Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Advanced animation in Unity: Animator, IK, Root Motion, Timeline, Playables API, Animation Rigging, blend trees. Triggers: /anim, /animation, 'Animator avance', 'IK', 'Root Motion', 'Timeline', 'Playables API', 'Animation Rigging', 'blend tree', 'state machine animation', 'animation events'.
Complete Unity 6+ audio system: SFX, music, ambience, 3D spatialization, AudioMixer, pooling, Audio Random Container, Scriptable Audio Pipeline. Triggers: /unity-audio, /audio, audio, son, musique, AudioMixer, AudioSource, spatial audio, 3D sound, sound design, SFX
Get finished MP4 videos ready to post, without touching a single slider. Upload your images or clips (MP4, MOV, JPG, PNG, up to 500MB), say something like "combine these photos into a 30-second promo video with background music and text overlays", and download 1080p MP4 when it's done. Built for content creators and marketers who move fast and want to produce videos quickly without editing software experience.
Turns raw 9:16 talking-head clips into a finished, premium Instagram reel end to end: picks the cleanest take of every line across your clips, cuts dead air, punches in from 4K, cuts you out of the background for words behind your head, applies one of three designed looks (bold kinetic words, cool girl, cool dude), builds animated UI inserts with parallel sub-agents, adds subtle sound design, and checks every cut frame by frame inside the Reels safe zone. Trigger with /video-edit or phrases like 'edit these clips', 'I dropped clips in my downloads', 'cut this into a reel', 'make this reel look fire'.
Edit raw video footage into edited video files with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. Content creators and marketers use it for automatically editing raw footage into a polished final video — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Install and drive Motion Previs Studio v4 from the `video-motion-previs` CLI to turn reference video into pose, depth, camera-motion, control-layer, and AI-video/Blender production packs. Use when an agent must check or install the desktop app, import and trim a shot, run motion analysis, export a bundle, inspect its files, capture the app, or send a layer to Blockout. Triggers on: Motion Previs Studio, video motion previs, camera solve, pose extraction, OpenPose BODY_25, depth control video, production pack, motion-previs MCP.
Skip the learning curve of professional editing software. Describe what you want — trim the intro, cut the dead air in the middle, and export a clean 3-minute clip — and get trimmed video clips back in 30-60 seconds. Upload MP4, MOV, AVI, WebM files up to 500MB, and the AI handles AI video trimming automatically. Ideal for content creators and marketers who want quick precise trims without learning Adobe Premiere.
Unified YouTube script creation for cardiology channels in Hinglish. Uses the COMPLETE research-engine pipeline (channel scraping, comment analysis, narrative monitoring, gap finding, view prediction) combined with RAG + PubMed for evidence. Data-driven topic selection, 15-30 min educational videos with 6-point voice check.
Apply an evidence-derived Action continuity choreography workflow observed across published GoodCase examples by haruuraeadss. Use when planning, storyboarding, or refining an AI video prompt in this motion pattern, including requests for 视频提示词, 分镜, 动作复刻, reference images, source video, or special generation steps. This is an unofficial synthesis and must preserve source attribution.
Remote-control Affinity (the unified Affinity by Canva app: vector, pixel, and layout studios) with JavaScript through its local automation endpoint — no MCP client configuration needed. Automate document edits, batch operations, text/layer manipulation, and reusable library scripts, with rendered-JPEG visual verification. Use whenever the user wants to script or automate Affinity, programmatically edit .af / .afdesign / .afphoto / .afpub documents, batch-process designs, or says "Affinity", "Affinity script", "automate Affinity", "batch edit in Affinity", "control Affinity" — even if they don''t mention scripting.
Agent-first media toolkit for image, video, and audio processing. Use when you need to resize, convert, generate, edit, upscale images, remove backgrounds, extend or crop canvases, extract audio, transcribe speech, or generate videos. All commands return deterministic JSON output.
Skip the learning curve of professional editing software. Describe what you want — animate this image into a 5-second video clip with smooth motion — and get animated video clips back in 30-90 seconds. Upload JPG, PNG, WEBP, BMP files up to 200MB, and the AI handles AI video generation automatically. Ideal for AI enthusiasts, content creators, developers who want to animate images into videos without coding or running local models.
Get auto-edited videos ready to post, without touching a single slider. Upload your raw video footage (MP4, MOV, AVI, WebM, up to 500MB), say something like "automatically cut dead air, add transitions, and sync background music", and download 1080p MP4 when it's done. Built for content creators and marketers who move fast and want quick professional edits without learning complex editing software.
Skip the learning curve of professional editing software. Describe what you want — trim the pauses, add transitions, and export as a clean final video — and get AI-edited video clips back in 1-2 minutes. Upload MP4, MOV, AVI, WebM files up to 500MB, and the AI handles AI-powered video editing automatically. Ideal for content creators and marketers who want to edit videos using simple text commands without learning complex software.
edit raw video footage into edited MP4 clips with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators and social media users use it for automatically editing raw footage into polished videos — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Volcengine Ark image/video generation and editing entry point, including follow-up modifications to delivered media and acceptance checks against retained specifications. Supports profile default resources and temporary API Key/Base URL/Endpoint; an explicit Endpoint is not overridden by the current plan profile. Images return synchronously; videos are polled asynchronously.
Creates beautiful ASCII art visualizations for plans, architectures, workflows, and data. This skill should be used when explaining system architecture, creating implementation plans, showing workflows, visualizing comparisons, or documenting file structures. NOT for code syntax highlighting or markdown tables. User explicitly loves ASCII art - use liberally for visual communication.
Turn a 2-minute unedited phone recording into 1080p polished edited clips just by typing what you need. Whether it's editing raw footage into a clean, shareable video or quick social content, drop your raw video clips and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
Remote-control a running Blender by Python script through a small local bridge — build and edit 3D scenes live: mesh and curve modeling with bmesh and modifiers, materials and shader node graphs, geometry nodes, lighting and cameras, keyframe animation, rigging, physics simulation, Grease Pencil, the video sequencer, and EEVEE/Cycles rendering, then measure the result, grab viewport screenshots, and export glTF / FBX / USD / Alembic / OBJ / STL. Use whenever the user wants to create or edit a 3D scene, model, animation, product shot, or .blend file, render an image or video, convert or export a 3D asset, or says "Blender", "3D model", "render this", "make a 3D animation", "Blender scene", "export to glTF" — even if they don't mention scripting.
The art and science of narrative-driven brand communication. This skill transforms brand messages into compelling stories that connect emotionally, build memory, and drive action. In a world of infinite content, story is the only thing that cuts through. Great brands don't sell products—they tell stories. Apple tells the story of creative rebels. Nike tells the story of human potential. Patagonia tells the story of environmental stewardship. This skill teaches you to find, craft, and tell your brand's story across every touchpoint. AI amplifies storytelling capability—generating variations, adapting across channels, maintaining consistency—but the human insight that identifies the true story remains essential. This skill bridges narrative craft with AI execution. Use when "story, storytelling, narrative, brand story, origin story, hero journey, emotional connection, customer story, testimonial, case study, brand film, about us, storytelling, narrative, brand-story, emotional, hero-journey, content" mentioned.
Pilot a spatial canvas from the CLI — create canvases, generate images/text/video/agent responses, read results, recall past work, and manage nodes. The canvas is a shared workspace visible in the browser; this skill gives you a live cursor on it. Use this skill whenever the user wants to interact with the canvas platform, asks to generate images or videos on canvas, mentions "canvas", "Neo", "Agent Neo", wants to draw/create/generate visual content on the spatial canvas, references past canvas work, or says anything that implies operating on the canvas. Also triggers on /canvas-pilot.
Translate a story or character and scene assets into cinematic single frames, triptychs, or nine-shot storyboards, and write executable video action, camera movement, and editing prompts for each shot as needed. Use for cinematic stills, continuous storyboards, spatial reconstruction of assets, and storyboard-to-video prompts; when the user only wants prompts, do not generate media automatically.
Color grade clips the way a professional colorist does — normalize, balance, match, then build a look — using inspect_color scopes and apply_color (exposure, white balance, wheels, curves, hue curves, LUTs). Use when the user asks to color, grade, match shots, fix white balance, fix exposure, neutralize a cast, or apply a look/film stock.
Turn a 2-minute screen recording or phone clip into 1080p polished creator videos just by typing what you need. Whether it's turning raw footage into shareable creator content 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.
Source b-roll for a video edit — classify each moment, scope the search, return vetted candidates, place on the word. Use when the user says "find b-roll", "/find-broll", "source clips for this edit", or wants footage/memes/screenshots to lay over a talking-head video.
Skip the learning curve of professional editing software. Describe what you want — create a 30-second video from this text: 'Introducing our new coffee blend — rich, smooth, and ethically sourced.' — and get ready-to-share videos back in 1-2 minutes. Upload TXT, DOCX, PDF, plain text files up to 500MB, and the AI handles AI video creation automatically. Ideal for marketers, content creators, small business owners who want videos without cameras, actors, or editing software.
Get animated personalized videos ready to post, without touching a single slider. Upload your photos or clips (JPG, PNG, MP4, MOV, up to 200MB), say something like "turn my photos into a funny animated video with dancing characters and music", and download 1080p MP4 when it's done. Built for casual users and families who move fast and want to make funny personalized videos without design skills.
Use for game development tasks: new games, gameplay design, features, fixes, and playtesting. Research comparable games before choosing new mechanics, inspect actual gameplay, and verify changes by playing through real controls. Keep small fixes within the existing design.
Guo Degang's thinking framework and way of expression. Based on deep research across 9 dimensions (including original-text analysis of 3 first-hand works plus 6 dimensions of web research) and 80+ first- and second-hand sources, distilled into 6 core mental models, 10 decision heuristics, and a complete expression DNA. Purpose: to serve as a thinking advisor, analyzing problems, reviewing decisions, and providing feedback from Guo Degang's perspective. Use when the user mentions "from Guo Degang's perspective", "what would Guo Degang think", "Guo Degang mode", or "guodegang perspective". It should also trigger even if the user only says "help me think from Lao Guo's angle", "what would Guo Degang do", or "switch to Guo Degang".
enhance raw video footage into enhanced video files with this skill. Works with MP4, MOV, AVI, WebM files up to 500MB. content creators use it for improving low-quality or shaky footage with AI upscaling and correction — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Write prose that sounds authentically human rather than AI-generated. Use this skill whenever writing long-form content, emails, articles, reports, documentation, blog posts, creative writing, social media copy, proposals, memos, or any text where sounding like a real person matters. Triggers on requests like "write this naturally," "make it sound human," "don't sound like AI," "write like a real person," or any writing task where the user has indicated they want authentic, non-robotic prose. Also use when editing existing text to remove AI-sounding patterns.
Validate whether two raster image layers are suitable for reveal, before/after, morph, mask-compositing, or interactive cursor reveal effects. Use when comparing base/reveal images, checking whether the main subject stayed in the same position, separating primary subject drift from background or secondary-object differences, producing annotated overlays/difference maps, or deciding whether an image layer must be shifted, scaled, cropped, or regenerated before frontend compositing.
Get animated video clips ready to post, without touching a single slider. Upload your still images (JPG, PNG, WEBP, HEIC, up to 200MB), say something like "animate this photo into a short kissing scene with natural movement", and download 1080p MP4 when it's done. Built for content creators who move fast and want to bring still photos to life with realistic motion and emotion.
Use this skill when the user says 「获取逐字稿」「转录视频」「提取文稿」「帮我扒一下」「这个视频说了什么」「这个博主说了啥」, or gives a video link and asks to extract its content. Even if the user just drops a video link without saying what for, trigger it proactively as long as the context involves benchmark analysis or content extraction. It calls video2text.py to get the raw transcript, an AI proofreads common speech recognition errors, and after identifying the author it archives to the benchmark blogger directory. Do not trigger for: analyzing viral patterns (use li-analyzer), recording your own topic ideas (use li-recorder), writing your own scripts (use li-writer). Use when the user wants to "get transcript", "transcribe video", "extract script", or gives a video link for content extraction. Runs speech-to-text, AI proofreads, and archives to benchmark blogger directory.
Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template phrases, transition word density, sentence uniformity, paragraph pattern repetition, and other signals that WeChat uses to flag AI content. Outputs a risk report and an optional humanized rewrite. Use when the user wants to check if an article looks AI-generated, make an article more human-like, bypass WeChat AI detection, or humanize AI-written content. Also trigger when the user mentions "去AI痕迹", "人性化润色", "微信AI检测", "anti-ai-check", "humanize article", "公众号发文检查".
Guide authoring of Audio Toolbox plugins (audioPlugin, audioPluginSource) that pass validateAudioPlugin and generate deployable VST/AU code. Use when creating audio effect or generator plugins, writing classdef files inheriting from audioPlugin, or troubleshooting validateAudioPlugin failures.
Create Minecraft 3D models (Java/Bedrock) — generate a vanilla-Minecraft design and three-view reference with an image model, then build, texture, and animate the model directly in Blockbench through the Blockbench MCP server. Use when the user asks to 做一个 Minecraft 模型 / 生成一格 XXX / 把设计图或三视图建成 Blockbench 模型 / 给模组或资源包添加模型, or any request where a 3D model should be created or edited in Blockbench. Assumes Blockbench MCP is installed and running; if the MCP tools are unavailable, remind the user to install and start Blockbench MCP first.
Get kid-friendly movies ready to post, without touching a single slider. Upload your images or video clips (MP4, MOV, JPG, PNG, up to 200MB), say something like "turn my pictures into a short movie with music and fun text", and download 720p MP4 when it's done. Built for kids and parents who move fast and want to make fun videos without complicated software.
Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Flux Kontext / Nano Banana 2 t2i instead. Calls `runcomfy run google/nano-banana-2/edit` through the local RunComfy CLI. Triggers on "nano banana edit", "edit with nano banana", "image edit nano banana", or any explicit ask to edit with this model
Generate slide decks, audio podcasts, infographics, and video overviews from NotebookLM notebooks. Customizable by audience, format, language (80+), orientation, and visual themes. Use when asked to generate slides, create podcast, make infographic, video overview, or automate NotebookLM content creation.
This skill should be used when the user asks to "写小说", "创作小说", "写长篇", "继续写", "更新文章", "写大纲", "设计人物", "写角色", "下一章", "展开写", "帮我写故事", "搜索素材", "生成插图", or discusses novel creation, story outlines, character design, chapter writing, serial fiction workflows, or novel illustration.
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.