Sizing utilities Tailwind CSS v4.1. Width (w-*, w-screen, w-full, w-auto), Height (h-*, h-screen, h-full, h-dvh NEW), Min/Max (min-w-*, max-w-*, min-h-*, max-h-*), Aspect ratio (aspect-video, aspect-square).

Expert prompt engineering for Google Veo 3.2 (Artemis engine). Use when the user wants to generate a video with Veo 3.2, needs help crafting cinematic prompts, or mentions Veo, Google video generation, or Artemis engine.

Convert a video to multiple GIF variants with different quality/size tradeoffs. Generates a comparison set so the user can visually pick the best result.

Render markdown or Mermaid content as formatted HTML in the browser. Triggers when the user asks to view, render, or preview a document as HTML; when the user asks to visualize, diagram, chart, or draw architecture, flows, sequence/class/state/ER diagrams; when resolving plan files from ~/.claude/plans/; or proactively when about to output a table with 4+ rows or 3+ columns, a structured comparison, an audit, a feature matrix, or any formatted content exceeding ~50 lines in the terminal.

Web Audio API for JARVIS audio feedback and voice processing

Use when YouTube data is needed without Google API quotas or OAuth setup: transcripts, video metadata, channel info, search results, playlists. Triggers on pasted YouTube links, creator names, @handles, topic research, video summaries, channel browsing, or any request where YouTube content would help — even if not mentioned explicitly. Not for uploads, account management, or written-source-only research.

Use when structured YouTube data is needed: pasted video/channel/playlist links, transcripts for analysis, video metadata, channel upload history, search results, or playlist contents — without Google API quotas or OAuth. Triggers on YouTube URLs, creator names, topic research, or any request needing YouTube content, even if not mentioned explicitly. Not for uploads, account management, or written-source-only research.

Generate cinematic videos with native synchronized audio using ByteDance Seedance 2.0 (Fast) via EachLabs. Supports text-to-video (bytedance-seedance-2-0-text-to-video-fast) and image-to-video (bytedance-seedance-2-0-image-to-video-fast). Use when the user specifically asks for Seedance 2.0, wants native audio with the video, realistic physics, director-level camera control, or 4–15 second clips up to 720p.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for the user's actual intent — single still vs video, full character vs face only, dialog scene vs silent motion. Triggers on "face swap", "swap face", "deepfake", "face replacement", "character swap", "head swap", "put X's face on Y", "make this video star X", "replace the actor in this video", "swap the character in the photo", "deepfake video", "ReActor alternative", or any explicit ask to substitute one identity for another.

Diagnose and fix Docker image pull failures on macOS with OrbStack, especially Docker Hub EOF/TLS/manifest errors caused by system proxies, Clash/CyberClash/Mihomo/Surge-style TUN mode, fake-ip DNS such as 198.18.0.x, or unstable registry access. Use when `docker pull` or `docker manifest inspect` fails with EOF, SSL_ERROR_SYSCALL, failed to fetch anonymous token, failed to resolve reference, failed to copy, or registry-1.docker.io/auth.docker.io connectivity confusion.

Use the genmedia CLI to search, inspect, run, and manage 1200+ fal.ai model endpoints. Trigger when the user mentions "genmedia", "fal CLI", or asks to "search models", "run a model", "fetch schema", "check pricing", "upload to fal", "queue async job", "track request", or any direct interaction with the fal.ai endpoint catalog. This is the foundational skill. Every other fal.ai-related skill in this repo executes its work through genmedia commands. Use `--json` whenever the output will be parsed by an agent.

A symbolic slide image for a document passage, consistent with the artifact's companion images. Use when the user wants a diagram or visual symbol for a section. Composes /forge + Codex.

Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.

Convert PDF to clean Markdown with image content described as text. Use when user wants to convert a PDF to markdown, extract content from PDF, or prepare PDF content for AI tools.

Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captures screens and sequences, and produces a deployable site that actually teaches people what the product does. Especially useful for complex or agentic apps that are hard to explain. Triggers: 'showcase site', 'product page', 'show off the app', 'marketing site', 'demo site', 'product showcase', 'explain the app', 'how do I market this'.

Generates 15-second vertical promo videos for social media from mastered audio. Use after mastering is complete and before release, when the user wants social media content.

Capture professional-quality remote interviews using double-ender technique and dedicated recording platforms for podcasts, media, and content production. Use when: Setting up remote podcast interviews with guests; Recording media interviews across distances; Creating customer interview content; Producing expert interviews for thought leadership; Conducting research interviews with high audio quality

Generate videos using OpenAI's Sora API. Use when the user asks to generate, create, or make videos from text prompts or reference images. Supports image-to-video generation with automatic resizing.

Scaffold a complete Vapi voice-agent project from a ROUGH_DRAFT.md spec. Generates package.json, .env.example, .gitignore, and the full TypeScript framework — scenario registry, per-language voice/transcriber stack, prompt composer, assistant builder, and an idempotent bootstrap script — plus one rough first-draft body.md per scenario. Drop this skill in any project's .cursor/skills/ folder (or ~/.cursor/skills/ for global use), write a ROUGH_DRAFT.md at the project root, name the skill, and `bun run bootstrap` puts the entire fleet live in dashboard.vapi.ai. Use when the user asks to scaffold or bootstrap Vapi voice agents from a rough draft, build a Vapi assistant fleet, or invokes this skill by name. Targets Bun + TypeScript + @vapi-ai/server-sdk.

MUX Player React components — responsive video player, chapter navigation, captions toggle, thumbnail hover previews, and video cards. Use this skill when the user says "add video player", "setup mux player", "video components", "add player", or "video-player".

Write long-form essays and newsletters in Dan Koe's voice — philosophical depth made accessible, staccato rhythm with expansive passages, confident authority, zero hedging. Structured as a teaching conversation with bad-AI/correction/good-version rounds reverse-engineered from his actual articles. Use for newsletters, X articles, blog essays, or any long-form content that needs to blend philosophy with practical frameworks.

Live closed captions for video rooms — floating caption overlay with speaker labels, configurable font size, position, and opacity. Powered by Deepgram transcription via LiveKit data channels. Use this skill when the user says "add captions", "setup closed captions", "add subtitles", "live captions", or "setup ai-captions".

Knowledge base defining 24 common AI writing patterns (inflated symbolism, promotional language, etc.) and guidelines on how to rewrite them to sound naturally human. TRIGGER WHEN: editing or reviewing text to remove AI traces, or when asked to humanize text. DO NOT TRIGGER WHEN: the task involves refactoring source code or when the task does not involve prose/text refinement.

Use this agent to scan Swift code for camera, video, and audio capture issues including deprecated APIs, missing interruption handlers, threading violations, and permission anti-patterns.

Transform brain dumps into polished blog posts in Nick Nisi's voice. Use when the user wants to write a blog post with scattered ideas, talking points, and conclusions that need organization into a cohesive narrative with Nick's conversational, authentic, and thoughtful tone.

Render and display Mermaid diagrams inline in iTerm2 or Ghostty. Use when creating, editing, or iterating on mermaid diagrams. Triggers on mermaid diagram work — flowcharts, sequence, state, class, ER, and XY charts.

Auto-invoke gencast to generate podcasts from documents when user mentions podcast, audio, or dialogue generation

Use this skill when the user wants to remove AI-generated writing patterns from text, make copy sound more natural and human-written, or edit content that reads like it was written by ChatGPT. Also use when the user says 'this sounds like AI,' 'too robotic,' 'AI slop,' 'make this sound human,' 'sounds like ChatGPT,' or 'remove AI patterns.' Detects and fixes 24 patterns including significance inflation, promotional language, superficial -ing analyses, vague attributions, AI vocabulary words, and more.

Transforms research and knowledge base material into information-dense infographic copy—clear, scannable, authoritative, and reference-worthy. Use when converting clinical algorithms, decision trees, comparison data (drug vs drug, treatment options), trial results, myth vs truth content, patient preparation guides, checklists, or sequential process workflows into structured copy ready for single-image infographic formats. Supports multiple infographic types including hero stats, dense multi-section layouts, side-by-side comparisons, myth-busters, step-by-step processes, and patient checklists. Outputs structured copy with compressed noun-heavy phrasing, specific numbers, trial citations, and JSON-formatted handoff data for downstream infographic generation.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Docker infrastructure manager for Odoo — production deployment, nginx proxy, CI/CD pipelines, performance tuning, multi-version image management, container debugging, and centralized workspace orchestration for Odoo 14-19 Enterprise. v2.0 consolidates nginx, debug, and perf into natural language triggers alongside the /odoo-docker sub-command interface. <example> Context: User wants to deploy Odoo to production with Docker user: "Deploy my Odoo 17 project to production using Docker" assistant: "I will use the odoo-docker skill to generate a production docker-compose.yml with Odoo, PostgreSQL, and nginx containers, with proper volume mounts and restart policies." <commentary>Core trigger - production Docker deployment.</commentary> </example> <example> Context: User wants nginx reverse proxy configuration user: "Set up nginx as a reverse proxy in front of my Odoo Docker container" assistant: "I will use the odoo-docker skill to generate an nginx.conf with SSL termination, WebSocket longpolling proxy, and proper cache headers for Odoo static assets." <commentary>Infrastructure trigger - nginx configuration for Odoo.</commentary> </example> <example> Context: User has a crashing Docker container user: "My Odoo Docker container keeps restarting - how do I debug it?" assistant: "I will use the odoo-docker skill to check container logs, verify environment variables, inspect the Odoo config, and identify the startup failure cause." <commentary>Debugging trigger - container crash diagnosis.</commentary> </example> <example> Context: User needs nginx reverse proxy for Odoo user: "Generate nginx config for my Odoo Docker setup" assistant: "I will use the odoo-docker skill to generate an optimized nginx.conf with gzip, WebSocket proxy, caching, and rate limiting." <commentary>Nginx trigger - reverse proxy configuration.</commentary> </example> <example> Context: User's container keeps crashing user: "My Odoo container keeps restarting, help me debug it" assistant: "I will use the odoo-docker skill to check container status, logs, health, network, and volumes systematically." <commentary>Debug trigger - container troubleshooting.</commentary> </example> <example> Context: User wants performance optimization user: "Analyze and tune my Odoo Docker performance" assistant: "I will use the odoo-docker skill to analyze Docker config, PostgreSQL tuning, resource limits, and generate recommendations." <commentary>Performance trigger - Docker tuning analysis.</commentary> </example> <example> Context: User wants to build Docker images user: "Build Docker image for Odoo 17 with my custom modules" assistant: "I will use the odoo-docker skill to create a Dockerfile and build the image with proper layer caching." <commentary>Build trigger - Docker image creation.</commentary> </example>

Use when modernizing a Perl project's GitHub Actions CI — applies seven idempotent transforms (fail-fast flag, Perl 5.42 matrix, perl-tester image bump, default-branch push, concurrency cancel, setup-cpm + cpm install, drop pre-5.24 macOS/Windows cells) to Dist::Zilla-style workflows.

Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.

Use this skill to generate walkthrough video scripts for app features. Triggers: "walkthrough script", "feature walkthrough", "app walkthrough script", "demo script", "video script for app", "feature tour script", "product walkthrough", "screen-by-screen script", "app feature scripts", "walkthrough narration", "tutorial script", "onboarding script", "feature highlight script" Outputs: Timed walkthrough scripts with narration, screen directions, and transitions for each app feature.

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step audio-inpaint (regenerate a time range inside an existing track), ACE Step audio-outpaint (extend an existing track before or after). Triggers on "ace step", "ace-step", "acestep", "ACE music", "open music model", "cheap AI music", "inpaint audio", "audio inpaint", "extend music", "audio outpaint", "lengthen track", "music with tags", or any explicit ask to generate or edit music with ACE Step.

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step audio-inpaint (regenerate a time range inside an existing track), ACE Step audio-outpaint (extend an existing track before or after). Triggers on "ace step", "ace-step", "acestep", "ACE music", "open music model", "cheap AI music", "inpaint audio", "audio inpaint", "extend music", "audio outpaint", "lengthen track", "music with tags", or any explicit ask to generate or edit music with ACE Step.

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step audio-inpaint (regenerate a time range inside an existing track), ACE Step audio-outpaint (extend an existing track before or after). Triggers on "ace step", "ace-step", "acestep", "ACE music", "open music model", "cheap AI music", "inpaint audio", "audio inpaint", "extend music", "audio outpaint", "lengthen track", "music with tags", or any explicit ask to generate or edit music with ACE Step.

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced character, dialog scene — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "talking head", "lip sync", "avatar video", "make X speak", "audio to video", "audio driven avatar", "virtual presenter", "AI spokesperson", "dubbed video", "UGC avatar", "HeyGen alternative", "Synthesia alternative", "digital human", "make this portrait talk", "video from voiceover", or any explicit ask to put words in a face.

Créez des storyboards visuellement cohérents en utilisant la technique des 2x2 Grid Shots de PJ Ace, garantissant éclairage, personnages et décors uniformes entre les plans. Use when: **Après avoir finalisé un script vidéo** - Transformer le concept en visuels; **Besoin de cohérence visuelle** - Personnages et éclairage constants entre les plans; **Préparer des assets pour animation** - Frames prêtes pour Veo, Runway, Kling; **Présenter un storyboard client** - Visualisation avant production;...

Générez des prompts optimisés pour chaque modèle de génération vidéo IA (Veo 3, Runway Gen-3, Kling 2.6, Pika), en exploitant leurs forces spécifiques. Use when: **Animer des frames de storyboard** - Transformer des images fixes en vidéo; **Choisir le bon modèle** - Sélectionner Veo, Runway, Kling ou Pika selon le besoin; **Optimiser la qualité de génération** - Prompts structurés pour meilleurs résultats; **Créer des transitions fluides** - Scene extension, first/last frame; **Utiliser le mo...

Guide to audio generation and understanding in MassGen. Covers text-to-speech, music, sound effects, and audio understanding across ElevenLabs and OpenAI backends.

Use the BlitzReels CLI to let AI coding agents complete onboarding, inspect, edit, verify, and export BlitzReels video projects from a shell. Use this whenever the user mentions the BlitzReels CLI, a local blitzreels command, agent-driven onboarding or video editing, local BlitzReels project edits, dashboard project URLs, captions, text overlays, media placement, silence/mistake edits, snapshots, exports, or asks an agent to control BlitzReels without hand-writing REST calls.

Use when captions, subtitles, or the spoken text of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to read, quote, or translate a video, accessibility needs, deaf/HoH use cases, content review, or language learning. Fetches timestamped caption data from any YouTube video. Not for uploading subtitles or account management.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Zoom Contact Center SDK for iOS. Use for native iOS chat/video/ZVA/scheduled callback integrations, app lifecycle bridging, rejoin flow, and callback handling.

Remove AI-generated jargon and restore human voice to text. Built from analyzing 1,000+ AI vs human content pieces.

# E2E Video Room Tests

Strip sensitive EXIF metadata from images before publishing to the web. Activates when working with images for blog posts, websites, or public content, or when EXIF, metadata, GPS data, or image privacy is mentioned.

This skill should be used when the user asks to "convert video", "trim video", "cut video", "extract audio", "compress video", "resize video", "create gif", "merge videos", "combine videos", "add audio to video", or needs help with ffmpeg commands for video and audio processing.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Canvas image editor with Konva.js — crop, resize, rotate, filters, brush masking, and layer compositing. Runs entirely client-side. Use this skill when the user says "add image editor", "setup canvas editor", "add konva", "image editing", or "photo editor".

Guide to image generation and editing in MassGen. Use when creating images, editing existing images, iterating on image designs, or choosing between image backends (OpenAI, Google Gemini/Imagen, Grok, OpenRouter).

Polishes raw Suno audio by processing per-stem WAVs (vocals, backing_vocals, drums, bass, guitar, keyboard, strings, brass, woodwinds, percussion, synth, other) with targeted cleanup, EQ, and compression, then remixing into a polished stereo WAV ready for mastering. Use after audio import and before mastering.

Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Compute a composite 0-100 efficiency score using JS/CSS coverage, render-blocking resources, transfer size, and navigation timing via CDP.

Analyze a song, track, or audio file with Recoup's audio language model (Music Flamingo). Use when asked to "analyze this song", "what does this track sound like", "run Music Flamingo", "use the audio model", "get a full report on this audio", "what key/BPM/mood/genre is this", "transcribe the lyrics", or any request to understand a piece of audio from its sound. This is the default entry point for audio analysis — it resolves the audio URL, picks the right preset, calls the endpoint, and routes to focused workflows (metadata, lyrics, playlist pitch, sync brief, mix feedback) when the ask is specific.

Use this skill to analyze product reviews, find common issues, and prioritize improvements. Triggers: "analyze reviews", "review analysis", "customer feedback", "what are people saying", "product reviews", "review sentiment", "find complaints", "customer complaints", "improvement recommendations", "voice of customer", "VOC analysis", "feedback analysis" Outputs: Prioritized issues, sentiment analysis, improvement recommendations.

Use when subtitles or the spoken text of a YouTube video is needed: pasted video links or IDs, requests to translate a video, read along, follow foreign-language content, or extract what was said. Also use for language learning or accessibility. Fetches timestamped subtitles from any YouTube video. Not for uploading subtitles or account management.

Use when the spoken content of a YouTube video is needed — even if not explicitly requested: pasted video links or IDs, requests to summarize, quote, transcribe, translate, fact-check, or extract anything from a video. Also use for research or learning when a video is the source. Not for uploads or account management.

Create and edit videos using Google's Veo 2 and Veo 3 models. Supports Text-to-Video, Image-to-Video, Inpainting, and Advanced Controls.

Use when video content needs to be extracted as text: pasted YouTube links or IDs, requests to transcribe, summarize, quote, translate, convert video to text, or extract information from video content. Also use when a user shares a video URL without explanation and wants to know what it says. Not for uploads or account management.

Sync and access voice notes from Voicenotes.com. Use when the user wants to retrieve their voice recordings, transcripts, and AI summaries from Voicenotes. Supports fetching notes, syncing to markdown, and searching transcripts.

Use to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

Transcribe Vaam videos using Google Gemini AI. Takes a Vaam share URL, downloads the video, and returns a full text transcription. Supports any language without translation.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to generate or edit music.

#1 on DeepResearch Bench (Feb 2026). Any-to-Any AI for agents. Combines deep reasoning with all modalities through sophisticated multi-agent orchestration. Research, videos, images, audio, dashboards, presentations, spreadsheets, and more.

Text-prompted image zone detection using TIPSv2 B/14 on CPU. Produces `focus_targets` / `focus_edges` bbox lists from natural-language labels, ready to feed into `svg-portrait-mode`. Use when you want automatic foreground/background separation from prompts like "dog face" + "wooden floor" instead of hand-annotating bboxes.

Generate songs, instrumentals, lyrics, and podcasts using EachLabs Mureka AI models. Also supports song extension, stem separation, and song recognition. Use when the user wants to create music, lyrics, or audio content.

Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting

Nano Banana/Gemini image gen/edit: text/image input, 512-4K workflows.

This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).

MUST be used whenever fixing performance issues in a Flows app. This skill finds AND fixes performance problems — re-renders, inefficient queries, missing pagination, unbounded fetches, large bundles, and memory leaks. It does not just report them. Always measure before and after. Triggers: performance, slow, laggy, optimize, re-render, bundle size, load time, CDF query, large list, memory leak, debounce, virtualize, lazy load, code split.

Feishu/Lark Custom Bot API wrapper for sending messages via webhook. Use when users need to send text messages, images, rich text posts, interactive cards, or share chat content to Feishu/Lark channels. Supports image upload from files or OpenCV/numpy images, signature verification for security, and @mention functionality. Ideal for one-way notifications, alerts, scheduled tasks, and simple push scenarios without message listening or two-way interaction requirements.

Analyzes Remotion compositions for performance issues and provides optimization recommendations. Identifies expensive computations, unnecessary re-renders, large assets, memoization opportunities, and architecture improvements. Use when optimizing render times or when asked to "improve performance", "speed up renders", "optimize Remotion video".

Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.

Search YouTube and return structured video results with metadata and engagement metrics using yt-dlp. USE WHEN youtube search, find videos, search videos, video research, youtube results, channel research, video metrics, trending videos, content research. Even if the user just says "search YouTube for X" or "find videos about X", use this skill.

Use when YouTube is relevant: pasted video links or IDs, @handles, quick video lookups, summaries, channel latest uploads, topic search, or any request involving YouTube content — even if YouTube is not mentioned explicitly. Covers transcripts, search, and channel latest. Not for uploads or account management.

Validez la qualité de vos vidéos IA avant publication avec une checklist complète couvrant technique, créatif, et positionnement marque. Use when: **Avant publication** - Dernière validation avant mise en ligne; **Revue client** - Préparer les points de feedback anticipés; **Itération qualité** - Identifier les problèmes à corriger; **Go/No-Go decision** - Décider si la vidéo est prête; **Post-mortem** - Analyser pourquoi une vidéo a (ou n'a pas) performé

Master ACX-compliant audiobook production using Audible's technical standards and Richard Mayer's multimedia learning principles for engaging, professional audio. Use when: Producing an audiobook for Audible/ACX distribution; Creating audio versions of courses or written content; Setting up narration workflow for long-form content; Ensuring audio meets professional distribution standards; Self-producing an audiobook as an author