VRGDG H3 Short Film Pipeline
vrgamegirl19/comfyui-vrgamedevgirl
Builds an AI short film in a local ComfyUI with the VRGDG Video Builder, MiniMax H3 scenes, reference images, a music score, QA and a final edit.
音频降噪：去除录音中的背景噪声、电流声、风噪、嗡嗡声，基于 ffmpeg 滤镜链（afftdn/highpass/lowpass）。
Install Audio Denoise
$ npx skills add ZJU-REAL/Easel --skill audio-denoise -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ZJU-REAL/Easel audio-denoise --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw/audio-denoise .claude/skills/audio-denoise && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "audio-denoise" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise into .claude/skills/audio-denoise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-denoise", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoiseType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ZJU-REAL/Easel --skill audio-denoise -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ZJU-REAL/Easel audio-denoise --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/openclaw/audio-denoise .agents/skills/audio-denoise && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "audio-denoise" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise into .agents/skills/audio-denoise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-denoise", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ZJU-REAL/Easel --skill audio-denoise -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ZJU-REAL/Easel audio-denoise --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/openclaw/audio-denoise .cursor/skills/audio-denoise && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "audio-denoise" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise into .cursor/skills/audio-denoise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-denoise", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ZJU-REAL/Easel.git --path skills/openclaw/audio-denoise--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ZJU-REAL/Easel --skill audio-denoise -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ZJU-REAL/Easel audio-denoise --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/openclaw/audio-denoise .gemini/skills/audio-denoise && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "audio-denoise" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise into .gemini/skills/audio-denoise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-denoise", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ZJU-REAL/Easel audio-denoiseInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ZJU-REAL/Easel --skill audio-denoise -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/openclaw/audio-denoise .github/skills/audio-denoise && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "audio-denoise" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise into .github/skills/audio-denoise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-denoise", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ZJU-REAL/Easel --skill audio-denoise -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ZJU-REAL/Easel audio-denoise --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZJU-REAL/Easel.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/openclaw/audio-denoise .opencode/skills/audio-denoise && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "audio-denoise" agent skill from https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/audio-denoise into .opencode/skills/audio-denoise/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audio-denoise", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
audio-denoise- GitHub stars
- 3.3k
- Token cost
- ~762 tokens
- SKILL.md length
- 184 words
- Files
- 2
- Skills in repo
- 113
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
音频降噪：去除录音中的背景噪声、电流声、风噪、嗡嗡声，基于 ffmpeg 滤镜链（afftdn/highpass/lowpass）。
- Works in 4 steps: 探测输入文件 → 准备 RNN 模型（仅 Tier3） → 执行降噪 → …
- Tasks that involve Video production
- SKILL.md covers 输入, 输出, 三级降噪方案（对应脚本 --tier） and 执行步骤, plus 2 more sections
- Calls python and curl; reaches github.com
What it does
Audio Denoise is an agent skill from ZJU-REAL/Easel. 音频降噪：去除录音中的背景噪声、电流声、风噪、嗡嗡声，基于 ffmpeg 滤镜链（afftdn/highpass/lowpass）。 当用户说"降噪""去噪""去杂音""消除背景噪声""电流声""风噪""录音有杂音""音频降噪"时使用。 和 audio-editing 的区别：audio-editing 做剪辑/转码/音量等通用音频操作（内置 denoise 兜底），本 SKILL 专做降噪调参。
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `EASEL-META.md`).
It sits in Media & Creative, covering Video production and Music and audio generation. It works with FFmpeg. The repository describes itself as: An open-source AI agent for social media — discover trends, create content, publish everywhere, and learn what works across Xiaohongshu, Douyin, Zhihu, Bilibili, and more.🎨一个开源的… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Video production
- Tasks that involve Music and audio generation
Example prompts
- “消除背景噪声”
- “/audio-denoise”
Requirements
- Python 3
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 5e0ccc1. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
pythoncurl
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Audio Denoise loads about 762 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 184 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ZJU-REAL/Easel at commit 5e0ccc1, republished under its Apache-2.0 licence (© ZJU-REAL). 184 words, ~762 tokens.
Download SKILL.mdSave it as
.claude/skills/audio-denoise/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- audio-denoise
- description
- 音频降噪：去除录音中的背景噪声、电流声、风噪、嗡嗡声，基于 ffmpeg 滤镜链（afftdn/highpass/lowpass）。 当用户说"降噪""去噪""去杂音""消除背景噪声""电流声""风噪""录音有杂音""音频降噪"时使用。 和 audio-editing 的区别：audio-editing 做剪辑/转码/音量等通用音频操作（内置 denoise 兜底），本 SKILL 专做降噪调参。
- layer
- produce
音频降噪
清理录音中的背景噪声。降噪专项 SKILL——通过共享脚本 skills/shared/scripts/audio_ops.py denoise 封装 ffmpeg 降噪滤镜，提供三级方案（从基础滤波到 RNN 神经网络），参数确定、可复现，不现场手拼命令。
通用音频操作（裁剪/转码/音量/提取/拼接/淡入淡出/变速）见 audio-editing。本 SKILL 专注降噪。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| input_file | 是 | 音频或视频文件路径 |
| tier | 否 | 1 / 2 / 3（默认 2） |
| output_file | 否 | 默认 outputs/主题名/{filename}-clean.{ext} |
| mix | 否 | 降噪强度 0.0-1.0（默认 0.8，仅 tier3 RNNoise） |
| preserve_original | 否 | 保留原始文件（默认 true） |
支持格式：wav, mp3, flac, aac, m4a, mp4, mkv, mov。
输出
- 降噪后的音频文件（放入
outputs/主题名/） - 处理报告：原始文件信息、所用 tier 与滤镜链、输出文件信息、大小对比
三级降噪方案（对应脚本 --tier）
脚本按 tier 自动选滤镜链并打印实际执行的 ffmpeg 命令。
Tier 1 — 基础降噪（ffmpeg 内置滤波）
切除低频隆隆声、高频嘶嘶声 + FFT 降噪，纯 ffmpeg 无外部依赖。
滤镜：highpass=f=80,lowpass=f=8000,afftdn=nr=12:nf=-40:tn=1
适用：轻度噪声、无需模型的快速处理。
Tier 2 — 加强降噪（更强 FFT + 非局部均值）
更激进的 FFT 降噪叠加 anlmdn，仍纯 ffmpeg。
滤镜：highpass=f=70,afftdn=nr=24:nf=-30:tn=1,anlmdn=s=0.0005
适用：中度噪声、稳态背景噪声（空调/风扇/底噪）。默认档。
Tier 3 — RNN 神经网络降噪（arnndn + 后处理）
RNNoise 针对人声优化 + 高通预处理 + 动态压缩 + 响度归一化。
滤镜：highpass=f=60,arnndn=m=<model>:mix=<mix>,acompressor=...,loudnorm=...
适用：人声录音、播客、访谈、复杂噪声环境。
需要 RNNoise 模型 sh.rnnn；缺失时脚本自动降级 Tier2 并打印下载提示。
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/audio_ops.py。
1. 探测输入文件
python skills/shared/scripts/audio_ops.py info input_file脚本自身检查 ffmpeg/ffprobe，缺失时给安装提示。向用户展示时长/码率/声道，判断音频还是视频。
2. 准备 RNN 模型（仅 Tier3）
检查脚本旁 skills/shared/scripts/models/sh.rnnn 是否存在。不存在则下载：
mkdir -p skills/shared/scripts/models
curl -L https://github.com/GregorR/rnnoise-models/raw/master/somnolent-hogwash-2018-09-01/sh.rnnn \
-o skills/shared/scripts/models/sh.rnnn不下载也可——脚本会自动降级 Tier2。也可用 --model <path> 指定其它模型。
3. 执行降噪
# 默认 Tier2
python skills/shared/scripts/audio_ops.py denoise input.wav -o outputs/主题名/input-clean.wav --tier 2
# Tier3（RNNoise，人声）
python skills/shared/scripts/audio_ops.py denoise input.wav -o outputs/主题名/input-clean.wav --tier 3 --mix 0.8- 脚本会打印实际运行的 ffmpeg 命令（透明执行）。
- 视频输入自动
-c:v copy：只处理音轨，视频轨原样保留。
4. 验证输出 + 报告
脚本处理完自动打印输出文件的时长/码率/声道/采样率。如需完整对比：
python skills/shared/scripts/audio_ops.py info outputs/主题名/input-clean.wav报告内容：原始 vs 输出（格式/时长/大小/采样率）、所用 tier 与滤镜链、大小变化。
规则
- 绝不删除原始文件 — 即使用户未指定
preserve_original。 - 先探测再处理 — 始终先
info展示文件信息。 - 视频输入只动音频 — 脚本自动
-c:v copy。 - 透明执行 — 脚本打印实际 ffmpeg 命令。
- 降噪过度时 — 建议降低 tier 或
--mix（如 0.8→0.5）。 - 无 Profile 依赖 — 音频处理不需要账号画像。
自研参考
- FFmpeg afftdn/arnndn/anlmdn 滤镜文档
- xiph/rnnoise — RNN 噪声抑制
- GregorR/rnnoise-models — 预训练模型
- timsainb/noisereduce — Python 频谱门控（备选方案）
© ZJU-REAL, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/openclaw/audio-denoise of ZJU-REAL/Easel.
- SKILL.md
- EASEL-META.md
Open the folder on GitHubat commit 5e0ccc1
Compare with similar skills
Audio Denoise next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Audio Denoise this skillZJU-REAL/Easel | 3.3k | — | ~762 | Automated safety check: Pass | Apache-2.0 | |
| VRGDG H3 Short Film Pipelinevrgamegirl19/comfyui-vrgamedevgirl | 763 | — | ~4.2k | Automated safety check: Pass | Custom licence | |
| Qiaomu Cutjoeseesun/qiaomu-cut-skill | 372 | — | ~6.8k | Automated safety check: Notes | MIT | |
| ShowtimeFavioVazquez/showtime | 206 | — | ~3k | Automated safety check: Pass | MIT | |
| Media Productionleon-ai/leon | 18k | — | ~1k | Automated safety check: Pass | MIT | |
| Video Voiceover and Music MixerSpaceZephyr/creator-buddy | 1.6k | — | ~615 | Automated safety check: Pass | None |
Similar skills
Qiaomu Cut
joeseesun/qiaomu-cut-skill
把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video—including one-line requests such as “制作一个科普视频：介绍…
Showtime
FavioVazquez/showtime
A skill your agent uses when the user wants a video made, edited or finished: a launch or promo, product demo, explainer, trailer or teaser, tutorial or walkthrough, a screen recording turned into a…
Media Production
leon-ai/leon
Generates images, audio and video through Leon's media tools, joins them with FFmpeg, checks the output and attaches playable files for the owner.
Video Voiceover and Music Mixer
SpaceZephyr/creator-buddy
Adds sound to a finished video: generates narration from a script with TTS, finds royalty-free background music, and mixes everything together with ffmpeg.
Release Video
huytieu/COG-second-brain
Turn a product release (the list of shipped items plus real screen recordings) into a motion recap video and one explained demo per feature, with sound effects tied to on-screen motion and a…
More from ZJU-REAL/Easel
All 113 skills in this repoSkill Wechat Publisher
ZJU-REAL/Easel
微信公众号文章自动创作与发布工具。给定参考文章、文字或文档，自动搜索整理全网相关信息、生成图文并茂的公众号文章，并发布到微信公众号草稿箱。特别强调反 AI 检测写作。
Card Design
ZJU-REAL/Easel
社媒卡片视觉设计系统：提供配色、中文字体层级、满画幅布局、品类骨架和死空白/密度质检，避免模板化 PPT 与廉价 AI 感。
Ecom Details Image
ZJU-REAL/Easel
生成电商商品视觉方案：主图概念、场景图、详情页视觉方向和 AI 生图 Prompt. An agent skill from ZJU-REAL/Easel.
Infographic
ZJU-REAL/Easel
将数据或文字内容转化为可视化信息图，支持静态（AntV）和动画 GIF 两种模式。当用户需要制作信息图、数据可视化、流程图、对比图、动画图表、GIF 图表、思维导图、SWOT 分析图时调用。本地渲染信息图/GIF 动画；要单张静态图片 URL 用 chart-visualization，要 CSV/JSON→整页报告用 data-report
Novel Writer
ZJU-REAL/Easel
长篇小说/网文连载创作：从世界观、人设和三级大纲写到逐章正文，并用文件化状态维护伏笔、前情和跨章一致性. An agent skill from ZJU-REAL/Easel.
Paper Explainer
ZJU-REAL/Easel
科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。
Related
Works with
Categories
Questions about Audio Denoise
What does Audio Denoise do?
音频降噪：去除录音中的背景噪声、电流声、风噪、嗡嗡声，基于 ffmpeg 滤镜链（afftdn/highpass/lowpass）。. Audio Denoise is an agent skill from ZJU-REAL/Easel.
When should I use Audio Denoise?
Audio Denoise fits situations like: tasks that involve Video production; tasks that involve Music and audio generation.
How do I install Audio Denoise in Claude Code?
Run `npx skills add ZJU-REAL/Easel --skill audio-denoise -a claude-code`. Or copy the skill folder (skills/openclaw/audio-denoise in ZJU-REAL/Easel) into .claude/skills/audio-denoise in your project. Claude Code loads it when a task matches its description.
How do I install Audio Denoise in Codex?
Run `npx skills add ZJU-REAL/Easel --skill audio-denoise -a codex`. Or copy the skill folder (skills/openclaw/audio-denoise in ZJU-REAL/Easel) into .agents/skills/audio-denoise in your project. Codex loads it when a task matches its description.
Can I use Audio Denoise in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZJU-REAL/Easel --skill audio-denoise -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audio-denoise, .gemini/skills/audio-denoise, .github/skills/audio-denoise and .opencode/skills/audio-denoise in your project.
What does Audio Denoise need to run?
Going by SKILL.md and its folder, Audio Denoise needs the command-line tools its instructions call (python and curl). Our summary lists: Python 3.
Does Audio Denoise access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Audio Denoise safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Audio Denoise use?
Audio Denoise is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Audio Denoise use?
About 762 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Audio Denoise?
Skills that share tags, products or a category with Audio Denoise: VRGDG H3 Short Film Pipeline (vrgamegirl19/comfyui-vrgamedevgirl, 763 stars), Qiaomu Cut (joeseesun/qiaomu-cut-skill, 372 stars), Showtime (FavioVazquez/showtime, 206 stars) and Media Production (leon-ai/leon, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Audio Denoise?
ZJU-REAL (a GitHub organization) maintains it in ZJU-REAL/Easel, which has 3,310 GitHub stars. The repository holds 113 skills in this directory. The repository was last updated on October 9, 2026.
Source: ZJU-REAL/Easel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.