- ❌ "我的心好痛" → ✅ "输入法还记得你的名字"
- ❌ "时间过得好快" → ✅ "校服领口松了两颗扣"
目录结构
skills/minimax-music/
├── SKILL.md
├── settings.example.yaml # 配置模板
├── scripts/
│ └── music_generator.py
└── references/
└── prompt_templates.md # 完整方法论（必读）快速开始
环境配置
- 复制配置模板：
cp settings.example.yaml settings.yaml- 在
settings.yaml中配置输出目录：
OUTPUT_DIR: "/path/to/your/music/output"- 确保
MINIMAX_API_KEY已设置在环境变量中（脚本从os.environ读取）
单首生成
from scripts.music_generator import generate_music
import yaml
settings = yaml.safe_load(open("settings.yaml"))
result = generate_music(
prompt="中文民谣，关于清晨便利店独自喝咖啡的场景...",
lyrics="___LYRICS_OPTIMIZER___",
vocals="沙哑男声，有岁月感，有呼吸感",
genre="folk",
mood="melancholic, warm",
instruments="木吉他，指弹风格",
tempo="moderate",
structure="verse - verse - pre-chorus - chorus - bridge - chorus",
avoid="'心痛' or '悲伤' or '眼泪', 情歌套路, 说教结尾",
settings=settings,
)每日三首
from scripts.music_generator import generate_daily_music
results = generate_daily_music("/path/to/skills/minimax-music/")mmx music generate 核心参数
人声音乐（含 --lyrics-optimizer）
mmx music generate \
--prompt "<场景+情绪描述，禁止项>" \
--lyrics-optimizer \
--vocals "<人声：音域+质感+每段落发声策略>" \
--genre "<流派>" \
--mood "<情绪>" \
--structure "<verse-chorus-verse-chorus-bridge-chorus>" \
--avoid "<具体要排除的元素>" \
--out "/path/to/output.mp3"器乐
mmx music generate \
--prompt "<音色+层次+情绪曲线+场景描述>" \
--instrumental \
--genre "<流派>" \
--mood "<情绪>" \
--instruments "<乐器层次>" \
--avoid "<不要的元素>" \
--structure "<intro - main theme - ending>" \
--out "/path/to/output.mp3"--vocals 写法模板
专业写法：音域 + 音色质感 + 各段落发声策略
--vocals "男高音 tenor，略带沙哑有力量感。
主歌 chest voice 叙事，接近说话的语气；
预副歌 mixed voice 慢慢叠加能量；
副歌 strong belt 爆发，高音有穿透力；
桥段 head voice 轻唱，脆弱感；
尾副歌 belt 推到最高，最后长音 vibrato 收尾"核心原则：主歌收 → 预副歌蓄 → 副歌放 → 桥段收 → 尾副歌最放
详见 references/prompt_templates.md — 完整声乐术语和模板
歌词禁止清单
必须禁止：
- 抽象情绪词：心痛、悲伤、难过、崩溃、绝望
- 陈词滥调：飞蛾扑火、遍体鳞伤、沧海桑田、海枯石烂
- 说教结尾：珍惜当下、把握今天、勇敢前行
- 过度煽情：直接哭喊、直接说"我爱你爱到死"
参考资料
完整方法论、意象库、prompt 模板、速查表：
→ references/prompt_templates.md
注意事项
mmx music generate超时 300 秒，耐心等待--lyrics-optimizer的 prompt 必须包含场景+禁止项，不能太笼统- API Key 从环境变量
MINIMAX_API_KEY读取，禁止硬编码 --aigc-watermark推荐开启- 歌词生成后对照四轴法则自检
- 每日生成建议每次只改一个变量迭代优化
Decide Fit First
Design Intent
How To Use It
Boundaries And Review