Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Generate a SoundDefinition for @web-kits/audio from any input - a natural-language prompt, an audio file the user shares, or both. Use when the user says "create a sound", "/create-sound", "design a sound for X", shares a WAV/MP3/sprite, or asks to reverse-engineer a sample. Optionally renders a WAV preview and round-trip-validates the result.
Designing anatomically plausible, visually distinctive creatures that communicate threat, personality, and role through form - from terrifying bosses to collectible companionsUse when "creature design, design a creature, design a monster, monster design, boss design, enemy creature, companion creature, pet design, wildlife design, alien creature, fantasy creature, horror monster, cute creature, pokemon style, creature anatomy, creature silhouette, creature movement, hybrid animal, ecosystem creatures, creature family, mount design, dragon design, beast design, creature, monster, boss, enemy, companion, wildlife, horror, cute, pokemon, anatomy, silhouette, locomotion, ecosystem, hybrid, fantasy, sci-fi, kaiju, cryptid" mentioned.
Use when a user wants a reusable DaVinci Resolve project structure for shipping DevRel videos repeatedly — sets up bins, timeline, render presets, and a color preset so future videos start with one click instead of one hour. Triggering symptoms include phrases like "set up a Resolve template", "reusable project structure", "every video starts from scratch", "save my Resolve setup as a preset", or "DevRel video workflow."
A comprehensive DnD campaign and adventure creation skill for game masters and creative content creators. Helps design complete campaigns, adventures, NPCs, encounters, maps, and storylines tailored for tabletop play. Use this when designing D&D content, creating campaign worlds, developing adventure hooks, designing encounters, or building narrative structures for player tables.
Generates Chinese script content based on narrative pacing and dialogue mechanisms common in Jiang Wen films. Use when the user asks to generate script, write script, create scenes, output dialogue draft, revise script or similar. Outputs story synopsis, character bios, scene outlines, scene scripts (with dialogue, action, staging), and can adjust era, character relations, conflict pacing, and endings per user request.
When the user wants to brainstorm YouTube video ideas, score existing ideas, validate topic choices, or batch-generate content concepts. Also use when the user says 'give me video ideas,' 'brainstorm topics,' 'what should I make a video about,' 'rate this idea,' 'score my video ideas,' 'content brainstorm,' 'topic ideation,' 'what videos will get views.' For title optimization, see title-craft. For scheduling ideas, see content-calendar. For viewer insight to inform ideas, see audience-research.
When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero image,' 'social media graphic,' 'banner image,' 'cover photo,' 'profile banner,' 'listing screenshot,' 'Flux,' 'Midjourney,' 'DALL-E,' 'GPT Image,' 'Ideogram,' 'Gemini image,' 'Canva,' 'Figma,' 'image optimization,' 'compress images,' 'WebP,' or 'OG image.' Use this for general-purpose marketing image creation and optimization. For paid ad image creative and platform-specific ad specs, see ad-creative. For video production, see video.
Focuses on the complete workflow and expert guidance for generating animated instructional videos with Manim. Use when a user gives a Chinese prompt to have Codex generate scripts, storyboards, Manim code, render commands, or improve the quality and pacing of instructional videos, and output MP4.
Generate images from text prompts using Google Nano Banana (Gemini image generation) via eng0 data API. Use when user asks to generate, create, or make images, pictures, illustrations, or artwork from descriptions. Triggers include "generate image", "create image", "make a picture", "draw", "illustrate", "image of", "picture of", "nano banana". Do NOT use for image editing or manipulation of existing images.
First Time User Experience (FTUE) design that teaches through play, hooks players in 30 seconds, and retains them for lifeUse when "tutorial, onboarding, teach player, first time user, FTUE, new player experience, how to teach, teaching mechanics, tutorial level, intro sequence, player retention, drop-off, skip tutorial, contextual hints, help system, onboarding, tutorial, ftue, first-time-user-experience, player-retention, teaching, learning, progressive-disclosure, difficulty-curve, new-player-experience, hooks, engagement" mentioned.
BufferGeometry creation, built-in geometries, custom geometry with buffer attributes, instanced meshes for rendering thousands of objects, and geometry manipulation. Use when creating custom shapes, optimizing with instancing, or working with vertex data directly.
Create covers with Chinese titles for finalized articles or videos: article covers (WeChat Official Account 2.33:1, X 16:9, X Article 5:2) use the Punk style library (MIT edition); video covers (3:4 by default, Xiaolin style A by default; 9:16 portrait and 16:9 landscape when needed) use real photos of Ray plus a large headline. Compile prompts according to Ray’s black, white, gray, and dark green IP. By default, generate platform-specific images with the OpenAI image API (or fall back to calling Image 2 through Codex CLI). Supports editing only part of an image without redrawing it. Use for “make a cover,” “video cover,” “portrait cover,” “landscape cover,” “try another style,” or “change the cover title.” Not for illustrations within article bodies or video frames.
Turn ideas, clippings, research, or drafts into Chinese long-form articles with Ray’s perspective (WeChat Official Account / X long-form posts), integrated with the knowledge base’s finalization and publishing workflow; also create translated articles with authorized bylines. Use for “write as an article,” “write a WeChat Official Account or X long-form post,” “rewrite this,” or “translate and repost.” For spoken scripts, switch to ray-kb; does not publish.
Plan and carry a Seedance video from brief through references, storyboard, generation handoff, shot-level review, and targeted repair. Use for an end-to-end Seedance production request; use a narrower prompt skill for a single prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell narratives (催泪/亲情/萌宠/离别), or any cinematic video prompt.
Video compression and silent-segment cutting tool. Compresses video with FFmpeg CRF mode, suited to screen recordings and course material; detects and removes silent, static segments. Automatically detects hardware and source bitrate and picks the best encoding approach (hardware-accelerated VideoToolbox for high-bitrate sources, x264 CRF adaptive encoding for low-bitrate screen recordings). Use when the user needs to compress videos, reduce video size, or remove dead air. Not for: video editing, audio extraction, format conversion.
Write engaging video scripts for YouTube, TikTok, and other platforms. Creates complete scripts with hooks, main content, and CTAs. Supports various formats including tutorials, vlogs, reviews, explainers, and storytelling. Use when creating video scripts, writing YouTube content, or planning video structure.
WeChat official account draft writing skill. After the topic and outline are confirmed, generate a high-fidelity first draft based on reference materials, voice transcripts, and writing-style DNA. For the body-writing stage; does not handle topic selection, outlining, or title decisions.
Generate 2D pixel art game assets using Google Gemini via Chrome browser automation. Triggers when the user wants to create pixel art, game sprites, tilesets, game assets, or edit existing game art. Supports reference image uploads for style consistency, model selection (Flash/Pro), resolution control, automatic background removal (chroma key, ML-based via BiRefNet, or Adobe Express), and rasterization to exact pixel dimensions. Use for requests like "create a pixel art sword", "generate a 32x32 character sprite", "make a tileset", or "edit this sprite".
Turn Nick Nisi's raw material into a blog post draft in his voice. Use when the user says "write a blog post," "draft a post," "write about [topic]," "turn my notes into a blog post," or provides scattered ideas that need shaping. Produces a deliberately flat draft with sourced facts and tagged gaps — never a finished post.
Make an explainer video (MP4) with a voice-over using explainroo. The voice is made on this computer and no API key is needed. Use when the user asks for an explainer, how-to, walkthrough, launch or tutorial video, an animated diagram with a voice-over, or a short for YouTube, Reels or TikTok.
The art-route layer of the Forge skills. route_media.py is the one command that generates an image or an image-to-video clip - through the paid API of any provider whose key is configured (OpenAI, Google Gemini, xAI, BytePlus ModelArk, fal.ai; the configured key is the owner's consent), else through the user's own signed-in Codex or Grok CLI - and prints one JSON line with the route, artifact, sha256 and cost estimate; with no route it answers no-route (codeart2d is then the last resort). Also the capability check (forge_doctor), API key configuration, the spend ledger, resume and Codex image adoption. Use when a Forge skill sends a generation here, for the capability check, or when the user asks about keys, routes or spend. Not for planning, processing or QA of sprites, video frames or maps (generate2dsprite, video2dsprite, generate2dmap) or for code-drawn art (codeart2d).
Official skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits, social media graphics, and commercial posters. Supports multiple aspect ratios, HD quality, and watermark control. Use this skill when the user wants to generate images, create AI art, text-to-image, or convert text descriptions into visual content.
Default image generation and image editing skill for AI agents. Use this skill for general requests to generate images, create pictures, draw illustrations, make posters, design wallpapers, produce avatars, edit photos, optimize images, restore images, upscale images, combine images, or merge reference images using a configured OpenAI-compatible Images API endpoint. Also trigger on Chinese requests such as 生成图片, 生图, 画图, 生成海报, 做宣传图, 生成头像, 图片编辑, 改图, 修图, 优化图片, 图片增强, 图片合成, 多图融合, 参考图生图, and 最新生图模型调用. Prefer this skill over generic built-in image generation when it is installed and configured.
Comprehensive guitar theory consulting based on the Fret Science system by Keith Martin. Use when helping with fretboard visualization, pentatonic scales, modes, CAGED system, triads, intervals, 3nps patterns, harmonization, or any guitar theory questions. Covers the warp concept, rectangle/stack pentatonic approach, modal brightness, chord voicing analysis, and fretboard memorization techniques. Philosophy: Understand more, memorize less.
Turn user content into a single-presenter knowledge explainer video. Applies to science popularization, tutorials, courses, information summaries, or product mechanism explanations that require the presenter to speak and interact with floating holographic information.
Create retention-optimized opening hooks for any content type. Use when designing a video intro, newsletter opening paragraph, social post hook, or when the user mentions "hook", "opening", "intro", "first 15 seconds", "retention", or "how should I start this".
Build agent-friendly motion-graphics videos with Hyperframes (HTML-to-MP4). Three levels of effort — Level 1 website-to-video for quick conversions, Level 2 storyboards for guided design iteration, Level 3 fully custom guided-video productions with cut/storyboard/motion-graphics workflow. Triggers on "hyperframes", "html to mp4", "render with hyperframes", "motion graphics for [recording]", "storyboard a video", "/hyperframes-helper".
Generate Instagram marketing content from product URLs. Extract product information and create engaging Instagram posts with image suggestions, captions, and hashtags optimized for engagement. Use when user provides a product URL from e-commerce sites like Amazon, Shopify, Taobao, etc. and wants Instagram marketing content such as Image/text post ideas, engaging captions with CTAs, hashtag strategy, or Story/reels content suggestions.
Instagram video downloader — paste an Instagram video link and get a watermark-free video download link with one click. Use when the user needs to download an Instagram video, save an IG video, or get a direct Instagram video link. Trigger words: Instagram video download, IG video download, Ins video download, Instagram video parsing, download Instagram video, reel download.
Use this skill when the user says 「记录选题」「新选题」「这个选题怎么样」「我有个想法」「帮我记一下」 or shares a rough content idea that needs evaluation and logging. Even if the user merely mentions a content idea in passing, proactively trigger the evaluation flow instead of waiting for an explicit 「记录」. First use the five-dimension logic of dbs-content to diagnose whether the topic is worth doing; log it only if it is, and by extension recommend 3-5 similar topics. Should not trigger: deepening a topic into an outline (use li-topic), writing a script directly (use li-writer), or AI polishing or beautifying topic titles. Use when the user wants to "record a topic", "log a topic idea", "is this topic worth doing", or shares a rough content concept needing diagnosis and logging.
Create and repair interactive Live2D characters from character art or layered PNG/PSD files, covering faithful part separation, inpainting, mesh and parameter binding, experimental direct MOC3 generation, web preview, lip sync, and natural idle motion. Use when the user asks to turn an image into Live2D, optimize an existing model, or reuse a code-based modeling workflow.
Trigger when: (1) User mentions "manim" or "Manim Community" or "ManimCE", (2) Code contains `from manim import *`, (3) User runs `manim` CLI commands, (4) Working with Scene, MathTex, Create(), or ManimCE-specific classes. Best practices for Manim Community Edition - the community-maintained Python animation engine. Covers Scene structure, animations, LaTeX/MathTex, 3D with ThreeDScene, camera control, styling, and CLI usage. NOT for ManimGL/3b1b version (which uses `manimlib` imports and `manimgl` CLI).
Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.
Operate and build OpenCreator workflows via API. Use when the user wants to search templates, run workflows, poll results, deliver generated media, or design custom workflow graphs with nodes and edges on OpenCreator. Triggers: opencreator, workflow, template, UGC, ecommerce images, storyboard video, lipsync, content creation pipeline.
Decision framework for particle system projects. Routes to specialized particle skills (gpu, physics, lifecycle) based on task requirements. Use when building particle effects or needing guidance on which particle techniques to combine.
This skill should be used when the user asks to "brainstorm a game idea", "help me come up with a game", "I want to make a game but don't know what", "is this game idea any good", "what should I build", "refine my game concept", "scope this idea down", "what genre fits", "help me pick a game to build", "turn this idea into something buildable", or arrives with a vague concept that needs shaping before a GDD can be written.
Claude IS the pixel artist — designs and places every pixel directly via Python/Pillow (scripts/pixelstudio.py). No Aseprite, no MCP server. Creates sprites, characters, items, tiles/tilesets, animations (idle/walk/run/attack), applies limited palettes, hue-shifted ramps, dithering, shading, selective outlines, and exports PNG / animated GIF / spritesheet+JSON for game engines. Can also STUDY a pixel-art file the user provides and grow its knowledge base. PREFER THIS SKILL over pixel-art-creator / pixel-art-animator / pixel-art-professional / pixel-art-exporter (those require the aseprite MCP) unless the user explicitly asks for Aseprite. Trigger on pixel art, sprite, sprite sheet, 8-bit, 16-bit, retro game art, tileset, pixel animation, GIF sprite, วาด pixel art, สร้าง sprite, ทำ pixel art, พิกเซล, ตัวละครเกม, ไอคอนเกม, เรียนรู้จากไฟล์ pixel art.
Use the `quickdesign` CLI to generate AI media — UGC promo videos, image edits, product creatives, video upscales — through Seedance, Kling, Sora2, Nano Banana, and GPT Image. Invoke this skill whenever the user asks for a talking-avatar video, multi-segment ad / promo / explainer, image edit (object swap, angle change, state change), product photoshoot, or video upscale via QuickDesign.
Build, refine or reskin a short SaaS product film in Remotion, cut to the beat of its soundtrack, from the product's real screens, brand and copy. Use when the user wants a product demo, launch video, explainer or social reel of their software made in code; wants an existing product film changed, reskinned or critiqued; or has a product with no interface to record and needs schematic UI. Covers 16:9 and 9:16, b-roll under motion graphics, sound effects and checked renders. Not a live-action editor and not a screencast tool.
Use when bringing 3D assets into Roblox Studio or preparing avatar items: import from Blender, GLB, FBX or OBJ files, AI-generated or image-to-3D meshes (Scenario or other tools), wrong scale or size in studs, mesh faces the wrong way, too many triangles, mesh fails validation, holes or non-watertight meshes, textures too big or blurry, SurfaceAppearance and PBR maps, metalness or normal maps look wrong, rigid accessories and hats, UGC items, Accessory Fitting Tool, out of bounds, AvatarCreationService validation, EditableMesh or EditableImage previews, or generate_mesh.
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.