Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Not for non-AMC calibration or runtime analytics.

YouTube Data API v3 complete wrapper - search videos, get video/channel/playlist details, get comments, download subtitles, etc. Supports filtering and sorting by time/views/rating and more.

Zoom RTMS Meeting Assistant — start on-demand to capture meeting audio, video, transcript, screenshare, and chat via Zoom Real-Time Media Streams. Handles meeting.rtms_started and meeting.rtms_stopped webhook events. Provides AI-powered dialog suggestions, sentiment analysis, and live summaries with WhatsApp notifications. Use when a Zoom RTMS webhook fires or the user asks to record/analyze a meeting.

Manage comprehensive Spanish learning system with A2 level support, vocabulary tracking, TTS integration, practice management, and deep search capabilities.

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

Alibaba Cloud Security Center (SAS) agent onboarding and management assistant. Use this skill when the user wants to onboard servers to Security Center, install the security agent, deploy cloud security protection, connect via proxy, troubleshoot agent offline or installation failures, create image templates with pre-installed agent, view Security Center version and expiration, check authorization quota, upgrade or switch server protection versions, toggle pay-as-you-go feature modules, uninstall the Security Center agent from a server, find servers with specific software installed (e.g. Nginx, MySQL, Redis), or detect security risks (vulnerability scanning, baseline checks, security alert queries).

Provides patterns to deploy ECS tasks and services with GitHub Actions CI/CD. Use when building Docker images, pushing to ECR, updating ECS task definitions, deploying ECS services, integrating with CloudFormation stacks, configuring AWS OIDC authentication for GitHub Actions, and implementing production-ready container deployment pipelines. Supports ECS deployments with proper security (OIDC or IAM keys), multi-environment support, blue/green deployments, ECR private repositories with image scanning, and CloudFormation infrastructure updates.

Use when working with camera, photos, audio, haptics, ShazamKit, or Now Playing. Covers AVCaptureSession, PHPicker, PhotosPicker, AVFoundation, Core Haptics, audio recognition, MediaPlayer, CarPlay, MusicKit.

This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Build computer vision solutions - image classification, object detection, and transfer learning

Upload and manage files using Google Gemini File API via scripts/. Use for uploading images, audio, video, PDFs, and other files for use with Gemini models. Supports file upload, status checking, and file management. Triggers on "upload file", "file API", "upload image", "upload PDF", "upload video", "file management".

Generate images using Google Gemini and Imagen models via scripts/. Use for AI image generation, text-to-image, creating visuals from prompts, generating multiple images, custom aspect ratios, and high-resolution output up to 4K. Triggers on "generate image", "create image", "imagen", "text to image", "AI art", "nano banana".

This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Provides expert guidance for building GraalVM Native Image executables from Java applications. Use when converting JVM applications to native binaries, optimizing cold start times, reducing memory footprint, configuring native build tools for Maven or Gradle, resolving reflection and resource issues in native builds, or implementing framework-specific native support for Spring Boot, Quarkus, and Micronaut. Triggers include "graalvm native image", "native executable java", "java cold start optimization", "native build tools", "ahead of time compilation java", "reflection config graalvm", "native image build failure".

Diagnose lyric problems across prosody, rhyme, meaning, register, sound, and structure. Use when AI-generated or human lyrics feel flat, cliched, awkward, or mismatched.

Run a real-time AI phone agent using Twilio, Deepgram, and ElevenLabs. Handles incoming calls, transcribes audio, generates responses via LLM, and speaks back via streaming TTS. Use when user wants to: (1) Test voice AI capabilities, (2) Handle phone calls programmatically, (3) Build a conversational voice bot.

Best practices for Remotion — video creation in React. Use when the agent needs to work with Remotion code: compositions, animations, audio, captions, 3D, transitions, text effects, charts, GIFs, Lottie, maps, or any video rendering pipeline. Covers FFmpeg integration, audio visualization, and all Remotion APIs.

Search, rent, manage, and release phone numbers with the Sinch Numbers API. Use when listing active numbers, searching available numbers, renting or releasing numbers, updating number configuration (SMS/voice/callback), managing emergency addresses, or checking available regions.

AI-powered audio and video editing pipeline: Whisper word-level transcription (insanely-fast-whisper on MPS) → Claude segment classification (KEEP / CUT_FILLER / CUT_FALSE_START / CUT_STUTTER / CUT_DEAD_AIR / CUT_EDIT_MARKER) → ffmpeg execution with 40ms qsin crossfades and room-tone gap fill → optional Cleanvoice API cloud polish for mouth sounds and loudness normalization. Distinguishes rhetorical pauses from accidental ones. Breaths attenuated to 50% volume (not removed). Preview mode (--preview flag) shows proposed cuts without modifying audio. Aggressive mode (--aggressive flag) applies tighter filler detection thresholds. Polish step (--polish flag) uploads to Cleanvoice API for mouth sound removal and loudness normalization — confirm before cloud upload of sensitive content. Pipeline tools: Transcribe.ts, Analyze.ts, Edit.ts, Polish.ts, Pipeline.ts. Single workflow: Clean.md. Requires ANTHROPIC_API_KEY; CLEANVOICE_API_KEY optional for polish step. USE WHEN: clean audio, edit audio, remove filler words, clean podcast, remove ums, cut dead air, polish audio, trim recording, audio cleanup, cut stutters, edit interview recording, preview edits, aggressive clean. NOT FOR video composition or animation (use Remotion).

Use when transcribing non-realtime speech with Alibaba Cloud Model Studio Qwen ASR models (`qwen3-asr-flash`, `qwen-audio-asr`, `qwen3-asr-flash-filetrans`). Use when converting recorded audio files to text, generating transcripts with timestamps, or documenting DashScope/OpenAI-compatible ASR request and response fields.

Use when generating videos with DashScope Vidu models. Use when implementing text-to-video, image-to-video (first frame), keyframe-to-video (first+last frame), or reference-to-video generation via the video-synthesis async API.

Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text descriptions, generate artwork in various styles, create visual content for creative projects, or need AI-powered image generation capabilities.

Provides digital forensics and signal analysis techniques for CTF challenges. Use when analyzing disk images, memory dumps, event logs, network captures, cryptocurrency transactions, steganography, PDF analysis, Windows registry, Volatility, PCAP, Docker images, coredumps, side-channel power traces, DTMF audio spectrograms, packet timing analysis, CD audio disc images, or recovering deleted files and credentials.

Provides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Use for encoding puzzles, pyjails, bash jails, RF/SDR, DNS oddities, unicode tricks, esoteric languages, QR or audio puzzles, constraint solving, game theory, unusual sandbox escapes, and hybrid logic puzzles. Prefer a more specific skill first when the challenge is mainly web, pwn, reverse, forensics, malware, OSINT, or crypto. Treat this as the fallback skill for genuine cross-category or edge-case challenges, not the default starting point.

Docker containerization for development and production. Covers Dockerfiles, multi-stage builds, layer caching, Compose services, networking, volumes, health checks, security hardening, and production deployment patterns. Use when writing Dockerfiles, optimizing image size, configuring Compose services, debugging container networking, setting up health checks, hardening containers for production, or troubleshooting build cache issues.

Master Docker containerization, image building, optimization, and container registry management. Learn containerization best practices and image security.

Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.

Generate and edit images using the Gemini API (Nano Banana Pro). Use this skill when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.

Translate and dub a video into another language with voice cloning and lip-sync, powered by HeyGen Video Translation. The presenter keeps their face, their voice is cloned into the target language, and lips re-sync to the new audio — viewers see the same person speaking natively. Use when: (1) localizing an existing video into one or more languages ("translate this video to Spanish", "make this in French and German", "dub this into Japanese", "I need this in 10 languages for a launch"), (2) the user has a finished video and wants the SAME presenter speaking another language (not a new presenter — that's heygen-video), (3) podcast / audio-only translation ("translate this podcast", "dub the audio but keep my video"), (4) high-stakes translations where the user wants to review/edit subtitles before final render (the proofreads workflow), (5) "translate my video", "dub this", "localize this clip", "make a multilingual version", "subtitle and dub". Returns the translated video URL (or audio file for audio-only mode), one per target language. Chain signal: if the user wants to CREATE a new video in another language (no source video exists yet), route to heygen-video and write the script in the target language — do not use heygen-translate. Use heygen-translate only when there is an existing source video to localize. NOT for: creating new videos from scratch (use heygen-video), avatar creation (use heygen-avatar), TTS-only synthesis (use heygen-video with audio-only output), or text-only translation.

Use this skill for any image-related AI generation or editing task. Triggers include: GENERATE: "generate image", "create image", "make picture", "draw", "visualize", "image of", "create art", "generate art" EDIT: "edit image", "modify image", "change image", "update image", "fix image", "enhance image" ADD/REMOVE: "add to image", "put in image", "remove from image", "delete from image", "add element" STYLE: "style transfer", "make it look like", "convert style", "apply style", "in the style of" PRODUCT: "product photo", "product placement", "place product", "mockup", "put product on" COMPOSITE: "combine images", "merge images", "blend images", "create composite" Supports text-to-image generation, image editing with references, product placement, style transfer, and multi-image composition using Google Gemini (Nano Banana Pro) or OpenAI DALL-E.

Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro). Supports text-to-image, image editing, various aspect ratios, and high-resolution output (2K/4K). Use when user wants to generate images, create images, use Gemini image generation, or do AI image generation.

This skill should be used when the user asks to "make the PRD an HTML", "render this PRD as HTML to review", "build an interactive PRD", "let me vet the PRD as HTML", "turn this spec into something I can click through", or wants to review and approve a PRD/spec by inspecting an immersive HTML rendering instead of reading raw markdown. It produces a self-contained, tabbed, single-file HTML review experience with SVG flow diagrams — not a flat colorized dump of the .md.

ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}'` to extract its cell outputs and apply EVERY filter/sample-exclusion the notebook used — even when the question says 'Using DESeq2/Run X/Compute Y' (this describes the METHOD the notebook used, not a request to rerun). The notebook's cell outputs are the only published authoritative answers; reimplementing or reading stale pre-computed CSVs in the data folder produces different numbers because of outlier-sample removal, library version, and filter steps you don't see by skimming. STEP 2 routing — pick a sub-skill name from this exact list (never invent): tooluniverse-rnaseq-deseq2 (RNA/miRNA-seq DE, correlation, PCA, clustering, dispersion), tooluniverse-gene-enrichment (GO/KEGG/Reactome/GSEA/pathway enrichment), tooluniverse-statistical-modeling (regression, ANOVA, ordinal/logistic, chi-square, correlation, power), tooluniverse-image-analysis (microscopy, colony, fluorescence, dose-response, .tif — including ANOVA / Dunnett / power-analysis on image-derived measurements), tooluniverse-epigenomics (DNA methylation, CpG, m6A, MeRIP-seq, bisulfite, ChIP-seq, chromatin), tooluniverse-sequence-analysis (FASTQ, Trimmomatic, BWA, samtools, coverage), tooluniverse-variant-analysis (VCF, VAF, SNP, mutation), tooluniverse-phylogenetics (treeness, PhyKIT, parsimony), tooluniverse-single-cell (scRNA, h5ad, scanpy), tooluniverse-crispr-screen-analysis (MAGeCK, sgRNA), tooluniverse-proteomics-analysis (mass spec, TMT). Use for CSV/Excel/VCF/FASTA/h5ad and any biology/chemistry/medicine analysis question.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

This skill should be used when the user asks to "analyze video", "summarize video", "extract video transcript", "understand video content", "video to text", "describe video", "ask questions about video", or "what happens in this video". Analyzes videos using Google Gemini API with local file upload or YouTube URL input.

Use when generating images with Model Studio DashScope SDK using Qwen Image generation models (qwen-image, qwen-image-plus, qwen-image-max, qwen-image-2.0 series and snapshots). Use when implementing or documenting image.generate requests/responses, mapping prompt/negative_prompt/size/seed/reference_image, or integrating image generation into the video-agent pipeline.

Use when understanding images with Alibaba Cloud Model Studio Qwen VL models (qwen3-vl-plus/qwen3-vl-flash and latest aliases). Use when building image Q&A, visual analysis, OCR-like extraction, chart/table reading, or screenshot understanding workflows.

AI SDK-based image generation using official OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and quality presets.

Remove AI writing patterns from prose. Use this skill when writing, drafting, editing, reviewing, or revising any text to eliminate predictable AI tells, slop, and formulaic patterns. Trigger this skill whenever the user asks to "deslop", "de-AI", "make it sound human," "remove AI patterns," "remove AI tropes," "clean up AI writing," fix "slop," "deslop" text, or review prose for authenticity. Also use when the user asks you to write or draft anything and wants it to sound natural rather than AI-generated. Common use cases include scientific writing (manuscripts, abstracts, cover letters, grant narratives, discussion sections, peer review responses), blog posts, newsletters, memos, reports, and any other substantial prose.

Search Europeana's 50M+ cultural heritage items from 4,000+ European museums, galleries, libraries, and archives. Use this skill whenever the user wants to find European art, manuscripts, photographs, maps, 3D objects, audio, or video from institutions like the Rijksmuseum, British Library, Louvre, or Gallica. Also triggers when searching for open-access European cultural heritage, IIIF resources, or cross-referencing European collections with other library catalogs.

Test whether MicroSim controls (buttons, sliders, dropdowns) are fully visible inside their iframe without being clipped. Uses Playwright to load each MicroSim's main.html, measure actual content height, and compare against the iframe height declared in index.md. Use this skill whenever the user mentions iframe height testing, MicroSim visibility checking, controls being cut off, iframe sizing, or wants to verify that MicroSims render correctly at their configured heights. Also trigger when the user says things like "check if my sims fit", "are the controls visible", "test iframe heights", or "fix clipped controls".

Create a narrated video walkthrough of a pull request with code slides and audio narration. Use when asked to create a PR walkthrough, PR video, or walkthrough video.

Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.

YouTube API access without the official API quota hassle — transcripts, search, channels, playlists, and metadata with no Google API key needed. Use when the user needs YouTube data programmatically, wants to avoid Google API quotas, or asks for "youtube api", "get video data", "youtube without api key", "no quota youtube".

Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

Use this skill to turn screen recordings into polished app demo videos with AI voiceover and music. Triggers: "app demo", "demo video from recording", "screen recording demo", "narrate this recording", "add voiceover to screen recording", "make a demo from this recording", "polish this screen recording", "app walkthrough video", "product demo video", "turn this recording into a demo", "screen recording with voiceover", "app showcase video", "demo with narration" Orchestrates: screen analysis, voiceover script, device framing, TTS, background music, and final assembly. NOTE: This skill requires an existing screen recording as input. It does NOT generate screen recordings.

ASCII video: convert video/audio to colored ASCII MP4/GIF.

Digital Audio Workstation usage, music composition, interactive music systems, and game audio implementation for immersive soundscapes.

Search the web with DuckDuckGo as a no-API-key fallback or second source. Use when the normal web search tool or primary search provider is rate-limited, failing, unavailable, not delivering enough useful results, or producing weak results, and you want quick text, news, image, or video search results, instant-answer lookups, or DuckDuckGo bang resolution without browser automation.

Diagnose flat dialogue, same-voice characters, and lack of subtext. Use when conversations feel wooden, characters sound alike, or dialogue only does one thing at a time.

Expert patterns for branching dialogue systems including dialogue graphs (Resource-based), character portraits, player choices, conditional dialogue (flags/quests), typewriter effects, localization support, and voice acting integration. Use for narrative games, RPGs, or visual novels. Trigger keywords: DialogueLine, DialogueChoice, DialogueGraph, dialogue_manager, typewriter_effect, branching_dialogue, dialogue_flags, localization, voice_acting.

Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".

Search the Library of Congress digital collections via the loc.gov JSON API. Use this skill whenever the user wants to search LOC's digitized books, photos, maps, manuscripts, newspapers, audio, or film/video, look up items by LCCN, browse LOC collections, find primary sources with date range filters, or retrieve citations and download links for LOC materials. Also triggers when cross-referencing items found in other library catalogs against LOC holdings.

This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). Use this skill for tasks involving paper dissemination, conference preparation, creating explorable academic homepages, generating video abstracts, or producing print-ready posters from LaTeX or PDF sources.

Diagnose sentence-level issues after structure is solid. Use when prose feels flat, sentences are monotonous, word choices are generic, or voice is inconsistent.

Forensic-level deconstruction of YouTube videos to extract viral formulas, hooks, retention mechanics, and emotional engineering. Use when analyzing video transcripts to clone success patterns for new content.

Choose the right fal.ai endpoint for a given task. Modality-organized catalog of production endpoint defaults, text-to-image, image-to-image, text-to-video, image-to-video, and more. Use when the user has not named a specific model, or asks "which model for X", "best endpoint for Y", "what should I use for Z".

Craft high-quality natural-language image prompts for any modern text-to-image or image-edit model that accepts flowing English. Trigger when the user wants help writing, rewriting, improving, or translating an English natural-language image prompt — including "write me an image prompt", "improve this image prompt", "describe this scene for an image model", or "convert these tags into a natural language prompt". Do NOT trigger for requests that are purely about dispatching to an image API, choosing samplers/schedulers, picking LoRAs, or setting up ControlNet — those belong to a runtime skill.

Best practices for Remotion - Video creation in React. Use when creating programmatic videos with Remotion, adding animations or transitions, working with audio/captions, rendering compositions, embedding 3D content, building charts, or using Mapbox maps in video.

Session conversational voice with McConkey personality. Invoke for Saucer Boy energy during work sessions — ambient personality that makes working with Jerry fun, or explicit McConkey invocation for on-demand persona responses. Use when you want McConkey-style commentary, encouragement, or perspective. Personality disengages automatically for hard stops, security, and governance.

Builds rich text editors with Tiptap, a headless ProseMirror-based editor framework for React with Tailwind v4 support. Covers SSR-safe setup, image uploads, prose styling, collaborative editing, and markdown support. Use when adding a rich text editor, configuring Tiptap extensions, handling image uploads in editors, or setting up collaborative editing with Y.js. Use for tiptap, rich text, editor, prosemirror, react, tailwind.

Research YouTube topics, analyze competitor videos, deconstruct viral content, and query the YouTube Data API. Use when researching a video topic before planning, analyzing video transcripts for viral patterns, searching competitor channels, or fetching video and channel stats via the YouTube Data API v3.

This skill helps users extract YouTube video transcripts and perform deep competitive analysis on the content. Agent should proactively apply this skill when users express needs like analyze YouTube video content strategy, perform competitive video content analysis, extract and analyze YouTube subtitles for marketing insights, understand competitor value propositions from their videos, identify target audience from YouTube video content, analyze pain points and needs mentioned in YouTube videos, evaluate competitor CTA strategies in video content, find content gaps in competitor YouTube videos, analyze video narrative structure and hooks, extract key messaging and positioning from YouTube content, benchmark competitor video content quality, research competitor marketing angles through video analysis, identify audience signals and terminology level in videos, analyze emotional tone and persuasion techniques in YouTube content.

Resize photos and videos to exact pixel dimensions or aspect ratios using Adobe tools. Use this skill whenever a user wants to resize, scale, or change the dimensions of an image or video file — including phrases like "resize this to 1920x1080", "make this 4K", "scale to 800x600", "change the aspect ratio to 16:9", "resize my video", "make the image smaller", "crop to square", "fit this to a specific size", "resize for print", "resize for web", "make it 300 DPI ready", "change canvas size", "resize a batch of photos", or any request specifying target dimensions (W×H, ratio, or named size like "4K", "HD", "A4"). Also triggers for: "make this fit a specific size", "resize to [any dimension]", "I need this at [WxH]", "scale my video down", "change resolution", "downscale", "upscale". NOT for social media platform sets (use adobe-create-social-variations for that). Uses image_crop_and_resize for photos, video_resize for videos.

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

Clerk Billing for subscription management - render Clerk's PricingTable and in-app checkout drawer, configure subscription plans, seat-limit plans for B2B, feature entitlements with has(), and billing webhooks. Use for SaaS monetization, plan gating, checkout flows, trials, invoicing, and subscription lifecycle management.

Guided conversational interview to understand a user's creative vision before generating model-appropriate image prompts. Asks clarifying questions about subject, mood, style, and technical preferences (4-7 exchanges), then synthesizes positive prompt, negative prompt, recommended settings table, and pipeline recommendation. Formats prompts for the target model (SDXL tag-style, FLUX natural language, SD1.5 weighted tokens). Triggers on "I want to create...", "help me make an image of...", "I have an idea for...", "help me craft a prompt", "write me a prompt for...", or any request for help describing a creative vision. Does NOT cover workflow building, prompt debugging/fixing, technical explanations, model training, code generation, or identity-preserving character generation.

Docker and Podman container management: Dockerfile optimization, multi-stage builds, Compose v2 orchestration, networking, volumes, security hardening, supply chain integrity, health checks, resource limits, Quadlet systemd integration, and debugging. Invoke whenever task involves any interaction with containers — writing Dockerfiles, configuring Compose, managing Podman Quadlets, reviewing container security, debugging container issues, or setting up image signing and scanning.

Makes AI-generated prose sound natural and human-written. Covers tone analysis, sentence variation, voice consistency, readability improvement, and AI-typical pattern removal including hedging, filler words, and over-qualification. Use when improving blog posts, marketing copy, or narrative documentation. Use for tone consistency, readability, sentence rhythm, and removing AI-typical writing patterns.

Bootstraps Flux CD on Kubernetes clusters, creates and manages GitOps sources (Git/Helm/OCI/Bucket), configures kustomizations and Helm releases, reconciles resources, sets up image automation and alerting, and pushes OCI artifacts. Use this skill whenever the user mentions the flux CLI, flux bootstrap, flux create source, flux create kustomization, flux create helmrelease, flux reconcile, flux get, Flux CD, GitOps with Flux, or asks about managing Kubernetes deployments via GitOps. Also trigger when users ask about creating Git/Helm/OCI/Bucket sources, building or diffing kustomizations, pushing OCI artifacts, setting up image automation, creating Flux alerts/receivers, or bootstrapping Flux on GitHub/GitLab/Gitea/Bitbucket. Even if the user just says "flux" in a Kubernetes context, this skill applies.

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via `gen4_turbo`), or building multimodal AI pipelines.

Use this skill for AI music generation. Triggers include: "generate music", "create a song", "make music", "compose", "create a beat", "generate audio", "make a soundtrack", "create a jingle", "instrumental music", "background music", "lo-fi beats", "electronic music" Supports vocals (Suno/Udio) and instrumental-only (Google Lyria).

NotebookLM integration patterns for external RAG, research synthesis, studio content generation (audio, cinematic video, slides, infographics, mind maps), and knowledge management. Use when creating notebooks, adding sources, generating audio/video, or querying NotebookLM via MCP.

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.

Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.

Use this skill for AI text-to-speech generation. Triggers include: "generate voice", "create audio", "text to speech", "TTS", "read this aloud", "generate narration", "create voiceover", "synthesize speech", "podcast audio", "dialogue audio", "multi-speaker", "audiobook" Supports Google Gemini TTS, ElevenLabs, and OpenAI TTS.

AI agent self-portrait generator. Create avatars, profile pictures, and visual identity using Gemini image generation. Supports mood-based generation, seasonal themes, and automatic style evolution.

Private registry setup, image management, and multi-registry operations

Publish static page artifacts from the publisher workspace to a GitHub Pages repository using a fine-grained token, with advisory image optimization and an original-image path. Use when a React/static page artifact is already prepared and needs to be copied into the Pages repo under a strict year/year-month/page-slug directory layout, then committed and pushed, with a final public artifact URL returned.

Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Covers both LiveKit Cloud and self-hosted deployments using lk CLI.

Generate AI music with ElevenLabs Music API. Use for: background music, soundtracks, jingles, theme songs, instrumental tracks, AI music composition.

Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys. Do NOT use for deploying to Vercel, Cloudflare, or Render (use their respective skills).

React performance optimization patterns including memoization, code splitting, bundle size reduction, re-render elimination, and profiling. Covers React Compiler automatic optimization, manual memo/useMemo/useCallback targeting, React.lazy with Suspense, barrel file avoidance, content-visibility for large lists, startTransition for non-urgent updates, and React DevTools profiling. Use when optimizing React app performance, reducing bundle size, eliminating unnecessary re-renders, debugging slow components, code splitting, or profiling rendering bottlenecks. Use for performance audit, bundle analysis, re-render diagnosis, lazy loading, virtualization.

Turn a real, timely trigger into content for an artist — a fresh milestone (crossed 2B streams, added to a flagship playlist, a TV/film sync, a chart entry) or a current trend/sound. Use when the user says "they just hit [X], make something", "make something for the milestone", "what's the move right now", "make it feel current/timely", or "react to [news]". Reads the artist's research feed to find the real moment, picks the angle, then routes the actual asset to the right content skill (promo graphic / caption / short video). Not for evergreen "make a post" requests with no trigger — use the router for those.

Augmented vision tools for analyzing images beyond native visual capabilities. Use when tasked with describing images in detail, reproducing images as SVGs, identifying subtle features, comparing image regions, reading degraded text, or any task requiring careful visual inspection. Also use when the image-to-svg skill needs ground truth about colors, shapes, or boundaries.

Detects and eliminates AI writing tropes that make text sound artificial or formulaic. Use when generating text content, writing documentation, creating code comments, or reviewing writing style. Supports two-tier preference overrides (global ~/.claude/office.local.md + project .claude/office.local.md).

Use this skill for AI video generation. Triggers include: "generate video", "create video", "make video", "animate", "text to video", "video from image", "video of", "animate image", "bring to life", "make it move", "add motion", "video with audio", "video with dialogue" Supports text-to-video, image-to-video, video with dialogue/audio using Google Veo 3.1 (default) or OpenAI Sora.

Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.

Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) — through a consultative, modular step-by-step approach that only adds what you actually need. This should trigger for requests such as Add Maven plugins in pom.xml; Improve Maven plugins in pom.xml. Part of cursor-rules-java project

Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.

Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.

Docker containerization patterns for Python/React projects. Use when creating or modifying Dockerfiles, optimizing image size, setting up Docker Compose for local development, or hardening container security. Covers multi-stage builds for Python (python:3.12-slim) and React (node:20-alpine -> nginx:alpine), layer optimization, .dockerignore, non-root user, security scanning with Trivy, Docker Compose for dev (backend + frontend + PostgreSQL + Redis), and image tagging strategy. Does NOT cover deployment orchestration (use deployment-pipeline).

Generate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.

Generate architecture diagrams as .excalidraw files from codebase analysis, with optional PNG/SVG export. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, generate excalidraw files, export excalidraw diagrams to PNG or SVG, or convert .excalidraw files to image formats.

Generate high-quality images from text prompts using fal.ai's text-to-image models. Supports intelligent model selection, style transfer, and professional-grade outputs.