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/audio-visualizerWrote 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/audio-visualizer)<a href="https://agentmods.dev/skills/zju-real/easel/audio-visualizer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/audio-visualizer.svg" alt="Measured on agentmods" 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 | $0.00185 | $0.01168 |
| Opus 5 | $0.00093 | $0.00584 |
| Sonnet 5 | $0.00037 | $0.00234 |
| Haiku 4.5 | $0.00018 | $0.00117 |
Grade A, and why
audio-visualizer 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 8d 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.
What it actually says
音频可视化视频
把音频渲染成带动态波形/频谱的视频，配封面+标题，让纯音频能发到视频平台。全部走
skills/shared/scripts/audio_viz.py，不要手拼 showwaves/showcqt 滤镜。
输出音频（混音）见 audio-mix；用图片做视频见 slideshow-video； 给已有视频加字幕见 auto-subtitle。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 音频文件 | 是 | 播客/音乐/口播片段（没给就问） |
| 画幅 | 是 | 用户或上游任务未明确横版/竖版（或具体分辨率）时，制作前必须追问并等确认；不得按平台、Profile 或默认值静默推断，已明确则不重复问 |
| 模式 | 否 | cqt（默认，音乐最好看）/ bars / waves / spectrum |
| 封面 | 否 | 居中封面图（专辑封面/头像/主题图） |
| 标题 | 否 | 顶部标题文字 |
输出（outputs/主题名/）
- 可视化视频（
*.mp4，音频已嵌入） - 报告：模式、时长、画幅
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/audio_viz.py（render -h 看参数）。
# 音乐/金句：CQT 音乐频谱（随音符跳动，最好看）
python skills/shared/scripts/audio_viz.py render -i clip.mp3 \
-o outputs/主题名/out.mp4 --mode cqt --title "本期金句" --cover cover.jpg
# 播客口播：底部波形条 + 封面
python skills/shared/scripts/audio_viz.py render -i podcast.mp3 \
-o outputs/主题名/out.mp4 --mode waves --cover avatar.png --size 1080x1920
# 律动柱状 / 滚动声谱
python skills/shared/scripts/audio_viz.py render -i song.mp3 -o out.mp4 --mode bars
python skills/shared/scripts/audio_viz.py render -i song.mp3 -o out.mp4 --mode spectrum
模式怎么选
| 模式 | 观感 | 适用 |
|---|---|---|
cqt |
全屏音符频谱，随旋律跳动 | 音乐、有旋律的内容（默认） |
bars |
底部频谱柱，律动感强 | 音乐、卡点、电台 |
waves |
底部波形线，简洁干净 | 播客、口播、访谈 |
spectrum |
全屏滚动声谱图，科技感 | 电子/科技类、氛围 |
--bg-image 换背景图，--color 换背景色，--wave-color 换波形颜色。
Profile 感知
- 有 Profile：
platforms.md只用于给出画幅建议，仍须用户确认；标题/封面风格贴合账号； 播客/口播账号默认waves，音乐账号默认cqt/bars。 - 无 Profile：先确认横版/竖版；默认 cqt 模式。
规则
- 长音频先用 audio-editing/text-condenser 截出金句片段再可视化，别整集渲染。
- 音频原声完整嵌入输出，不重采样丢质量。
- 封面图会等比缩放居中，标题自动描边保证可读。
- 产物统一进
outputs/主题名/。
参考来源
音频波形/频谱可视化用 ffmpeg showwaves/showfreqs/showspectrum/showcqt，是播客/音频号
上视频平台的标准做法。把各可视化滤镜与封面/标题合成封装成确定性脚本。
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.
- 8d ago First seen · 76 lines · 185 tokens per session scan A d8d007d2de8c
audio-visualizer is a skill published in the GitHub repository ZJU-REAL/Easel (411 stars, last pushed today), licensed Apache-2.0. It adds 185 tokens to every session and 1,168 once invoked, about $0.0009 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…