Create and Edit AI Music with RunComfy
Choosing a suitable music model and request format can require detailed platform knowledge. This skill routes each request and prepares the correct RunComfy workflow.
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "ai-music" from https://skillstore.io/skills/prime-skills-ai-music.md and its manifest at https://skillstore.io/api/skills/prime-skills-ai-music/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
正在使用「ai-music」。 Create a low-cost, 60-second instrumental loop for a calm puzzle game.
預期結果:
Recommended route: ACE Step base. The prepared brief uses ambient electronic tags, a steady low-intensity groove, seamless-loop direction, and no lyrics.
正在使用「ai-music」。 Extend my 30-second hook with a 20-second intro and a 40-second outro.
預期結果:
Recommended route: ACE Step audio-outpaint. The request preserves the source hook while adding both requested sections in one generation call.
正在使用「ai-music」。 Write a polished 45-second Spanish pop jingle with a strong chorus.
預期結果:
Recommended route: ElevenLabs Music for premium polish, with ACE Step 1.5 as a lower-cost multilingual alternative. The brief includes Spanish lyrics and section markers.
All static matches are false positives caused by Markdown formatting, documentation links, example media URLs, and transparent CLI behavior notes. No prompt injection, covert data exfiltration, hidden command execution, or unauthorized filesystem access was found.
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
https://skillstore.io/skills/prime-skills-ai-music/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/prime-skills-ai-music?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/prime-skills-ai-music?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/prime-skills-ai-music/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/prime-skills-ai-music.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>prime-skills. (2026). ai-music security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/prime-skills-ai-music/audits/1@techreport{prime-skills-prime-skills-ai-music-2026,
author = {prime-skills},
title = {ai-music security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/prime-skills-ai-music/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-music security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "prime-skills"
date-released: "2026-09-25"
url: "https://skillstore.io/skills/prime-skills-ai-music/audits/1"
identifiers:
- type: other
value: "skillstore:prime-skills-ai-music:audit:1"
description: "Skillstore immutable audit report identifier"
每位作者的技能都保留為獨立的可安裝項目。推薦變體依 Skillstore 證據排序。
為何此變體排名第一
skills-collective-ai-music
2026-09-09
Select a premium model and structure a polished vocal or instrumental brief for a campaign.
Create varied background tracks and loops with cost-sensitive ACE Step settings.
Replace a timed section or add an intro and outro without rebuilding the full track.
Create a 60-second instrumental track for [purpose]. Use [genre], [mood], [tempo], and [instruments]. Choose a cost-effective model.
Create a [duration] song in [language] with [genre] styling, [vocal type], and these lyrics: [lyrics]. Include clear verse and chorus sections.
Replace the section from [start time] to [end time] in [audio URL]. Match [style details] and use [lyrics or instrumental direction].
Develop [number] low-cost drafts for [brief], compare their musical direction, then prepare one premium [duration] final track within a budget of [amount].
作者
prime-skills授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
2aa351cb09c29b7287d263bd8ea81e9bee3b2a61
維護新鮮度
2026/9/30
使用量
0 次下載 · 0 次瀏覽
檔案結構
📄 SKILL.md
Animate Images with RunComfy Video Models
Different video requests require different models, media inputs, and prompt settings. This skill guides RunComfy model selection and CLI calls for animation, voiceover lip-sync, and combined references.
Edit Images with GPT Image on RunComfy
Targeted image edits can change details you want to preserve. This skill provides RunComfy commands and focused prompts for background changes, text replacement, and reference-based composition.
Relight Still Images with RunComfy
Existing photos may have lighting that does not match the desired mood or product presentation. This skill guides RunComfy relighting with model selection and precise lighting prompts.
Edit Image Regions with Masks or Descriptions
Local image edits need clear targeting and preservation constraints. This skill guides RunComfy model selection and CLI requests for masked inpainting or description-based edits.
Expand Video Canvases with RunComfy
Changing video formats can crop important action or leave empty borders. This skill guides prompt-driven canvas expansion through RunComfy and recommends dedicated workflows for stricter quality needs.
Create Lip-Synced Videos with RunComfy
Lip-sync workflows require different models for existing videos, portraits, and scripts. This skill selects a suitable RunComfy route and prepares the corresponding CLI workflow.
在 RunComfy 上使用 ElevenLabs 生成音樂
由 runcomfy-com
建立可用於製作的音樂提示詞和 CLI 呼叫可能既耗時又容易出錯。此技能會引導 Claude、Codex 和 Claude Code 在 RunComfy 上進行 ElevenLabs Music 生成，提供清楚的參數與工作流程建議。
在 RunComfy 上生成 ACE Step 音樂
由 runcomfy-com
建立平價的 AI 音樂通常需要端點選擇、結構化歌詞，以及可重複的 CLI 輸入。此技能會引導你透過 RunComfy 進行 ACE Step 生成、inpainting 和 outpainting。
建立姿勢控制的圖片與影片
由 runcomfy-com
姿勢控制生成通常需要選擇正確的模型和輸入格式。此技能會將圖片和影片請求路由至 RunComfy 工作流程。
使用 RunComfy 建立 AI 虛擬人影片
由 runcomfy-com
建立對嘴同步的虛擬人影片通常需要選擇正確的模型與輸入格式。此技能會將請求路由至 RunComfy 模型，並提供可直接使用的 CLI 呼叫指令。
將影像延伸至畫框之外
由 agentspace-so
裁切過的影像通常需要更寬的畫布，以用於橫幅、社群貼文或產品版面配置。此 skill 會引導 Claude、Codex 和 Claude Code 使用 RunComfy 模型進行影像外補，同時保留原始主體。
使用 RunComfy 模型路由編輯影片
由 runcomfy-com
當錯誤的模型處理工作時，影片編輯經常會失敗。此技能會將每個請求路由到相符的 RunComfy 模型，並搭配對應的提示詞與限制。