audio-processing — Claude Code skill: what it does, how to install
audio-processing is a Claude Code skill with guidelines for recording and editing audio for Xiaohongshu posts and podcasts, matched to platform requirements.
no license 176 installs ★ 564 updated 2026-01-23
npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a claude-codeWhat audio-processing does
This skill outlines production rules for voiceovers and podcasts targeted at Xiaohongshu. It guides microphone selection, room acoustic prep, and recording gain calibration. The recommended target gain sits between -12 dB and -6 dB, keeping peaks near -3 dB to avoid irreversible clipping.
A diagnosis chart helps fix typical sound flaws: room reverb, hardware hiss, low volume, and muffled frequencies. It also details mastering standards: AAC, MP3, or M4A formats at 44.1 kHz or 48 kHz sample rates. Skipping the platform target of -16 LUFS will trigger aggressive automated compression upon upload.
These guidelines cover recorded voice clips and audio posts. Live streaming setups require entirely different signal chains and are outside the scope of this skill.
What it helps with
- configure recording gain between -12 dB and -6 dB
- clean up room reverb and background hum from voice tracks
- normalize track loudness to the target -16 LUFS standard
- export final files to AAC or MP3 at 192 kbps bitrate
Example prompts for the agent
- Help me set up microphone levels for recording voiceovers for Xiaohongshu.
- How do I remove room reverb and normalize my track to -16 LUFS?
- Suggest export settings for an MP3 voiceover track before publishing.
How to install audio-processing
1Skills CLI (Vercel)
npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a claude-code2Manually: put the files in place
~/.claude/skills/audio-processing/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/audio-processing/
1Skills CLI (Vercel)
npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a codex2Manually: put the files in place
.agents/skills/audio-processing/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a cursor2Manually: put the files in place
.cursor/skills/audio-processing/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install vivy-yi/xiaohongshu-skills skills/01-内容创作/audio-processing2Manually: put the files in place
.github/skills/audio-processing/SKILL.md1Skills CLI (Vercel)
npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a gemini-cli2Platform CLI
gemini skills install https://github.com/vivy-yi/xiaohongshu-skills --path skills/01-内容创作/audio-processingManually: put the files in place
.devin/skills/audio-processing/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about audio-processing
How to install audio-processing in Claude Code?
Run npx skills add vivy-yi/xiaohongshu-skills --skill audio-processing -a claude-code.
What does audio-processing do?
It gives your coding agent reference rules for recording speech, reducing background noise, and mastering audio for Xiaohongshu.
What technical audio specifications does Xiaohongshu require?
The platform requires AAC, MP3, or M4A audio at 44.1 kHz or 48 kHz, 128 to 320 kbps bitrate (192 kbps recommended), and -16 LUFS loudness.