Agent skill

Audio Denoise

by godot-fun in godot-fun/gai

Reduces background noise in a single audio file using FFmpeg afftdn.

MITAuto-check passedMedia & Creative

Install Audio Denoise

skills CLI
$ npx skills add godot-fun/gai --skill audio-denoise -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install godot-fun/gai audio-denoise --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/audio-denoise .claude/skills/audio-denoise && rm -rf skills-src

Use ~/.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/

Facts

Skill name
audio-denoise
GitHub stars
182
Token cost
~465 tokens
SKILL.md length
149 words
Files
1
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

Reduces background noise in a single audio file using FFmpeg afftdn.

  • Works in 4 steps: Use the bundled script, not hand-written… → Default is light denoise — do not raise… → Missing Python/FFmpeg → populate… → …
  • The user wants audio denoise
  • SKILL.md covers Rules, Quick Start, Defaults and Common Flags, plus 2 more sections
  • Calls python

What it does

Audio Denoise is an agent skill from godot-fun/gai. Reduces background noise in a single audio file using FFmpeg afftdn. Use when the user wants audio denoise, noise reduction, hiss removal, room noise cleanup, or SFX/voice cleanup before normalization.

Its SKILL.md is about 470 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Video production and Database schema design. It works with FFmpeg. The repository describes itself as: A lightweight AI agent and skill workflow framework built with Godot. The licence is MIT.

When your agent uses it

  • The user wants audio denoise
  • Noise reduction
  • Room noise cleanup
  • SFX/voice cleanup before normalization

Example prompts

  • “Use the audio-denoise skill to reduce background noise in a single audio file using FFmpeg afftdn”
  • “/audio-denoise”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Use the bundled script, not hand-written afftdn filters.
  2. Default is light denoise — do not raise --nr unless the user asks; heavy denoise dulls transients.
  3. Missing Python/FFmpeg → populate .dependency/ per skill-dependency-manager, retry same command.
  4. Do not copy, move, or replace the source with denoised output — tell the user where audio-denoise/ files are; they swap assets manually…

What it can do on your machine

Read from SKILL.md and the folder at commit aff659b. 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:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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 465 tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 149 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~465

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 godot-fun/gai at commit aff659b, republished under its MIT licence (© godot-fun). 149 words, ~465 tokens.

Download SKILL.mdSave it as .claude/skills/audio-denoise/SKILL.md (or your agent's skills folder).
name
audio-denoise
description
Reduces background noise in a single audio file using FFmpeg afftdn. Use when the user wants audio denoise, noise reduction, hiss removal, room noise cleanup, or SFX/voice cleanup before normalization.

Audio Denoise

Reduce background noise via FFmpeg afftdn.

Rules

When this skill applies, read and follow skill-dependency-manager — run scripts as documented, install missing tools into .dependency/.

Quick Start

Denoise a single audio file, output to <audio-dir>/audio-denoise/<audio-name>:

bash
.dependency/python/python .ai/audio-denoise/denoise.py --audio path/to/audio.wav

Defaults

SettingDefaultNotes
Denoiseafftdnnr=10 dB, nf=-25 dB — conservative for SFX

Common Flags

--audio · --nr · --nf · --output

bash
.dependency/python/python .ai/audio-denoise/denoise.py --audio Audio/SFX/click.wav
.dependency/python/python .ai/audio-denoise/denoise.py --audio Audio/Voice/line.wav --nr 8

Originals are never modified. Input must be a single audio file (--audio), not a directory. Supported: .wav, .mp3, .ogg, .flac, .aac, .m4a, .wma.

Agent Notes

  1. Use the bundled script, not hand-written afftdn filters.
  2. Default is light denoise — do not raise --nr unless the user asks; heavy denoise dulls transients.
  3. Missing Python/FFmpeg → populate .dependency/ per skill-dependency-manager, retry same command.
  4. Do not copy, move, or replace the source with denoised output — tell the user where audio-denoise/ files are; they swap assets manually when ready.

Tests

From repo root:

bash
.dependency/python/python .ai/audio-denoise/test_denoise.py

Manual CLI examples: cli/audio-denoise.md

© godot-fun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/audio-denoise of godot-fun/gai.

Open the folder on GitHubat commit aff659b

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.

Audio Denoise compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audio Denoise this skillgodot-fun/gai182—~465Automated safety check: PassMIT
Video Understandcalesthio/OpenMontage65k—~841Automated safety check: PassAGPL-3.0
Video Shotseternityspring/reelbench-skills8682 repos~1.8kAutomated safety check: NotesApache-2.0
HyperFrames Video Entry Pointheygen-com/hyperframes59k3 repos~5.2kAutomated safety check: PassApache-2.0
Mobile Demo Film Editorsuperset-sh/superset15k—~1.8kAutomated safety check: PassCustom licence
Karaoke CaptionsAI-Builder-Club/skills1.3k1 repos~850Automated safety check: PassNone

Similar skills

  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    65k GitHub stars~841 tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Video Shots

    eternityspring/reelbench-skills

    拉片:把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面. An agent skill from eternityspring/reelbench-skills.

    868 GitHub starsUsed in 2 repos~1.8k tokens
    Media & CreativeAuto-check: notes
  • HyperFrames Video Entry Point

    heygen-com/hyperframes

    Entry point for making, editing and rendering videos from HTML compositions with HyperFrames, routing each request to the right workflow.

    59k GitHub starsUsed in 3 repos~5.2k tokens
    Media & CreativeAuto-check passed
  • Mobile Demo Film Editor

    superset-sh/superset

    Edits real mobile screen recordings into a configurable demo video with phone framing, title cards, cutaways and an end card, using a bundled renderer.

    15k GitHub stars~1.8k tokensUpdated today
    Media & CreativeAuto-check passed
  • Karaoke Captions

    AI-Builder-Club/skills

    Generate TikTok/Shorts-style karaoke captions using MLX Whisper, ASS subtitles, and FFmpeg libass.

    1.3k GitHub starsUsed in 1 repo~850 tokens
    Media & CreativeAuto-check passed
  • Video Scrub

    eternityspring/reelbench-skills

    把一条视频重建成「只有画面和声音」的干净文件——源片的元数据一概不搬: GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨,全部留在原地。

    868 GitHub starsUsed in 1 repo~1.3k tokens
    Media & CreativeAuto-check: notes

More from godot-fun/gai

All 36 skills in this repo
  • AI Text To Speech

    godot-fun/gai

    Zero-shot text-to-speech with voice cloning via IndexTTS2 (index-tts).

    182 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Audio Fade

    godot-fun/gai

    Applies fade-in and fade-out at the start and end of a single audio file using FFmpeg.

    182 GitHub stars~652 tokensUpdated today
    Auto-check passed
  • Normalizes a single audio file to consistent LUFS loudness with true-peak limiting using FFmpeg.

    182 GitHub stars~684 tokensUpdated today
    Auto-check passed
  • Standardizes a single audio file to 44100 or 48000 Hz and exports 16-bit PCM WAV using FFmpeg.

    182 GitHub stars~638 tokensUpdated today
    Auto-check passed
  • Audio Split

    godot-fun/gai

    Splits a single audio file into two segments (part 1 before the split point, part 2 after) using FFmpeg.

    182 GitHub stars~554 tokensUpdated today
    Auto-check passed
  • Audio To Ogg

    godot-fun/gai

    Converts a single audio file to OGG Vorbis using FFmpeg for Godot-ready compressed assets.

    182 GitHub stars~766 tokensUpdated today
    Auto-check passed

Works with

Questions about Audio Denoise

What does Audio Denoise do?

Reduces background noise in a single audio file using FFmpeg afftdn. Audio Denoise is an agent skill from godot-fun/gai. Reduces background noise in a single audio file using FFmpeg afftdn.

When should I use Audio Denoise?

Audio Denoise fits situations like: the user wants audio denoise; noise reduction; room noise cleanup; SFX/voice cleanup before normalization.

How do I install Audio Denoise in Claude Code?

Run `npx skills add godot-fun/gai --skill audio-denoise -a claude-code`. Or copy the skill folder (.agents/skills/audio-denoise in godot-fun/gai) 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 godot-fun/gai --skill audio-denoise -a codex`. Or copy the skill folder (.agents/skills/audio-denoise in godot-fun/gai) 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 godot-fun/gai --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). Our summary lists: Python 3.

Does Audio Denoise access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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 MIT 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 465 tokens (SKILL.md is roughly 1.9k 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: Video Understand (calesthio/OpenMontage, 65k stars), Video Shots (eternityspring/reelbench-skills, 868 stars), HyperFrames Video Entry Point (heygen-com/hyperframes, 59k stars) and Mobile Demo Film Editor (superset-sh/superset, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audio Denoise?

godot-fun (a GitHub organization) maintains it in godot-fun/gai, which has 182 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 8, 2026.

Source: godot-fun/gai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.