New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audition Voice Cleanup

by THU-SAGE in THU-SAGE/syll

Cleans a voice recording by driving Adobe Audition on a macOS host to reduce hiss, hum, background noise and sibilance, after asking for your consent.

MITAuto-check passedMedia & Creative

Install Audition Voice Cleanup

skills CLI
$ npx skills add THU-SAGE/syll --skill audition-clean-voice -a claude-code

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

GitHub CLI
$ gh skill install THU-SAGE/syll audition-clean-voice --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/THU-SAGE/syll.git skills-src && mkdir -p .claude/skills && cp -r skills-src/syll/skills/audition-clean-voice .claude/skills/audition-clean-voice && 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
audition-clean-voice
GitHub stars
303
Token cost
~1.2k tokens
SKILL.md length
614 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Cleans a voice recording by driving Adobe Audition on a macOS host to reduce hiss, hum, background noise and sibilance, after asking for your consent.

  • Works in 4 steps: You call clean_audio_in_audition with… → The tool launches / focuses Adobe… → The tool measures the result… → …
  • Removing hiss or hum from a voice recording
  • SKILL.md covers When To Reach For This, How It Works, Confirm Before Control and Honesty Protocol, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill calls a `clean_audio_in_audition` tool with the path to an audio file. The tool is not an in-process filter: it launches or focuses the real Adobe Audition app on a macOS host, opens the clip, applies noise reduction and de-essing, exports the result, measures the noise-floor reduction and whether the voice was preserved rather than just made louder, and returns a verdict. Before and after audio render inline.

Because the tool takes over the host's mouse and keyboard, the agent first calls it with `confirmed=false`, which only returns a consent question, passes that question to you and calls again with `confirmed=true` only after a clear yes. The agent reports only the tool's verdict (excellent, pass, partial, gain_only or failed) with its measured score, and says the cleanup is incomplete when the result is partial. Chinese trigger phrases are supported alongside English ones.

When your agent uses it

  • Removing hiss or hum from a voice recording
  • Reducing background noise in a narration or interview take
  • Softening harsh sibilance with de-essing

Example prompts

  • “Clean up ~/Recordings/interview.wav and remove the background hiss.”
  • “De-ess this narration, it has too much sibilance.”
  • “Remove the hum from my voice memo and tell me how much the noise floor dropped.”

Requirements

  • Adobe Audition installed on a macOS host
  • Your permission for the agent to take over the host's mouse and keyboard

Workflow steps

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

  1. You call clean_audio_in_audition with the path to the source audio file.
  2. The tool launches / focuses Adobe Audition, opens the clip, applies the
  3. The tool measures the result (noise-floor reduction, whether the voice
  4. The before and after audio render inline automatically — you do not need to

What it can do on your machine

Read from SKILL.md and the folder at commit 3741347. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Audition Voice Cleanup loads about 1.2k tokens when it runs. Until then it costs about 97 tokens; SKILL.md has 614 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 THU-SAGE/syll at commit 3741347, republished under its MIT licence (© THU-SAGE). 614 words, ~1,193 tokens.

Download SKILL.mdSave it as .claude/skills/audition-clean-voice/SKILL.md (or your agent's skills folder).
name
audition-clean-voice
description
Clean up a voice recording — remove hiss, hum, background noise, and harsh sibilance — by driving the real Adobe Audition app on a macOS host. Triggers: clean up audio, clean up the voice, remove hiss, remove hum, remove background noise, denoise, noise reduction, de-ess, reduce sibilance, repair voice, fix the recording. 中文触发词：降噪、去底噪、去杂音、去噪音、人声清理、清理录音、修复人声、去齿音、去咝声。

Audition Clean Voice

Use the clean_audio_in_audition tool to clean up a voice recording — reducing hiss, hum, broadband noise, and harsh sibilance. This is not a filter that runs in this process — it drives the real Adobe Audition application on a macOS host, opens the clip, applies the cleanup, and exports the result.

When To Reach For This

The user wants a recording to sound cleaner. Recognize the intent from phrases like:

  • English: "clean up this audio", "clean up the voice", "remove the hiss", "remove the hum", "get rid of the background noise", "denoise this", "reduce the noise", "de-ess", "too much sibilance", "repair the voice", "fix the recording".
  • 中文：「降噪」「去底噪」「去杂音」「去噪音」「帮我清理人声」「清理一下录音」「修复人声」 「去齿音」「去咝声」。

How It Works

  1. You call clean_audio_in_audition with the path to the source audio file.
  2. The tool launches / focuses Adobe Audition, opens the clip, applies the noise reduction / de-ess chain, and exports the cleaned audio.
  3. The tool measures the result (noise-floor reduction, whether the voice was preserved vs. only made louder) and returns a verdict.
  4. The before and after audio render inline automatically — you do not need to attach or describe them yourself.

Confirm Before Control

This tool seizes the mouse and keyboard of the host machine. It MUST NOT take over the screen without the user's explicit permission.

  1. First call — confirmed=false. Always make the first call with confirmed=false. The tool will return a takeover-consent question (it does not touch the mouse/keyboard yet). Surface that question to the user.
  2. Wait for an explicit yes. Only proceed once the user clearly agrees — a "yes", "go ahead", "do it", "确认", "可以" in the conversation counts. Silence, ambiguity, or "maybe" does not count.
  3. Second call — confirmed=true. Only then call again with confirmed=true. This is the call that actually takes over the host.

Never set confirmed=true on the first call, and never assume consent.

Show full SKILL.md (309 more words)Show less

Honesty Protocol

Report only the verdict the tool returns. Do not embellish.

  • The tool returns an outcome such as excellent, pass, partial, gain_only, or failed, plus a measured score (e.g. noise-floor reduction).
  • If the verdict is excellent or pass, you may say the recording was cleaned / the noise was reduced.
  • If the verdict is partial, say the cleanup is incomplete / needs review — do not claim it is clean.
  • If the verdict is gain_only, the cleanup was not proven: the clip may only have been made louder, not actually denoised. Say so plainly — do not say "cleaned", "denoised", or "noise removed".
  • If the verdict is failed, say it failed and offer to retry or try a different clip.

Never claim "cleaned", "denoised", or "noise removed" beyond what the measured verdict supports. The user trusts the number, not your optimism.

Usage Protocol

When the user asks to clean a recording:

  1. Confirm the source. Make sure you have the path to the audio the user wants processed.
  2. First call, confirmed=false. Relay the takeover-consent question.
  3. Get explicit consent. Wait for the user's "go ahead".
  4. Second call, confirmed=true. Run the real cleanup.
  5. Report the verdict honestly. State the outcome exactly as measured. The before/after audio renders inline on its own.

Example

User: "这段录音底噪好大，帮我降噪一下"

  • First, call clean_audio_in_audition(audio_path="/path/to/voice.wav", confirmed=false).
  • The tool replies with a consent question; relay it: "This will take over the mouse and keyboard on the Mac to run Audition. Shall I go ahead?"
  • User: "好的，开始吧"
  • Then call clean_audio_in_audition(audio_path="/path/to/voice.wav", confirmed=true).
  • Tool returns verdict gain_only. You report honestly: "处理跑完了，但校验显示 只是音量变大、降噪效果未被证实，因此我不能说底噪已去除。要不要换个参数或换一段再试？" The before/after audio appears inline.

Do Not

  • Do not drive gui_action directly to attempt the cleanup — use this dedicated tool, which knows the Audition workflow and measures the result.
  • Do not call with confirmed=true before the user agrees.
  • Do not overstate the result. A gain_only verdict is not a cleanup.

© THU-SAGE, 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 syll/skills/audition-clean-voice of THU-SAGE/syll.

Open the folder on GitHubat commit 3741347

Compare with similar skills

Audition Voice Cleanup 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.

Audition Voice Cleanup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audition Voice Cleanup this skillTHU-SAGE/syll303—~1.2kAutomated safety check: PassMIT
Open Computer UseiFurySt/open-codex-computer-use2.4k—~1.5kAutomated safety check: PassMIT
Mac Computer UseTo3akaRin/mac-computer-use1.1k—~495Automated safety check: PassMIT
TuriX macOS Desktop AgentTurixAI/TuriX-CUA3.2k—~3.2kAutomated safety check: WarnMIT
Parallels macOS VM Labsteipete/agent-scripts7.3k—~1.8kAutomated safety check: PassMIT
Waku Computer Useegoist/waku1.6k—~3.6kAutomated safety check: PassGPL-3.0

Similar skills

  • Open Computer Use

    iFurySt/open-codex-computer-use

    Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows.

    2.4k GitHub stars~1.5k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Mac Computer Use

    To3akaRin/mac-computer-use

    操作 macOS 桌面应用，探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作，以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收；普通网页任务优先使用已有浏览器工具。

    1.1k GitHub stars~495 tokensUpdated 17 days ago
    Productivity & AutomationAuto-check passed

  • TuriX macOS Desktop Agent

    TurixAI/TuriX-CUA

    Controls the macOS desktop visually through the TuriX computer-use agent, for opening apps, clicking buttons and navigating interfaces that have no CLI or API.

    3.2k GitHub stars~3.2k tokensUpdated 27 days ago
    Productivity & AutomationAuto-check: warnings

  • Parallels macOS VM Lab

    steipete/agent-scripts

    Uses a clean Parallels macOS VM to test GUI automation, TCC permission prompts and screenshot tools like Peekaboo, verifying results from outside the guest.

    7.3k GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed

  • Waku Computer Use

    egoist/waku

    Control local macOS, Windows, and Linux apps through Waku Computer Use.

    1.6k GitHub stars~3.6k tokensUpdated 9 days ago
    Productivity & AutomationAuto-check passed

  • Native Mac App Controller

    alchaincyf/huashu-mac-use

    Controls macOS native apps that have no API, taking window-level screenshots as reproducible evidence without stealing focus and probing whether an app can be automated.

    300 GitHub stars~1.5k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

More from THU-SAGE/syll

All 8 skills in this repo

  • File Retrieval

    THU-SAGE/syll

    Finds a file on the local machine, shows previews of the candidates, and sends the one you pick back through the current chat channel after confirmation.

    303 GitHub stars~1.3k tokensUpdated 4 mo ago
    Auto-check passed

  • Photoshop Background Cutout

    THU-SAGE/syll

    Removes an image background and exports a transparent PNG by driving the real Adobe Photoshop app on a macOS host, after asking your permission to take over the screen.

    303 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed

  • Desktop GUI Agent

    THU-SAGE/syll

    Controls desktop applications through screenshots: a vision model reads the screen and returns click, type and scroll actions that pyautogui then performs.

    303 GitHub stars~662 tokensUpdated 4 mo ago
    Auto-check passed

  • Morning News Podcast

    THU-SAGE/syll

    Builds a short spoken morning news briefing from a few web searches and turns it into one audio clip, on request or on a schedule.

    303 GitHub stars~533 tokensUpdated 4 mo ago
    Auto-check passed

  • HoYoLAB Check-in Simulator

    THU-SAGE/syll

    Produces a clearly labeled, research-based stand-in for a Genshin Impact or Honkai: Star Rail daily check-in when no real sign-in can be run.

    303 GitHub stars~551 tokensUpdated 4 mo ago
    Auto-check passed

  • Local Mail Sim

    THU-SAGE/syll

    Simulate an overnight local mail summary when there is no real local mailbox integration or recorded GUI workflow available.

    303 GitHub stars~355 tokensUpdated 4 mo ago
    Auto-check passed

Works with

Categories

Questions about Audition Voice Cleanup

What does Audition Voice Cleanup do?

Cleans a voice recording by driving Adobe Audition on a macOS host to reduce hiss, hum, background noise and sibilance, after asking for your consent. The skill calls a `clean_audio_in_audition` tool with the path to an audio file. The tool is not an in-process filter: it launches or focuses the real Adobe Audition app on a macOS host, opens the clip, applies noise reduction and de-essing, exports the result, measures the noise-floor reduction and whether the voice was preserved rather than just made louder, and returns a verdict.

When should I use Audition Voice Cleanup?

Audition Voice Cleanup fits situations like: removing hiss or hum from a voice recording; reducing background noise in a narration or interview take; softening harsh sibilance with de-essing.

How do I install Audition Voice Cleanup in Claude Code?

Run `npx skills add THU-SAGE/syll --skill audition-clean-voice -a claude-code`. Or copy the skill folder (syll/skills/audition-clean-voice in THU-SAGE/syll) into .claude/skills/audition-clean-voice in your project. Claude Code loads it when a task matches its description.

How do I install Audition Voice Cleanup in Codex?

Run `npx skills add THU-SAGE/syll --skill audition-clean-voice -a codex`. Or copy the skill folder (syll/skills/audition-clean-voice in THU-SAGE/syll) into .agents/skills/audition-clean-voice in your project. Codex loads it when a task matches its description.

Can I use Audition Voice Cleanup 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 THU-SAGE/syll --skill audition-clean-voice -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audition-clean-voice, .gemini/skills/audition-clean-voice, .github/skills/audition-clean-voice and .opencode/skills/audition-clean-voice in your project.

What does Audition Voice Cleanup need to run?

SKILL.md names no scripts, command-line tools or credentials: Audition Voice Cleanup is instructions for the agent only. Our summary lists: Adobe Audition installed on a macOS host; Your permission for the agent to take over the host's mouse and keyboard.

Does Audition Voice Cleanup 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 Audition Voice Cleanup 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 Audition Voice Cleanup use?

Audition Voice Cleanup 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 Audition Voice Cleanup use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Audition Voice Cleanup?

Skills that share tags, products or a category with Audition Voice Cleanup: Open Computer Use (iFurySt/open-codex-computer-use, 2.4k stars), Mac Computer Use (To3akaRin/mac-computer-use, 1.1k stars), TuriX macOS Desktop Agent (TurixAI/TuriX-CUA, 3.2k stars) and Parallels macOS VM Lab (steipete/agent-scripts, 7.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audition Voice Cleanup?

THU-SAGE (a GitHub organization) maintains it in THU-SAGE/syll, which has 303 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on June 9, 2026.

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