Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/ai-musicWrote 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/zju-real/easel/ai-music)<a href="https://agentmods.dev/skills/zju-real/easel/ai-music"><img src="https://agentmods.dev/badge/skills/zju-real/easel/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/zju-real/easel/ai-music"><img src="https://agentmods.dev/badge/skills/zju-real/easel/ai-music.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 56 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00161 | $0.01597 |
| Opus 5 | $0.00081 | $0.00798 |
| Sonnet 5 | $0.00032 | $0.00319 |
| Haiku 4.5 | $0.00016 | $0.00160 |
Grade A, and why
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 音乐 / BGM 生成（AI Music）
给短视频、Vlog、社媒内容生成原创背景音乐 / 配乐 / 纯音乐。全程通过共享脚本
skills/shared/scripts/ai_music.py 封装音乐生成 API（可插拔 provider），
异步提交 → 轮询 → 下载。生成的音乐可再交给 audio_ops.py / video_ops.py
做裁剪、归一化或加到视频。
边界：本 SKILL 只做背景音乐 / 配乐。要人声口播 / 旁白 / 朗读用 tts-voiceover。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| prompt | 是 | 风格 / 情绪 / 乐器描述（如“轻快 lo-fi，钢琴+鼓点，vlog 片头”） |
| provider | 否 | dashscope 或 suno-compatible，也可用 env MUSIC_PROVIDER |
| lyrics | 否 | 歌词（提供后走带演唱模式，不再是纯音乐） |
| duration | 否 | 时长（秒），部分 provider 支持 |
| instrumental | 否 | 纯音乐（无人声 BGM） |
| output | 否 | 默认 outputs/主题名/{name}.mp3 |
输出
- 音乐音频文件（mp3，放入
outputs/主题名/） - 打印实际提交的 provider / model、任务轮询过程、最终输出路径
配置（需设的环境变量）
配置检查路径铁律：先
cd到AGENTS.md末尾给出的 Easel 项目根，确认当前目录有.env和skills/shared/scripts/，再运行注册表、check或生成命令。不得改用 workspace 的./shared/scripts/...，也不得以env/printenv没显示变量为由判断未配置。
在项目根 .env 或环境变量中设置（脚本自动向上查找 .env）。用户自己填 key。
通用
MUSIC_PROVIDER=dashscope # 或 suno-compatible；也可用 --provider 覆盖
provider = dashscope（阿里云 DashScope / 百炼）
DASHSCOPE_API_KEY=... # 必填（别名 DASHSCOPE_KEY / ALIYUN_API_KEY）
DASHSCOPE_MUSIC_MODEL=audio-generation # 可选（兼容旧名 DASHSCOPE_MODEL）
DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1 # 可选
provider = suno-compatible（Suno 类第三方 API 网关）
MUSIC_API_KEY=... # 必填
MUSIC_BASE_URL=https://api.example.com/v1 # 必填，你的 API 根地址
MUSIC_MODEL=music-1 # 可选，按服务商模型名调整
执行步骤
先跑 python skills/shared/scripts/model_registry.py configured --group music --env-file .env。只有一个可用时直接显式传 --provider；多个可用且用户没点名时，先列出选项询问，不按 MUSIC_PROVIDER 擅自选择。
脚本路径（相对项目根）：skills/shared/scripts/ai_music.py。每个子命令支持 -h。
1. 先自检配置 check（不发请求）
python skills/shared/scripts/ai_music.py check --provider dashscope
缺 key 会明确列出缺哪个 env（含别名提示）。配置齐了再往下。
2. 生成音乐 generate
# 纯音乐 BGM（dashscope）
python skills/shared/scripts/ai_music.py generate --provider dashscope \
--prompt "轻快的 lo-fi 嘻哈，钢琴 + 柔和鼓点，适合 vlog 片头" \
--duration 30 --instrumental \
-o outputs/主题名/vlog-bgm.mp3
# 带演唱（suno-compatible，给了歌词）
python skills/shared/scripts/ai_music.py generate --provider suno-compatible \
--prompt "温暖的民谣，吉他弹唱" \
--lyrics "$(cat lyrics.txt)" \
-o outputs/主题名/song.mp3
What ships with it
1 file 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 First seen · 116 lines · 161 tokens per session scan A 8d0968aeaa3f
ai-music is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 161 tokens to every session and 1,597 once invoked, about $0.0008 per session on Opus 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 2026-08-30.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…