音訊處理

Master style guide development with writing standards, terminology, voice and tone, and consistency guidelines.

Restore previous session state from Serena MCP checkpoints. Retrieves checkpoint by ID or auto-selects most recent, deserializes context, restores command/skill/phase/wave state. Use when: resuming after context loss, continuing previous session, recovering from interruption.

Game audio systems, music, spatial audio, sound effects, and voice implementation.Build immersive audio experiences with professional middleware integration.

Split audio files by detecting silence gaps. Auto-segment podcasts into chapters, remove long silences, and export individual clips.

Extract Voice of Customer quotes from forums, reviews, and social media. Use when gathering customer language for copywriting, understanding pain points, or building messaging frameworks.

Captures Dmitrii's distinctive writing voice and preferences for all written outputs. Use when creating case studies, blog posts, articles, documents, emails, proposals, PRDs, specifications, messages, or any written content on Dmitrii's behalf. MUST be invoked for any mid-to-long form content creation.

Analyze writing samples to create a comprehensive voice DNA profile. Use when the user wants to capture their unique writing voice, needs to create a voice profile for AI content, or is setting up a new writing system.

Review specifications for soundness, completeness, and implementability - validates structure, identifies ambiguities, checks for gaps before implementation

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

Run TTS canary tests, measure audio quality/latency, and rollback on threshold breaches. Use before rolling out new voices or pipelines.

Orchestrate multi-voice TTS production: assign speakers, chunk dialogue, dispatch to voices, sync timing, and mix into a final track. Use after dialogue-dramatizer produces script turns.

This skill should be used when analyzing an existing project to automatically generatepersonalized skills, agents, commands, and documentation based on detected patterns and needs.AUTO-ACTIVATES for: project setup, analyze project, setup claude code, personalize claude,auto-generate tools, detect project needs, bootstrap project.PROVIDES: Deep project analysis (code patterns, architecture, domain detection),automatic skill generation (personalized for THIS project's patterns),automatic agent generation (for recurring tasks), automatic command generation (for workflows),custom CLAUDE.md (with project-specific context and best practices).ANALYZES: Code patterns (repetitive endpoints, components, queries), project structure(architecture, layers, modules), dependencies (frameworks, libraries), recurring tasks(what developers do repeatedly), domain detection (invoicing, e-commerce, analytics, etc.).GENERATES: Personalized skills (e.g., "invoice-endpoint-builder" for invoicing project),task-specific

Brand strategy, identity, positioning, and voice development. Use when developing brand guidelines, creating positioning statements, defining brand voice, or building brand architecture.

Cut, trim, and edit audio segments with fade effects, speed control, concatenation, and basic audio manipulations.

Expert in spatial audio, procedural sound design, game audio middleware, and app UX sound design. Specializes in HRTF/Ambisonics, Wwise/FMOD integration, UI sound design, and adaptive music systems. Activate on 'spatial audio', 'HRTF', 'binaural', 'Wwise', 'FMOD', 'procedural sound', 'footstep system', 'adaptive music', 'UI sounds', 'notification audio', 'sonic branding'. NOT for music composition/production (use DAW), audio post-production for film (linear media), voice cloning/TTS (use voice-audio-engineer), podcast editing (use standard audio editors), or hardware design.

Analyze transcript files using OpenAI API (gpt-5-mini) to extract insights, summaries, key topics, quotes, and action items. This skill should be used when users have transcript files (from WhisperKit, YouTube, podcasts, meetings, etc.) and want AI-powered analysis, summaries, or custom insights extracted from the content. Supports both default comprehensive analysis and custom prompts for specific information extraction.

Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.

This skill should be used when the user asks to "configure esp32-s3-box-3", "set up box-3", "create box-3 voice assistant", "display lambda on box-3", "configure ili9xxx display", "set up gt911 touch", "configure i2s audio", "es7210 microphone", "es8311 speaker", "box-3 audio pipeline", or mentions error messages like "I2S DMA buffer error", "Touch not responding", "Display flicker", "Audio popping", "PSRAM not detected". Provides complete ESP32-S3-BOX-3 hardware templates, display lambda cookbook, touch patterns, and voice assistant configurations.

Validate inference chains step-by-step by examining whether each logical connection from premise to conclusion is sound, making implicit reasoning steps explicit and checking for gaps or leaps. Use when: (1) asked to validate reasoning steps, trace the logic, or verify if conclusions follow from premises, (2) arguments skip intermediate inferential steps or use 'therefore' without showing the reasoning path, (3) evaluating multi-step proofs, mathematical reasoning, or decision frameworks where each step builds on previous ones, (4) reasoning depends on unstated assumptions being treated as established facts.

Produce grounded audio briefs by chaining source-scoped input, citation verification, dialogue dramatization, and multi-speaker TTS orchestration. Use for “Audio Overview” style outputs.