Menu
Comprehensive audio processing and manipulation system for AI agents with advanced editing and enhancement capabilities
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
A library of 150 brand and aesthetic design systems (Apple, Stripe, Linear, Vercel, Notion, GitHub, Figma, Spotify, Tesla, and more, plus styles like brutalism, glassmorphism, neumorphism, editorial, minimal). Use when the user wants a UI to look like a brand, match a brand's style or vibe, or adopt a named aesthetic. Read references/<brand>.md for that brand's colors, typography, spacing, radii, and component style before generating any UI.
Apply Anthropic's official brand colors and typography to artifacts for consistent visual identity and professional design standards. A reference for shaping your own.
Create beautiful visual art in PNG and PDF documents using design philosophy and aesthetic principles for posters, illustrations, and static pieces.
Frontend design and UI/UX development tools for shipping production-ready interfaces with strong typographic and layout discipline.
Apply professional font and color themes to artifacts including slides, docs, reports, and HTML landing pages. Ships 10 pre-set themes.
Orchestrates UI and page design. Use when the user asks to design a page, screen, UI, landing page, dashboard, login flow, pricing page, invoice, resume, FAQ, article, slide deck, social card, or any web layout; to make it look like a brand (Apple, Stripe, Linear, Vercel, Notion, ...); or to build a mockup, prototype, wireframe, or HTML preview. Picks a matching layout skill, optionally adopts a brand design system, then writes a single self-contained HTML file to <project>/.devspace/preview/ so DevSpace can preview it.
| name | audio-processor |
| description | Comprehensive audio processing and manipulation system for AI agents with advanced editing and enhancement capabilities |
This built-in skill provides comprehensive audio processing and manipulation capabilities for AI agents to edit, enhance, and transform audio content with professional-grade quality and precision.
tool: audio-processor
action: enhance_audio
audio_path: "/recordings/interview_raw.wav"
enhancements:
- type: "noise_reduction"
strength: 0.7
- type: "equalization"
preset: "voice_clarity"
- type: "compression"
ratio: 4.0
threshold: -20
- type: "normalization"
target_level: -1.0
output_format: "wav"
output_path: "/recordings/interview_enhanced.wav"
tool: audio-processor
action: convert_format
audio_path: "/music/song.flac"
target_format: "mp3"
quality_settings:
bitrate: 320
sample_rate: 44100
channels: 2
output_path: "/music/song.mp3"
preserve_metadata: true
tool: audio-processor
action: isolate_speech
audio_path: "/recordings/meeting_with_music.mp3"
isolation_strength: 0.9
background_music_suppression: 0.8
output_format: "wav"
speech_output: "/recordings/meeting_speech_only.wav"
background_output: "/recordings/meeting_background_only.wav"
tool: audio-processor
action: edit_audio
audio_path: "/podcasts/episode_full.mp3"
edits:
- type: "trim"
start_time: "00:05:30"
end_time: "00:45:20"
- type: "remove_section"
start_time: "00:23:15"
end_time: "00:23:45"
- type: "fade_in"
duration: "2s"
- type: "fade_out"
duration: "3s"
output_path: "/podcasts/episode_edited.mp3"
The audio-processor skill can be configured with the following parameters:
default_output_format: Default output format (wav, mp3, flac, ogg)max_file_size: Maximum file size for processing (default: 100MB)temp_directory: Temporary directory for audio processing (default: system temp)quality_preset: Default quality preset (low, medium, high, premium)privacy_mode: Privacy mode for handling sensitive audio (strict, moderate, relaxed)This skill is essential for any agent that needs to process audio recordings, enhance speech quality, convert audio formats, or perform professional-grade audio editing and manipulation.