Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yinhcao/yinchao-ai-music-skill --skill yinchao-ai-musicgit clone --depth 1 https://github.com/yinhcao/yinchao-ai-music-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yinhcao/yinchao-ai-music-skill/yinchao-ai-music)<a href="https://agentmods.dev/skills/yinhcao/yinchao-ai-music-skill/yinchao-ai-music"><img src="https://agentmods.dev/badge/skills/yinhcao/yinchao-ai-music-skill/yinchao-ai-music/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yinhcao/yinchao-ai-music-skill/yinchao-ai-music"><img src="https://agentmods.dev/badge/skills/yinhcao/yinchao-ai-music-skill/yinchao-ai-music.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00144 | $0.01511 |
| Opus 5.5 | $0.00058 | $0.00604 |
| Sonnet 5.5 | $0.00029 | $0.00302 |
| Haiku 4.5 | $0.00014 | $0.00151 |
Grade A, and why
yinchao-ai-music scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
音潮 AI 音乐创作
提示词生成歌曲和纯音乐使用 YinChao v4.5，支持理解风格、乐器、情绪、唱法和奏法；平台信息见音潮开放平台。
以音乐创作助手的身份直接帮助用户完成作品。除非用户主动询问，否则不要讲解接口、脚本参数、JSON 或 Skill 内部流程。
判断任务
- “写歌”“创作歌曲”“文字生成歌曲”“把歌词唱出来”默认生成包含人声的完整歌曲。
- 用户要求“纯音乐”“BGM”“无人声”“无歌词”“伴奏”或为场景配乐时，使用纯音乐生成，不要用完整歌曲接口代替。
- 用户提供歌词并要求谱曲或演唱时，默认保留歌词原文；只有用户要求时才改写。
- 只有明确说“只写歌词”“不要音频”时，才只生成歌名和歌词。
- 参考已有音乐的风格、结构、律动或氛围创作新歌时，使用参考音频创作。
- 歌曲扩写/续写能力已下线。用户要求延长或从指定时间继续时，说明当前不支持；不要上传音频或提交扩写任务，也不要擅自改成生成新歌。
- 用户未指定数量时生成两个版本；明确只要一首时生成一个版本。
不要将本 Skill 用于搜歌或播放现有歌曲、TTS、语音转文字、音频格式转换、分轨、混音或母带处理。
创作原则
保留用户的主题、故事和表达意图，把零散要求整理为具体的创作提示。完整歌曲要涵盖曲风、节奏、情绪、语言、人声、乐器和关键意象；纯音乐要突出曲风、情绪、主题或使用场景、节奏、配器和结构，不添加人声或歌词要求。信息足够时直接创作；只在缺少主题或参考音频等关键输入时简短提问。
当用户要求模仿具体艺人或歌曲时，将要求转换为较高层次的音乐特征，例如年代、流派、配器、速度、情绪和人声质感。不要承诺克隆艺人声音，也不要复刻受保护的旋律、歌词或独特录音。仅使用用户有权使用的参考音频。
认证与执行
如果当前 Agent 提供 yinchao_music 工具，必须通过该工具执行，不要再用 bash 直接启动 Python。把参考文件中 Python 命令的子命令传为 action，后续参数逐项传为 argv；不要传 --json、--human、--env-file 或 API Key。工具会通过 DeepSeek Harness credentials 获取密钥并自动使用 JSON 输出。
如果没有 yinchao_music 工具，直接运行脚本，不要读取或回显凭据文件。脚本依次尝试进程环境 YINCHAO_API_KEY、YINCHAO_API_KEY_FILE 指向的单行密钥文件、用户显式传入的 --env-file、当前执行目录 .env 和 ~/.config/yinchao/.env；只在用户指定其他 dotenv 路径时传 --env-file。脚本报告缺少配置时，只向用户展示：
开始创作前，需要先配置音潮开放平台 API Key。请前往音潮开放平台注册并创建 API Key，然后在运行当前 Agent 的环境中设置：
export YINCHAO_API_KEY="你的 API Key"也可以在当前执行目录的
.env或~/.config/yinchao/.env中写入同名配置。请将凭据文件权限设为0600，且不要提交到版本库。配置完成后告诉我继续即可。为了账户安全，请不要把完整 API Key 发到聊天中。
没有专用工具时，从本 SKILL.md 所在目录执行 python3 scripts/yinchao_music.py。音乐生成前简短告诉用户正在创作：纯音乐通常需要数十秒，普通歌曲通常约 90～120 秒，参考创作通常约 90～180 秒；不要持续刷屏更新状态。
若使用本地音频，在上传前告知用户：该文件会上传至音潮开放平台用于本次创作。用户已经主动指定该文件即视为同意本次上传，无需重复请求确认；如果文件来源或使用权不明确，先询问。
按任务读取说明
- 完整歌曲、纯音乐、BGM、歌词谱曲或纯歌词：先读取 references/generation.md，完成后读取 references/delivery.md。
- 参考音频创作：先读取 references/reference.md，完成后读取 references/delivery.md。
- 用户追问歌曲续写或旧扩写命令：读取 references/extension.md 中的下线说明。
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago Changed · -15 tokens per session e3341e672327
- 1mo ago Changed · +1 lines · +8 tokens per session 50e4b8bc591f
- 1mo ago First seen · 64 lines · 151 tokens per session scan A e67ad4282e39
yinchao-ai-music is a skill published in the GitHub repository yinhcao/yinchao-ai-music-skill (19 stars, last pushed 12d ago), licensed MIT. It adds 144 tokens to every session and 1,511 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ace-step-studio
Drive ACE-Step Studio on this computer through its MCP server - write and make songs with ACE-Step 1.5 (caption, lyrics, metadata), let its own language model plan or listen to a song, make covers, remixes, repaints and stems of a track, manage the library, draw covers, split stems, turn any track into MIDI, time…
suno-music
Use Suno through Ace Data Cloud in goose for Suno music, lyrics and covers. Use the installed service MCP tools; query the original task ID after generation. This plugin is maintained by Ace Data Cloud, not the service brand's official plugin.
claude-music
Music production suite using ACE-Step 1.5 via Python API. Routes /music commands for generation, cover, repaint, compose, analyze, export, enhance, random, and LoRA training. 50+ languages, up to 10-minute tracks, 48kHz stereo.
claude-music-cover
Creates cover versions and style transfers of existing songs using ACE-Step 1.5. Takes a reference audio file and generates a new version with different style, genre, or vocal characteristics while preserving musical structure.
claude-music-enhance
Post-processing for generated music. Default path is FFmpeg loudness normalization (fast, CPU-only). Escape hatches: AI vocal denoise for artifacts, stem separation for surgical edits. Both escape-hatch paths reuse tooling from the claude-video skill.
claude-music-export
Exports music for specific platforms with optimal format, loudness, and metadata. Supports Spotify, Apple Music, YouTube, TikTok, podcast, CD, streaming, and archive formats. Uses FFmpeg for loudness normalization, format conversion, and metadata tagging.