Media Skills

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro) with AI Gateway support.

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

Extract frames or short clips from videos using ffmpeg.

Search and play music tracks on YouTube Music through MCP integration. Use when user wants to search for songs, play music, or discover tracks on YouTube Music platform.

Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder. Use when creating custom AMIs for EC2 instances.

Build Azure managed images and Azure Compute Gallery images with Packer. Use when creating custom images for Azure VMs.

Push Packer build metadata to HCP Packer registry for tracking and managing image lifecycle. Use when integrating Packer builds with HCP Packer for version control and governance.

Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.

统一配图技能，支持文章配图、封面生成、小红书图片系列、单图修改/添加/删除、3变体风格预览。20种风格×多种布局。

生成自然真实的双人访谈播客，使用共享TTS模块支持3种引擎（Edge TTS / IndexTTS2 / MiniMax）和情感控制

Intelligently compress and rewrite documents into TTS-friendly scripts. Uses Claude AI to analyze content, compress to target duration, convert to spoken style with emotional language, and auto-segment. Perfect for video narration.

Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.

Generate and edit images using Google's Nano Banana 2 (Gemini 3.1 Flash Image Preview) API. This skill should be used when the user asks to create or modify images, especially when they need fast iteration, explicit aspect-ratio control, or resolution control from 512px to 4K.

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

Generate beautiful code snippet images using ray.so. This skill should be used when the user asks to create a code image, code screenshot, code snippet image, or wants to make their code look pretty for sharing. Saves images locally to the current working directory or a user-specified path.

Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.

| Diagnose and fix common Abridge clinical AI integration errors. Use when encountering EHR connectivity failures, note generation errors, audio streaming issues, or FHIR validation problems with Abridge. "fix abridge issue", "abridge troubleshoot".

| Optimize Abridge clinical AI integration performance for high-volume deployments. Use when reducing note generation latency, optimizing audio streaming throughput, improving FHIR push performance, or scaling for multi-site health systems. "abridge slow", "abridge scale".

| and expand image using the Firefly v3 API. Use when generating images from prompts, filling or expanding images with AI, or building creative automation pipelines. Trigger with phrases like "adobe firefly", "generate image adobe", "firefly text to image", "adobe AI image", "generative fill".

| to Firefly Services, consolidating Creative Cloud integrations, and strangler-fig migration from competitor document/image APIs to Adobe. Trigger with phrases like "migrate adobe", "adobe migration", "switch to adobe", "adobe replatform", "replace with adobe".

| Use when transcribing audio/video files, enabling speaker diarization, sentiment analysis, entity detection, PII redaction, or content moderation. Trigger with phrases like "assemblyai transcribe", "assemblyai transcription", "transcribe audio", "speaker diarization assemblyai".

| Execute AssemblyAI streaming transcription and LeMUR workflows. Use when implementing real-time speech-to-text, live captions, voice agents, or LLM-powered audio analysis with LeMUR. Trigger with phrases like "assemblyai streaming", "assemblyai real-time", "assemblyai live transcription", "assemblyai LeMUR", "assemblyai summarize audio".

| Implement AssemblyAI reference architecture with best-practice project layout. Use when designing new AssemblyAI transcription services, reviewing project structure, or building production-grade speech-to-text applications. Trigger with phrases like "assemblyai architecture", "assemblyai best practices", "assemblyai project structure", "how to organize assemblyai", "assemblyai design".

| benefits administration, and employee files/photos. Use when managing time off, checking PTO balances, handling benefits data, or working with employee documents in BambooHR. Trigger with phrases like "bamboohr time off", "bamboohr PTO", "bamboohr benefits", "bamboohr vacation", "bamboohr files", "bamboohr leave request".

| Create uncontested market space using value innovation instead of competing head-to-head. Use when the user mentions "blue ocean", "red ocean", "strategy canvas", "ERRC framework", "value innovation", or "non-customers". Covers the Four Actions Framework, buyer utility map, and value-cost trade-offs. For tech adoption strategy, see crossing-the-chasm. For product positioning, see obviously-awesome. Trigger with 'blue', 'ocean', 'strategy'.

| This skill enables Claude to process and analyze images using computer vision techniques. It's used to perform tasks such as object detection, image classification, and image segmentation. Use this skill when a user requests analysis of an image, asks for identification of objects within an image, or needs help with other computer vision related tasks. Trigger terms include "analyze image", "object detection", "image classification", "image segmentation", "computer vision", "process image", or when the user provides an image and asks for insights.

| This skill enables Claude to manage container registries, including ECR, GCR, and Harbor. It should be used when the user needs to create, configure, or manage container image registries. It helps generate production-ready configurations, implement best practices, and ensure a security-first approach. Use this skill when the user mentions terms like "container registry," "ECR," "GCR," "Harbor," "image repository," or requests assistance with managing container images. It's also helpful for generating configuration code for DevOps pipelines related to container registries.

| Implement production pre-recorded speech-to-text with Deepgram. Use when building audio transcription, batch processing, or implementing diarization and intelligence features. "batch transcription", "deepgram nova", "diarize audio".

| Implement real-time streaming transcription with Deepgram WebSocket. Use when building live transcription, voice interfaces, real-time captioning, or voice AI applications. "websocket transcription", "voice streaming", "deepgram live".

| Implement audio data handling best practices for Deepgram integrations. Use when managing audio file storage, implementing data retention, or ensuring GDPR/HIPAA compliance for transcription data. "deepgram GDPR", "deepgram HIPAA", "deepgram privacy", "PII redaction".

| Create a minimal working Deepgram transcription example. Use when starting a new Deepgram integration, testing your setup, or learning basic Deepgram API patterns. "simple transcription", "transcribe audio".

| Optimize Deepgram API performance for faster transcription and lower latency. Use when improving transcription speed, reducing latency, or optimizing audio processing pipelines. "deepgram latency", "deepgram faster", "deepgram throughput".

| Diagnose and fix ElevenLabs API errors by HTTP status code. Use when encountering ElevenLabs errors, debugging failed TTS/STS requests, or troubleshooting voice cloning and streaming issues. "debug elevenlabs", "elevenlabs 401", "elevenlabs 429", "elevenlabs 400".

| Implement ElevenLabs text-to-speech and voice cloning workflows. Use when building TTS features, cloning voices from audio samples, "clone a voice", "generate speech", "elevenlabs voice".

| Implement ElevenLabs speech-to-speech, sound effects, audio isolation, and speech-to-text. Use when converting voice to another voice, generating sound effects from text, removing background noise, or transcribing audio. "audio isolation", "remove background noise", "elevenlabs transcribe".

| Optimize ElevenLabs costs through model selection, character-efficient patterns, caching, and usage monitoring with budget alerts. Use when analyzing ElevenLabs billing, reducing character usage, or implementing quota monitoring for TTS workloads. "elevenlabs pricing", "elevenlabs expensive", "elevenlabs budget", "elevenlabs characters", "elevenlabs quota".

| Generate your first ElevenLabs text-to-speech audio file. Use when starting a new ElevenLabs integration, testing your setup, or learning basic TTS API patterns. "elevenlabs quick start", "first elevenlabs TTS", "text to speech demo".

| Configure local ElevenLabs development with mocking, hot reload, and audio testing. Use when setting up a dev environment for TTS/voice projects, configuring test workflows, or building a fast iteration cycle with ElevenLabs audio. "elevenlabs dev environment", "develop with elevenlabs", "test elevenlabs locally".

| Optimize ElevenLabs TTS latency with model selection, streaming, caching, and audio format tuning. Use when experiencing slow TTS responses, implementing real-time voice features, or optimizing audio generation throughput. "elevenlabs slow", "fast TTS", "reduce elevenlabs latency", "TTS streaming".

| Execute ElevenLabs production deployment checklist with health checks and rollback. Use when deploying TTS/voice integrations to production, preparing for launch, or implementing go-live procedures for ElevenLabs-powered apps. "elevenlabs go-live", "elevenlabs launch checklist", "production TTS".

| Implement ElevenLabs rate limiting, concurrency queuing, and backoff patterns. Use when handling 429 errors, implementing retry logic, or managing concurrent TTS request throughput. "elevenlabs 429", "elevenlabs retry", "elevenlabs backoff", "elevenlabs concurrent requests".

| Implement ElevenLabs reference architecture for production TTS/voice applications. Use when designing new ElevenLabs integrations, reviewing project structure, or building a scalable audio generation service. "how to organize elevenlabs", "TTS service architecture", "elevenlabs design patterns", "voice API architecture".

| Apply ElevenLabs security best practices for API keys, webhook HMAC validation, and voice data protection. Use when securing API keys, validating webhook signatures, or auditing ElevenLabs security configuration. "secure elevenlabs", "elevenlabs API key security", "elevenlabs webhook signature", "elevenlabs HMAC".

| Image Optimization Helper - Auto-activating skill for Frontend Development. Part of the Frontend Development skill category.

| Build product positioning by mapping competitive alternatives, unique attributes, and best-fit customers to the right market category. Use when the user mentions "positioning", "competitive alternatives", "how to position", "market category", or "why customers don''t get it". Covers positioning canvas and team workshops. For customer jobs analysis, see jobs-to-be-done. For go-to-market, see crossing-the-chasm. Trigger with 'obviously', 'awesome'.

| Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.

| Automatic activation for ALL Google Vertex AI multimodal operations - video processing, audio generation, image creation, and marketing campaigns.

| Refine a YouTube video idea into a structured production brief with angle, key points, value proposition, CTA asset, and audience segment. Use this skill whenever the user says "create a brief", "brief this idea", "develop this idea", "write a video brief", "production brief", or has selected a video idea from ideation and wants to define the angle and structure before packaging and outlining. Use when working with yt brief. Trigger with 'yt', 'brief'.