Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Control a PreSonus StudioLive Series III mixer from the command line. Trigger when the user asks about ucmix, a StudioLive / 32R / UCNET mixer, setting channel names/patches/48V/faders/mutes, monitor (aux) mixes, limiters, FX/reverb, stereo links, colors/icons, scenes, board-as-code (verify/apply a config), or reading/writing any mixer parameter.
Automatically rig 3D models with UniRig (VAST-AI-Research, SIGGRAPH'25) — predict a skeleton, predict skinning weights, and merge the rig back onto the original mesh. Use when the user wants auto-rigging for .obj/.fbx/.glb/.gltf/.dae/.vrm assets, a skeleton or skin weights for a character or creature, a UniRig environment prepared on a CUDA machine, batch rigging of a model directory, or an honest comparison between UniRig, SkinTokens, Tripo, Mixamo, AccuRig, and Blender Rigify. Triggers on: unirig, auto rig, auto-rigging, 3D rigging, skeleton prediction, skinning weights, rig a character, armature generation, rigged glb, rigged fbx, bone weights.
AI video maker that generates and edits videos entirely through conversation. Describe a video concept and the AI creates it from scratch — or upload existing footage and edit by chatting. Handles the complete video production workflow: generate scenes from text prompts, arrange clips on a timeline, add background music and sound effects, insert titles and lower thirds, apply color grading, overlay subtitles, and export as MP4. Built for content creators, marketers, and anyone who needs video content without learning editing software. Create product demos, social media clips, educational content, promotional videos, and personal projects through natural language. The AI video maker understands context — say "make it shorter" or "add energy" and it knows what to change. Supports mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav.
Professional AI video storyboard designer. Use this skill when the user wants to create videos, produce storyboard scripts, generate AI video prompts, or plan video content structure. Covers all video types: short videos, ads, educational content, brand videos, vlogs, short films, etc. Trigger this skill even if the user only says "help me make a video" or "I want to shoot something about XX". Outputs professional storyboard designs + prompts ready for mainstream AI video tools such as 即梦 (Seedance 2.0) / Sora / Kling / Runway / Veo, with dedicated output for 即梦 Seedance 2.0's multimodal @ reference syntax.
Based on the user's topic direction, help find specific topics with high traffic and strong appeal, and generate headlines that follow the 10 principles of viral headlines. Use for content creation, article writing, self-media operation, and similar scenarios, when the user needs topic suggestions or headline optimization.
Generate keyword strings for images, screenshots, or visual references — optimized for fuzzy search, not alt text or prose. Use when the user says 'keywords for this image', 'tag this for search', 'visual keywords', or wants searchable labels on an Eagle asset.
Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it. Use when an agent's drafts start sounding like a caricature of you, before publishing anything written in your voice, or every ten new pieces to re-measure.
Engineers internally consistent fictional worlds using Brand's Pace Layers for social structure and Sanderson's Laws of Magic for system constraints. Use when building settings, designing magic or tech systems, or auditing a world for logical contradictions.
Tired of scrubbing through hours of footage just to extract key moments, summaries, or actionable insights? The ai-gemini skill brings Google Gemini's multimodal intelligence directly to your videos on ClawHub. Analyze scenes, generate detailed descriptions, ask natural language questions about video content, and surface meaningful takeaways — all without manual review. Ideal for content creators, researchers, marketers, and educators. Supports mp4, mov, avi, webm, and mkv formats.
Turn a 3-minute tutorial video recorded on phone into 1080p captioned video files just by typing what you need. Whether it's adding AI-generated subtitles to videos on mobile or quick social content, drop your video files and describe the result you want. No timeline dragging, no export settings — 30-60 seconds from upload to download.
Get captioned video files ready to post, without touching a single slider. Upload your video files (MP4, MOV, AVI, WebM, up to 500MB), say something like "add subtitles in English and Spanish to my video", and download 1080p MP4 when it's done. Built for content creators who move fast and need accurate captions without manual transcription.
Identifies and removes signs of AI-generated text to make writing sound more natural and human. Use when the user asks to humanize text, make writing sound more natural, remove AI patterns, edit for human voice, or convert AI-generated content to natural prose. Also triggers on requests to check for AI writing patterns, review text for robotic language, or improve writing authenticity. Based on Wikipedia's "Signs of AI writing" guidelines.
Turn a 2-minute unedited screen recording into 1080p edited MP4 videos just by typing what you need. Whether it's automatically editing raw footage into polished videos using Gemini AI or quick social content, drop your raw video footage and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
Skip the learning curve of professional editing software. Describe what you want — add fun transitions, bright text titles, and background music for my kids birthday video — and get kid-friendly edited videos back in 1-2 minutes. Upload MP4, MOV, AVI, WebM files up to 500MB, and the AI handles AI kids video editing automatically. Ideal for parents and young creators who want child-safe simple edits without learning complex software.
Skip the learning curve of professional editing software. Describe what you want — animate this image into a 5-second video with smooth motion — and get AI-generated video clips back in 1-2 minutes. Upload MP4, MOV, JPG, PNG files up to 500MB, and the AI handles AI video generation automatically. Ideal for content creators and marketers who want to create cinematic AI video clips without complex editing software.
Turn a 2-minute iPhone screen recording into 1080p edited MP4 clips just by typing what you need. Whether it's editing raw Mac-recorded footage into polished videos without desktop software or quick social content, drop your raw video footage and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
edit raw video footage into prompt-edited video with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and marketers use it for editing videos by typing plain-text instructions instead of manual timeline editing — processing takes 30-90 seconds on cloud GPUs and you get 1080p MP4 files.
generate images or clips into ready-to-share videos with this skill. Works with MP4, MOV, JPG, PNG files up to 200MB. TikTok creators use it for generating short videos from photos or clips on a mobile device — processing takes 30-60 seconds on cloud GPUs and you get 1080p MP4 files.
Use when creating, repairing, converting, packaging, or verifying app icons for any platform from briefs, references, brand marks, SVG/logo/text assets, generated concepts, or existing icons; use the optional Apple adapter when Icon Composer output is requested
Write and translate natural, grammatically correct Arabic — Modern Standard Arabic plus Egyptian, Levantine, Gulf, and Maghrebi dialects — that avoids machine-translation tells. Use whenever producing Arabic prose: writing original Arabic, translating into Arabic (especially from English), or editing/proofreading Arabic for grammar, spelling (hamza, ة/ه, ى/ي), agreement, collocations, punctuation, register, or naturalness. Use even when the user only asks to "say this in Arabic" or pastes Arabic text to fix.
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Writes engaging Chinese novels chapter by chapter. Supports various genres (mystery, romance, fantasy, sci-fi, history, etc.), long-form creation of 10-50 chapters at 3,000-5,000 characters per chapter, with suspense hooks at the end of each chapter. Emphasizes in-depth polishing to remove AI traces and ensure natural, fluent prose. Use when the user asks for: writing a novel, creating a story, chapter-by-chapter writing, continuous plot, chapter cliffhangers, or a long novel.
Get compressed MP4 files ready to post, without touching a single slider. Upload your large video files (MP4, MOV, AVI, MKV, up to 500MB), say something like "compress this video to under 100MB without losing quality", and download 1080p MP4 when it's done. Built for content creators, marketers, students who move fast and want smaller file sizes without manually adjusting bitrate settings.
Use when creating or modifying LottieFiles Creator Plugins with the Creator Plugin API. Covers plugin sandbox/UI architecture, message passing, scene graph manipulation, assets, storage, animation, and plugin development workflows.
Install, operate, and troubleshoot 0ceal0t/Dalamud-VFXEditor for user-owned Final Fantasy XIV visual-effect, animation, sound, physics, UI, texture, material, model, and shader files. Use when a user asks about `/vfxedit`, AVFX, PAP, TMB, SCD, Dalamud plugin setup, effect replacement, export handoff, beta repositories, or VFXEditor source builds. Triggers on: Dalamud VFXEditor, /vfxedit, .avfx, .pap, .tmb, .scd, FFXIV VFX mod, or VFXEditor beta.
代川 DCVlog: makeup artist Vlog scripting + Korean-style portfolio collages + a sustainable, mature case library. Start with /dcvlog; supports “I want to start writing copy” and “I want to make a collage,” or say “update DCVlog.” In copy mode, it interviews for observations about people during real services, aesthetic choices, and the finished look, then drafts against 19 original texts, avoiding birthday/color-scheme templates. Collages support 1–6 photos; the case library preserves locked baselines and continuously adds new batches.
Creates studio-quality motion design videos with code (Remotion/React), licensed music, synchronized SFX, optional voice (ElevenLabs or a local TTS model selected based on the hardware), and automated lint and QA gates before delivery. Use for requests involving motion design, motion graphics, animated video, explainers, product or launch videos, animated reels or TikToks, kinetic typography, animated logos, UI animation, loops, video narration or voiceover, or techniques such as keyframing, zoom in and zoom out, motion smooth, morphing, rigging, frame by frame, cel animation, stop motion, rotoscopia, motion tracking, match moving, compositing, motion 3D, speed ramp, match cut, overshoot, parallax, and transitions. Also for animated video, kinetic typography, product launch video, explainer with voiceover, and text-to-speech narration.
Game feel consulting based on Steve Swink's "Game Feel: A Game Designer's Guide to Virtual Sensation" (Morgan Kaufmann, 2009). Use when helping with control responsiveness, input mapping, physics tuning, avatar movement, jump mechanics, polish effects, or analyzing why controls feel "floaty", "tight", "responsive", or "sluggish". Covers the psychology of real-time control, metrics for measuring feel, and practical tuning guidance. NOT for general game design - focused specifically on the tactile sensation of controlling virtual objects.
Tired of scrubbing through hours of footage trying to extract meaning, summaries, or actionable data from your videos? The google-ai skill brings Google's Gemini-powered intelligence directly into your video workflow. Automatically generate transcripts, identify key moments, summarize content, and ask natural language questions about any video. Perfect for content creators, researchers, educators, and business teams. Supports mp4, mov, avi, webm, and mkv formats.
xAI Grok Imagine API integration for image generation, text-to-video, image-to-video, and editing via natural language. Use when you need to generate images or videos from text prompts, edit existing images, animate static images into videos, or edit existing videos with natural language instructions. Supports conversational generation across messaging platforms with async polling, progress updates, and automatic delivery.
Rewrite text so it reads like a real person wrote it, not an AI. Auto-detects Russian vs English and applies the matching rule set. Use when the user asks to humanize text, remove the “AI smell,” de-AI, or make AI output sound natural—especially for Russian. Russian requests count too: очеловечь, перепиши как человек, оживи текст, убери запах ИИ, сделай живее, звучит как робот, убери канцелярит. Also use when asked whether a text was written by AI—нейросеть писала?, похоже на ChatGPT?, видно ли, что это ИИ, человек или бот писал, did AI write this?—then check and report findings without rewriting. While installed, also keep your own Russian and English writing free of the quick-list stock phrases, silently; never edit the user's text unless asked.
Skip the learning curve of professional editing software. Describe what you want — turn my local photos into a 15-second video with smooth transitions — and get animated video clips back in 30-60 seconds. Upload JPG, PNG, WEBP, HEIC files up to 200MB, and the AI handles AI video creation automatically. Ideal for social media creators who want to turn saved images into video without uploading to cloud editors.
create images, text into Marathi invitation videos with this skill. Works with JPG, PNG, MP4, MOV files up to 200MB. Marathi-speaking event hosts use it for creating free Marathi language invitation videos for weddings and events — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Expert in creating rich backstories, fictional universes, and ARGs (Alternate Reality Games). Covers world-building, mystery construction, community-driven storytelling, and transmedia narratives. Knows how to create depth that rewards exploration without overwhelming. Use when "lore, world building, backstory, ARG, mythology, fictional universe, hidden story, deep canon" mentioned.
Plans video strategy, scripts, and optimization for YouTube, TikTok, Reels, and video ads. Triggers for 'video strategy', 'YouTube', 'video script', 'Reels script', 'video SEO', 'thumbnail', 'video ad script', 'webinar', 'Loom', 'explainer video', 'product demo video', 'short-form video', or 'video content calendar'.
Read BEFORE troubleshooting or enhancing camera image quality. Diagnoses and enhances image quality from cameras connected via Image Acquisition Toolbox or USB Webcams support package. Discovers camera capabilities at runtime, analyzes captured images for quality issues (brightness, contrast, sharpness, noise, color balance, backlighting), suggests hardware setting adjustments tailored to the specific camera, and applies Image Processing Toolbox enhancement functions. Use when a user wants to improve camera image quality, troubleshoot dark/blurry/noisy/grainy/ overexposed/washed out/color cast images, or optimize camera settings.
Reference for MATLAB audiostreamer (Audio Toolbox R2025a+). Without this skill, agents consistently default to legacy audioDeviceWriter/audioDeviceReader or base MATLAB sound(), producing less capable code. Use when writing code for audio playback, recording, full-duplex device I/O, real-time audio measurements, or audio I/O processing with callbacks. Also use when debugging audiostreamer errors, dropouts, or latency issues, or migrating from audioDeviceReader, audioDeviceWriter, audioPlayerRecorder, or audioplayer/audiorecorder.
Get polished edited videos ready to post, without touching a single slider. Upload your raw video clips (MP4, MOV, AVI, WebM, up to 500MB), say something like "cut, trim, and add transitions to turn my clips into a finished movie", and download 1080p MP4 when it's done. Built for casual video creators who move fast and want to make polished videos without buying or cracking expensive software.
USE FOR finding web videos by a text query, powered by Octen. Returns ranked videos with the matched segment (start/end timestamps), duration, cover image, source page, and author. In Beta. Contact us to request beta access at https://octen.ai. Use it when the user wants to find videos, clips, tutorials, or a specific moment within video content.
Use this skill when the user wants to create Xiaohongshu (小红书/RedBook) posts. Trigger phrases: 小红书创作, create redbook, 小红书, 红书, 笔记创作, 帖子创作. The user will provide images, videos, or text content. This skill analyzes the content, searches for trending Xiaohongshu posts as reference, generates post title and copy, auto-edits videos (merge, subtitles, BGM, narration), attempts auto-upload to Xiaohongshu creator platform, and generates a local preview HTML file.
Translate an existing Remotion (React-based) video composition into a FrameVideo HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as FrameVideo (e.g. "port my Remotion project to FrameVideo"). Do NOT use when (a) authoring a NEW FrameVideo composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh FrameVideo build. When in doubt, default to the `framevideo` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.
The clip depends on the action loop. Write every link from run-up to landing in order, specify the desired physics for each part, and use the negative list to prevent flying, hovering, and teleporting. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (sports and extreme stunts; Chinese trigger terms: 体育与极限运动, 体育, 极限运动, 跑酷, 滑板), or asks how published examples of this type were prompted. Read references/cases.md before drafting.
Prepare cohesive image prompts for presentation slides by combining a chosen theme with concise factual team and technology references. Use when the user asks to prepare image prompts or backgrounds for presentation slides. Russian discovery terms: промпты слайдов, фоновые изображения, тема презентации, графика для слайдов.
Draw beautiful diagrams using AI image generation. Supports 10 chart types: flowcharts, architecture diagrams, ER diagrams, business model canvas, user journey maps, mind maps, competitive analysis charts, SWOT analysis, product roadmaps, and org charts. 6 built-in visual styles. Trigger words: "画个 XX 图", "生成商业模式画布", "做个架构图", "画 ER 图", "帮我画个流程图", "生成用户旅程图", "做个思维导图", "竞品分析图", "SWOT 分析图", "产品路线图", "组织架构图", "帮我可视化图表". [WeChat official account image version] User provides content → produces images for the WeChat official account. Prefer the image generation models built into the current environment (Codex built-in image_gen/image2, workbuddy image generation model) to directly generate PNGs; when no built-in model is available, fall back to the API scripts under scripts/.
Swimming pool owners book the service company they trust — and trust starts with seeing the work before the first call. A homeowner whose pool turned green last summer is not comparing prices on a directory listing. They are watching a before-and-after transformation video that shows a pool going from algae-covered to crystal clear, and calling the company that posted it. Swimming Pool Cleaning Video creates professional marketing and educational videos for pool cleaning services, pool maintenance companies, weekly service routes, and seasonal pool opening and closing specialists: produces before-and-after transformation videos showing pool water clarity restoration, algae treatment results, and equipment cleaning outcomes that demonstrate service quality better than any written review, creates weekly service explainer videos showing customers exactly what your technicians do during each visit — brush, vacuum, chemical balance check, equipment inspection — so they understand the value they are paying for every month, builds seasonal service videos promoting spring pool openings and fall winterization packages to the homeowners who need to book now before your schedule fills, and exports content for company websites, Google Business Profile, Nextdoor, and the neighborhood Facebook groups where pool service recommendations actually happen. Independent pool service companies, regional pool maintenance franchises, full-service pool companies handling both cleaning and repairs, and new pool installers expanding into recurring service contracts all use Swimming Pool Cleaning Video to convert backyard pool owners into loyal weekly service customers. Swimming pool cleaning video, pool maintenance marketing, pool service promo video, pool cleaning company video, weekly pool service video, pool care marketing, swimming pool service video maker, pool water treatment video, residential pool cleaning video, pool maintenance promo.
Create an AI talking head from the user's own photos plus a voice sample, or from a self-recorded video by extracting face frames and speech. Use an authorized cloned or existing ElevenLabs voice and a new script to generate speaking shots with fal MiniMax H3, narration and editable motion graphics, then render an MP4. Use for AI avatars, presenter videos, personal explainers and scripted on-camera clips. For a recording that only needs graphics without generating new speech, use a recording-editing workflow instead.
Plan and author SillyTavern text, MVU Zod, and hybrid cards with required greetings and worldbooks, character design, player profiles and agency, optional character stages, portrayal diagnosis and corrections, worldbuilding, variables, and prompt routing. Use for new or inherited cards, standalone rolecard prompt rules, opening style, small in-card creative pieces, author-facing assessment, character material, worldbuilding, state systems, and field tracing. Route independent worldbook design and writing, packaging, exact APIs, live debugging, embedded UI implementation, and workshop infrastructure to their owning skills
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.