Easel is an open-source content workspace and AI agent for managing social media from trend discovery through planning, content creation, publishing, and performance analysis. It is intended for social media creators and maintains separate account profiles, content projects, platform adaptations, and publishing records. The catalogue skills support these content and publishing workflows.
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-editingWrote 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-editing)<a href="https://agentmods.dev/skills/zju-real/easel/audio-editing"><img src="https://agentmods.dev/badge/skills/zju-real/easel/audio-editing/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/audio-editing"><img src="https://agentmods.dev/badge/skills/zju-real/easel/audio-editing.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 | $0.00164 | $0.01342 |
| Opus 5.5 | $0.00066 | $0.00537 |
| Sonnet 5.5 | $0.00033 | $0.00268 |
| Haiku 4.5 | $0.00016 | $0.00134 |
Grade A, and why
audio-editing 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
通用音频处理
除降噪外的通用音频操作：裁剪、转码、音量归一化、提取音轨、拼接、淡入淡出、变速。全部通过共享脚本 skills/shared/scripts/audio_ops.py 封装 ffmpeg，参数确定、可复现，不现场手拼命令。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| input_file | 是 | 音频或视频文件路径 |
| operation | 是 | trim / convert / normalize / extract / concat / fade / speed / denoise / info |
| output_file | 否 | 默认 outputs/主题名/{name}-{op}.{ext} |
支持格式：wav / mp3 / m4a / aac / flac，视频容器 mp4 / mkv / mov（提取音轨）。
输出
- 处理后的音频文件（放入
outputs/主题名/） - 每次操作打印实际执行的 ffmpeg 命令 + 输出文件的时长/码率/声道/采样率
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/audio_ops.py。每个子命令都支持 -h。
0. 环境检查 + 探测
python skills/shared/scripts/audio_ops.py info input.mp3
脚本自身会检查 ffmpeg/ffprobe，缺失时给安装提示。先 info 展示文件时长/码率/声道再动手。
1. 裁剪 trim
# 起止时间
python skills/shared/scripts/audio_ops.py trim in.mp3 -o outputs/主题名/clip.mp3 --start 00:00:05 --end 00:00:20
# 起点 + 时长
python skills/shared/scripts/audio_ops.py trim in.mp3 -o clip.mp3 --start 5 --duration 15
2. 转码 convert
python skills/shared/scripts/audio_ops.py convert in.wav -o out.mp3 --bitrate 192k
python skills/shared/scripts/audio_ops.py convert in.m4a -o out.wav --sample-rate 44100 --channels 2
输出格式由扩展名决定（mp3/wav/m4a/aac）。
3. 音量归一化 normalize
python skills/shared/scripts/audio_ops.py normalize in.mp3 -o out.mp3
默认 loudnorm 到 -14 LUFS / -1.5 dBTP（社媒/播客通用响度）。可用 --i --tp --lra 覆盖。
4. 提取音轨 extract
python skills/shared/scripts/audio_ops.py extract video.mp4 -o audio.m4a
python skills/shared/scripts/audio_ops.py extract video.mp4 -o audio.aac --copy # 不重编码，最快
5. 拼接 concat
python skills/shared/scripts/audio_ops.py concat a.mp3 b.mp3 c.mp3 -o all.mp3
按参数顺序拼接，重编码方式兼容不同采样率/容器。
6. 淡入淡出 fade
python skills/shared/scripts/audio_ops.py fade in.mp3 -o out.mp3 --fade-in 2 --fade-out 3
--fade-out 自动定位到结尾前 N 秒。
7. 变速 speed（保持音高）
python skills/shared/scripts/audio_ops.py speed in.mp3 -o out.mp3 --factor 1.5 # 1.5 倍速
python skills/shared/scripts/audio_ops.py speed in.mp3 -o out.mp3 --factor 0.8 # 放慢
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.
- 1mo ago First seen · 118 lines · 164 tokens per session scan A 96869103fe5d
audio-editing is a skill published in the GitHub repository ZJU-REAL/Easel (4,052 stars, last pushed 2d ago), licensed Apache-2.0. It adds 164 tokens to every session and 1,342 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
jacky-motion2-0
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-editor
Use when professional video post-production using FFmpeg — color grading, audio design, kinetic typography, transitions, motion effects, captions, brand overlays, and platform-optimized export for promotional and marketing videos. Use when editing videos, adding captions, color grading, or creating promo content.
digital-real-estate
Use when build and manage a portfolio of niche content sites generating affiliate and AdSense revenue with AI handling research, writing, SEO, and updates. Use when building and manage a portfolio of niche content sites generating.
ai-newsletter
Use when building and monetizing AI-powered email newsletters. Curate content, automate writing, and grow paid subscriptions. Generate $1K-20K/month.
p-video-2-pro-reference
Use when someone wants one cinematic clip that locks a subject from references — a product still, character, clip, or voice — using image or video references plus optional audio kept as the soundtrack or used as guidance. Not for text-only generation, 1080p, or drafts.
p-video
Use when someone wants a simple short clip from text or images — quick B-roll, drafts, or start/end frame animation. Not when the brief needs cinematic generation, highest quality, tight lip-sync, or imported audio at 1080p.