← 返回 Skills 市场
nitishgargiitd

Music Cog

作者 CellCog · GitHub ↗ · v1.0.10 · MIT-0
darwinlinuxwindows ✓ 安全检测通过
3649
总下载
4
收藏
18
当前安装
11
版本数
在 OpenClaw 中安装
/install music-cog
功能描述
AI music generation powered by CellCog. Original instrumental and vocal tracks, 5 seconds to 10 minutes. Cinematic scores, background tracks, podcast intros,...
使用说明 (SKILL.md)

Music Cog - Original Music, Fully Yours

Music generation — 5 seconds to 10 minutes. Instrumental and vocal tracks with high-quality AI vocals.

Generated tracks are royalty-free for commercial use per CellCog's terms of service — YouTube, podcasts, apps, games, ads, films, streaming.

How to Use

For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.

OpenClaw (fire-and-forget):

result = client.create_chat(
    prompt="[your task prompt]",
    notify_session_key="agent:main:main",
    task_label="my-task",
    chat_mode="agent",
)

All agents except OpenClaw (blocks until done):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
result = client.create_chat(
    prompt="[your task prompt]",
    task_label="my-task",
    chat_mode="agent",
)
print(result["message"])

Two Ways to Create Music

Simple Prompt (Use This 99% of the Time)

Just describe what you want. The model handles the rest — genre, arrangement, instrumentation, dynamics, and even lyrics:

"Compose a 90-second cinematic score. Start with solo piano, layer in strings at 30 seconds, build to a full orchestral swell, then resolve softly. Mood: bittersweet turning hopeful."

"Create a 3-minute lo-fi hip-hop track with soft piano, vinyl crackle, and mellow drums. 75 BPM. Study vibes."

"Write a 2-minute upbeat pop song with female vocals about starting fresh on a Monday morning. Catchy chorus, feel-good energy."

The model is exceptionally sophisticated — it handles any genre, genre fusion, songs with lyrics, complex arrangements, and mood transitions from a simple description.

Composition Plan (For Precise Timing Control)

Only use this when you need exact section durations — for example, syncing music to specific video segments or presentation slides:

"I need music that syncs with my video:

  • Intro: exactly 10 seconds, soft ambient
  • Build: exactly 20 seconds, energy rising
  • Climax: exactly 15 seconds, full orchestra
  • Outro: exactly 10 seconds, gentle fade"

This mode gives precise timing control per section but should only be used when timing accuracy matters for syncing with other media.


What Music You Can Create

Instrumental

Type Example
Cinematic scores Epic orchestral, tense thriller, emotional piano, sci-fi ambient
Background tracks Lo-fi beats, corporate background, cafe jazz, ambient soundscapes
Podcast intros/outros 5-10 second branded stings, transitions, bumpers
Game soundtracks Battle themes, exploration music, boss fights, menu themes
Jingles Ad jingles, notification sounds, reveal stingers
Ambient Meditation, nature soundscapes, focus music

Vocal Tracks

CellCog generates songs with perfect AI vocals — just describe the lyrical theme:

Type Example
Pop songs Catchy hooks, verse-chorus structure, radio-ready
Ballads Emotional, piano-driven, storytelling
Hip-hop/Rap Rhythmic vocals, beats, flow
Rock Guitar-driven, powerful vocals
R&B/Soul Smooth, melodic, groove

Specs

Parameter Range
Duration 5 seconds to 10 minutes
Output MP3 (44.1kHz, 128kbps)
Vocals Instrumental or with AI vocals
Licensing Royalty-free per CellCog terms of service

Chat Mode

Use chat_mode="agent" for music generation. Music executes well in agent mode.


Example Prompts

Cinematic score:

"Compose a 2-minute cinematic score for a nature documentary finale. Begin with solo cello (melancholic), layer in strings and piano at 40 seconds, build to a hopeful orchestral swell, resolve with gentle piano. Think Planet Earth meets Interstellar."

Lo-fi background:

"Create 5 minutes of lo-fi study beats. Soft piano, mellow drums, vinyl crackle, gentle bass. 75 BPM. Warm and unobtrusive — good for focus."

Podcast intro + outro:

"Create a podcast intro (8 seconds) and outro (6 seconds). Show is a tech startup podcast. Intro: energetic, modern electronic with a hook. Outro: same vibe but mellower wind-down. Should feel like the same show."

Song with vocals:

"Write a 3-minute upbeat indie pop song with female vocals. Theme: the excitement of moving to a new city. Catchy chorus, acoustic guitar foundation, builds with drums and synth. Feel-good, sing-along energy."

Game soundtrack:

"Compose a 2-minute boss battle theme for a fantasy RPG. Intense orchestral with choir, driving percussion, escalating tension. Think Dark Souls meets Final Fantasy."


Tips

  1. Describe the feeling, not just the genre: "Music that makes a startup pitch feel like the future" works better than "electronic music."

  2. Specify duration: "45 seconds" vs "3 minutes" changes composition structure significantly.

  3. Reference moods, not copyrighted songs: "Hans Zimmer-style epic" and "ChilledCow lo-fi vibes" work well. Do not reference specific copyrighted songs.

  4. For vocals: Set the lyrical theme and mood. The model writes lyrics that fit. Or provide specific lyrics you want sung.

  5. Energy arc matters: "Starts quiet, builds at midpoint, resolves softly" gives clear compositional structure.

  6. For video background music: If the music is for a CellCog video, mention it in your video prompt instead — CellCog handles music as part of video production automatically.


If CellCog is not installed

Run /cellcog-setup (or /cellcog:cellcog-setup depending on your tool) to install and authenticate. OpenClaw users: Run clawhub install cellcog instead. Manual setup: pip install -U cellcog and set CELLCOG_API_KEY. See the cellcog skill for SDK reference.

安全使用建议
This skill appears to be what it says: a CellCog-backed music generator. Before installing, confirm you trust CellCog and understand their terms/privacy (generated audio and any uploaded prompts will go to their service). Provide a CELLCOG_API_KEY with least-privilege and monitor usage/billing. Note the skill lists a 'cellcog' dependency but provides no install steps — ensure the runtime environment already has the SDK or be prepared for the agent to attempt package installation. Avoid sending sensitive or private data (lyrics or transcripts containing secrets) to the service, and rotate the API key if you stop using the skill.
功能分析
Type: OpenClaw Skill Name: music-cog Version: 1.0.10 The music-cog skill bundle is a standard integration for the CellCog AI music generation service. The SKILL.md file provides legitimate documentation, usage examples, and configuration instructions for an AI agent to generate audio tracks. There is no evidence of malicious intent, data exfiltration, or harmful prompt injection; the required environment variable (CELLCOG_API_KEY) and dependencies (cellcog) are consistent with the stated purpose of the tool.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
Name/description match the requested resources: python3 and CELLCOG_API_KEY are expected for a Python SDK client talking to the CellCog service. Declared dependency 'cellcog' is consistent with a CellCog SDK.
Instruction Scope
SKILL.md instructs the agent to call the CellCog client API (create_chat) and to provide music prompts; it does not direct reading unrelated system files, broad data collection, or exfiltration to unexpected endpoints.
Install Mechanism
This is instruction-only (no install spec), which is low risk. Minor inconsistency: dependencies list 'cellcog' but there are no install instructions (e.g., pip). That likely means the environment must already provide the package or the agent will attempt to install it at runtime.
Credentials
Only CELLCOG_API_KEY is required — appropriate and proportional for a third-party music generation API. No unrelated secrets or broad system credentials are requested.
Persistence & Privilege
always is false and there are no claims of modifying other skills or system-wide settings. The skill can be invoked autonomously by the agent (default), which is normal for skills of this type.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install music-cog
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /music-cog 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.10
- Added OpenClaw requirements for binaries and environment variables: `python3` and `CELLCOG_API_KEY`. - Updated the skill metadata to specify required dependencies for correct operation. - No changes to usage or functionality.
v1.0.9
- Clarified AI music generation in the description; emphasized royalty-free, original tracks. - Updated agent usage instructions to better differentiate between OpenClaw and other agents. - Streamlined installation/setup instructions, including clearer guidance for different platforms. - No changes to API or music creation features, just documentation improvements for user clarity.
v1.0.8
- Updated SKILL.md with a revised and expanded description to highlight frontier music generation models and an extended list of supported music types. - Clarified code examples: added explicit import and initialization for `CellCogClient` under the Cursor/Claude Code instructions. - Improved and streamlined introductory and instructional content for better clarity and usability. - No changes to source code or underlying music generation logic—documentation update only.
v1.0.7
- Clarified that music is royalty-free per CellCog's terms of service. - Updated usage instructions for different agents and clarified when to consult the main CellCog skill for detailed SDK reference. - Condensed and streamlined the introduction, emphasizing royalty-free commercial use. - Added a section on what to do if CellCog is not installed, with instructions for Cursor, OpenClaw, and other agents. - Minor wording changes and simplifications throughout for clarity and brevity.
v1.0.6
Major documentation rewrite and clarity improvements. - Rewrote and expanded documentation for clarity and ease of use. - Added clear guidance on using simple prompts vs. detailed composition plans. - Provided genre and use-case tables for both instrumental and vocal music. - Outlined licensing: all generated music is royalty-free and 100% user-owned. - Added prompt-writing tips and comprehensive usage examples. - Presented supported parameters (duration, output, vocals, licensing) in a clear spec table.
v1.0.5
- New concise overview focused on music generation features and use cases. - Expanded description to clarify support for instrumental, vocal, and all genres. - Added notes on audio production (speech, SFX), and relevant output (MP3). - Listed related skills for broader audio/video tasks. - Removed in-depth prompt examples and detailed feature breakdowns for brevity.
v1.0.4
- Added detailed guidance for using the skill with OpenClaw agents, including updated code examples for recommended fire-and-forget usage. - Clarified distinction between OpenClaw agent workflow and other agent workflows. - Updated prerequisites section for better SDK/API setup instructions. - No changes to features or functionality. Documentation improved for developer clarity.
v1.0.3
- Updated the "Quick start" example to be more general and reference the cellcog documentation for full SDK usage. - Clarified that full SDK/API reference and advanced options are covered in the cellcog skill, encouraging users to consult it. - No changes to music generation functionality or examples; documentation improvements only.
v1.0.2
- Added supported operating systems (darwin, linux, windows) to skill metadata. - Included a homepage link for CellCog in the metadata.
v1.0.1
- Added "author: CellCog" and "dependencies: [cellcog]" fields for clearer attribution and dependency management. - Clarified prerequisite instructions by referencing the `cellcog` skill and updating install guidance. - No functional changes to code or usage instructions.
v1.0.0
- Initial release of music-cog skill for original music generation. - Supports creating instrumental and vocal tracks (including songs with lyrics) from 5 seconds to 10 minutes. - Delivers royalty-free music suitable for commercial use (YouTube, podcasts, games, ads, etc.). - Offers simple prompt mode and composition plan mode for precise timing needs. - Requires CellCog skill for SDK and API integration. - Output format: MP3 (44.1kHz, 128kbps); supports any genre, mood, and structure via flexible prompting.
元数据
Slug music-cog
版本 1.0.10
许可证 MIT-0
累计安装 18
当前安装数 18
历史版本数 11
常见问题

Music Cog 是什么?

AI music generation powered by CellCog. Original instrumental and vocal tracks, 5 seconds to 10 minutes. Cinematic scores, background tracks, podcast intros,... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 3649 次。

如何安装 Music Cog?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install music-cog」即可一键安装,无需额外配置。

Music Cog 是免费的吗?

是的,Music Cog 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Music Cog 支持哪些平台?

Music Cog 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(darwin, linux, windows)。

谁开发了 Music Cog?

由 CellCog(@nitishgargiitd)开发并维护,当前版本 v1.0.10。

💬 留言讨论