Communitygithub.com

modbender/skill-library-mcp

端到端生成 AI 音乐视频。使用 Suno 创作音乐,利用 OpenAI/Seedream/Google/Seedance 生成视觉素材,并通过 ffmpeg 组装成音乐视频。支持带时间戳的歌词(自动 SRT)、Suno 原生音乐视频生成、幻灯片/视频/混合模式。基于 token 的每次生成成本追踪。

skill-library-mcp 是什么?

这个 AI Agent 技能提供了一个完整的端到端音乐视频生成流水线。它首先利用 Suno API(sunoapi.org)根据用户提示生成音乐,然后使用多个 AI 视觉提供商(如 OpenAI、Seedream、Google 或 Seedance)根据歌词或情绪生成图像或视频片段,最后通过 ffmpeg 将所有元素组装成一个连贯的音乐视频。该技能支持多种模式:幻灯片模式(速度快、成本低)、视频模式(质量高)、混合模式,以及直接利用 Suno 原生音乐视频功能的模式。它自动为带歌词的歌曲生成带时间戳的 SRT 字幕,并支持“角色”功能,以保持多首歌曲之间声音和风格的一致性。此外,所有生成步骤都包含成本估算和追踪,有助于管理 API 使用支出。该技能支持 Claude Code、Cursor 等主要平台,通过提供结构化的 Bash 脚本和清晰的流程,简化了通常需要多个工具和手动编排的复杂工作流程。

兼容平台~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/modbender/skill-library-mcp/tree/HEAD/data/ai-music-video

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

AI 音乐视频生成器

创建完整的音乐视频:AI 音乐 + AI 视觉 + ffmpeg 组装。

快速开始

"90년대 보이밴드 풍 한국어 노래 만들어줘" → 仅音乐
"발라드 뮤비 만들어줘" → 音乐 + 幻灯片 MV
"EDM 뮤비 풀영상으로" → 音乐 + 视频剪辑 MV
"Suno 뮤비로 만들어줘" → Suno 原生音乐视频

工作流程

1. 根据歌词/情绪规划场景

在生成之前,创建 prompts.json — 一个场景描述数组,这些描述源自歌曲的歌词、情绪和叙事。对于一首 3 分钟的歌曲,通常需要 8-12 个场景。

[
  {"prompt": "霓虹灯闪烁的城市街道,夜晚,雨水倒影", "type": "image"},
  {"prompt": "摄像机在日落时分缓慢扫过屋顶", "type": "video"},
  "一个人影独自走过樱花"
]

2. 生成音乐

bash scripts/suno_music.sh \
  --prompt "가사 또는 설명" \
  --style "90年代男孩乐队流行风,韩语" \
  --title "너만을 원해" \
  --model V4_5ALL --custom \
  --outdir /tmp/mv_project

选项:

  • --model V4_5ALL(默认),V5,V4_5PLUS,V4_5,V4
  • --instrumental — 无 vocals
  • --vocal-gender m|f — vocals 性别提示
  • --negative-tags "重金属音乐, 鼓点" — 要避免的风格
  • --music-video — 生成 Suno 原生音乐视频(MP4)
  • --dry-run — 仅成本检查

角色(일관된 스타일 유지):

  • --persona-id ID — 使用现有角色(以相同的 vocals/风格生成多首歌曲)
  • --create-persona — 从生成的歌曲中创建角色 → 保存到 persona.json
  • --persona-name "이름" / --persona-desc "설명" / --persona-style "스타일"

自动功能:

  • 🎤 带时间戳的歌词:非纯音乐曲目会自动获取歌词时间戳并保存为 {outdir}/lyrics.srt
  • 🎬 Suno 原生 MV:使用 --music-video,Suno 可直接生成可视化的 MP4 视频
  • 🎭 角色:使用 --create-persona,可提取声音/风格身份以供重复使用

3. 生成视觉素材(自定义 MV 流程)

bash scripts/gen_visuals.sh \
  --mode slideshow \
  --prompts-file /tmp/mv_project/prompts.json \
  --image-provider seedream \
  --outdir /tmp/mv_project

或者使用 OpenAI(更便宜,分辨率更低):

bash scripts/gen_visuals.sh \
  --mode slideshow \
  --prompts-file /tmp/mv_project/prompts.json \
  --image-provider openai --image-model gpt-image-1-mini --image-quality medium \
  --outdir /tmp/mv_project

在消费前先添加 --dry-run 以显示成本估算。

4. 组装

bash scripts/assemble_mv.sh \
  --audio /tmp/mv_project/track_0_xxx.mp3 \
  --outdir /tmp/mv_project \
  --output /tmp/mv_project/final_mv.mp4 \
  --transition fade

字幕行为:

  • 自动检测 {outdir}/lyrics.srt 并自动叠加歌词
  • --subtitle /path/to/custom.srt — 使用自定义 SRT 文件
  • --no-subtitle — 完全禁用歌词叠加

模式

模式视觉类型适用场景成本(10 个场景)
slideshowAI 图片快速、便宜~$0.02(mini low)/ ~$0.09(mini med)/ ~$0.45(Seedream)
videoAI 视频片段高品质~$1.40(Seedance Lite)/ ~$8.00(Sora 2)
hybrid两者混合均衡~$0.50-$4.00
suno-nativeSuno MV最简单仅消耗 Suno 积分

图片成本基于 token — 实际计费可能低于列出的估算值。使用 --dry-run 获取精确成本。

提供商选项

图片: --image-provider seedream(推荐),openai,或 google-together 图片模型(OpenAI): --image-model gpt-image-1-mini(默认,便宜)或 gpt-image-1(高级) 视频: --video-provider sora(默认),sora-pro,seedance-lite,seedance-pro,veo-fast,veo-audio 质量: --image-quality low|medium|high

成本追踪

每个脚本在执行前后都会输出成本。始终先运行 --dry-run。 成本数据保存到 {outdir}/cost_estimate.json 和 {outdir}/visuals_meta.json。

环境变量

export SUNO_API_KEY="your-sunoapi-key"      # 必需 — sunoapi.org
export OPENAI_API_KEY="your-openai-key"     # 必需 — 图片 + Sora 视频
export BYTEPLUS_API_KEY="your-byteplus-key" # 可选 — Seedream 4.5(推荐用于图片)
export TOGETHER_API_KEY="your-together-key" # 可选 — Seedance, Veo, Imagen
export SUNO_CALLBACK_URL=""                 # 可选 — 参见下面的回调 URL

⚠️ 必需的密钥: 在运行任何脚本之前,必须设置 SUNO_API_KEY 和 OPENAI_API_KEY。 使用 Seedream 图片提供商时需要 BYTEPLUS_API_KEY(在 console.byteplus.com 注册,有 200 张免费图片)。 只有在使用 Seedance/Veo/Imagen 提供商时才需要 TOGETHER_API_KEY。

回调 URL

Suno API 在音乐生成请求中需要一个 callBackUrl 字段。 默认情况下,如果未设置 SUNO_CALLBACK_URL,脚本会使用 https://localhost/noop 作为一个无害的无操作端点(一个不可达的 localhost URL,有效地禁用了回调)。

要自定义: 将 SUNO_CALLBACK_URL 设置为您自己的端点,或设置为 您控制的任何虚拟 URL。回调负载包含任务元数据和 音频 URL — 不会发送任何 API 密钥。

要禁用: 将 SUNO_CALLBACK_URL=https://localhost/noop 或任何不可达的 URL。 生成仍然可以通过轮询工作;脚本运行不依赖回调。

角色工作流程(채널 컨셉 유지)

当像 YouTube 频道一样以一致风格创作多首歌曲时:

# 1. 生成第一首歌曲 + 创建角色
bash scripts/suno_music.sh \
  --prompt "코드 리뷰하며 듣는 노래" \
  --style "indie rock, energetic, coding vibe" \
  --title "Pull Request" \
  --custom --create-persona \
  --persona-name "개발자 노동요 싱어" \
  --persona-desc "개발자가 코딩하며 듣기 좋은 에너지 넘치는 보컬. 인디록, 일렉, 팝 장르를 넘나든다." \
  --persona-style "indie rock, electronic, developer work music" \
  --outdir /tmp/dev-bgm-01

# 2. 从 persona.json 中确认 personaId
cat /tmp/dev-bgm-01/persona.json

# 3. 使用相同的角色生成下一首歌曲 — 保持 vocals/风格一致性
bash scripts/suno_music.sh \
  --prompt "야근하면서 듣는 노래" \
  --style "electronic pop, night coding" \
  --title "Midnight Deploy" \
  --custom --persona-id <PERSONA_ID> \
  --outdir /tmp/dev-bgm-02

角色会记住 vocals 特性 + 音乐风格,从而保持整个频道的一致感。

前提条件

  • curl、python3、ffmpeg(用于组装)

参考资料

  • SunoAPI 详情: 阅读 references/sunoapi.md
  • 视觉提供商详情: 阅读 references/visual-providers.md

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

modbender/skill-library-mcp

Paid acquisition strategy, budget allocation, and avoiding common advertising mistakes across platforms

modbender/skill-library-mcp

Complete investment portfolio risk management system. Analyze positions, calculate risk metrics, stress test scenarios, optimize allocations, and generate institutional-grade risk reports — all wit...

modbender/skill-library-mcp

Borrow from Aave via credit delegation. Agent self-funds by borrowing against delegator collateral. Supports borrow, repay, health checks. Works on Aave V2/V3.

modbender/skill-library-mcp

Discover and register autonomous AI agents. Use when: browsing the agent registry, submitting an agent for verification, or embedding agent badges. NOT for: general web search or agent capability analysis.

modbender/skill-library-mcp

Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human

modbender/skill-library-mcp

AI代码编辑器规则模板集合 - 为Cursor、Windsurf、Claude Code、Cline等AI编辑器提供项目规则配置。适用于需要配置AI编码助手规则的开发者,包含全栈Web、移动端、Vue3+SpringBoot等技术栈模板。

modbender/skill-library-mcp

Generate landing page code from product descriptions

modbender/skill-library-mcp

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

modbender/skill-library-mcp

Generate AI-powered notes from videos (document, outline, or graphic-text formats)

modbender/skill-library-mcp

The video AI notes tool is provided by Baidu. Based on the video download address provided by the user, it downloads and parses the video, and finally generates AI notes corresponding to the video (a total of three types of notes can be generated: document notes, outline notes, and image-text notes).

modbender/skill-library-mcp

Automated appointment management for beauty salons, clinics, studios, and photo booths. Handles booking requests, calendar sync, conflict detection, reminders, no-show tracking, and waitlist management.

modbender/skill-library-mcp

Bird identification, life list tracking, and trading card generation. Use this skill when the user: sends a bird photo to identify, says "set up my Birdfolio" or "set my region", asks "how's my checklist", asks "Birdfolio progress", asks "how many birds have I found", asks "show my Birdfolio" or "show my life list", asks "what's my rarest bird", or asks "tell me about [bird species]". Handles everything from first-time setup through ongoing life list tracking and visual trading card generation.

modbender/skill-library-mcp

Multi-project task and research management (JSON-first CLI)

modbender/skill-library-mcp

Track stock and crypto portfolios with CLI - real-time prices, P&L, dividend tracking, multiple portfolios

modbender/skill-library-mcp

Track cryptocurrency portfolios with real-time prices, P&L calculations, and allocation analysis. Query Bitcoin, Ethereum, Solana and 10,000+ token holdings.

modbender/skill-library-mcp

加密貨幣Portfolio追蹤 - 支援TRON/ETH/BSC,分析持倉、收益、Gas費用

modbender/skill-library-mcp

Lead strategy with competitive analysis, strategic planning, growth roadmaps, and business portfolio management.

modbender/skill-library-mcp

Create ATS-optimized resumes and CVs with proper structure, metrics, and industry targeting.

modbender/skill-library-mcp

Use this skill when the user asks to build, create, design, develop, or improve ANY frontend interface, web page, UI component, or visual element. This includes: - Building landing pages, websites, web apps, dashboards, portfolios, or any web interface - Creating UI components (buttons, forms, cards, navbars, modals, etc.) - Designing pages with React, Vue, Next.js, Svelte, or any frontend framework - Adding styling or improving visual design of existing components - Implementing specific design aesthetics (modern, dark, minimalist, brutalist, etc.) - User mentions "frontend", "UI", "UX", "design", "interface", "web design", or "styling" - User asks for "beautiful", "modern", "professional", "clean", or any aesthetic adjective - User requests help with CSS, Tailwind, styled-components, or any styling approach This skill automatically retrieves the appropriate design system prompt (Neo-brutalism, Modern Dark, Bauhaus, Cyberpunk, Material, etc.) to help create visually distinctive, production-grade frontend...

modbender/skill-library-mcp

Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization or description needed, (3) Extracting text, UI elements, or information from screen recordings, (4) Answering questions about video content, (5) Comparing multiple videos, (6) Analyzing tutorials, demos, or walkthroughs.

相关技能