Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Add sound effects, music, audio streaming, and video players to Decentraland scenes with AudioSource, AudioStream, and VideoPlayer. Use when the user wants sound, music, video screens, radio, live streams, or media playback. Do not use for player emotes (see player-avatar) or screen-space UI sounds (sounds attach to entities, not UI).
Apply the user's Chinese writing style when writing, translating, editing, proofreading, polishing, or publishing Chinese content, including blog posts, articles, subtitles, captions, tweets/X posts, threads, newsletters, and social posts. Enforce punctuation rules, especially Chinese curved quotes, halfwidth dash " - ", ASCII ellipsis "......", and no leftover fullwidth/English punctuation in Chinese body text
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.
Control camera behavior in Decentraland scenes. Covers CameraMode, CameraModeArea, VirtualCamera, MainCamera, and camera vs collider interactions. Use when the user wants camera control, cutscenes, forced camera modes, camera tracking, or a spectate / observer / replay / free-cam mode. Do NOT use for input restriction during cutscenes (see advanced-input for InputModifier) or cursor lock detection (see advanced-input for PointerLock).
Provides FFmpeg commands and filter recipes for video automation pipelines - format conversion, resizing, trimming, audio mixing, subtitles and overlays, slideshows, thumbnails, and encoding tuning. Use when the user asks to convert, trim, compress, mix, overlay, or burn text into media, generate thumbnails or slideshows, build a Ken Burns or social-media clip, or tune ffmpeg encoding parameters such as CRF, preset, faststart, or hardware acceleration.
Dynamic lighting and environment in Decentraland scenes. LightSource, shadows, SkyboxTime, realm detection, and emissive materials. Use when the user wants lights, shadows, skybox control, day-night cycle, or glowing materials. Do NOT use for PBR material properties like metallic/roughness (see advanced-rendering).
Craft highly effective prompts for Nano Banana Pro (Gemini image generation). Use when generating images with Nano Banana Pro for any purpose including photorealistic portraits, product photography, creative experiments, e-commerce mockups, social media content, editorial layouts, 3D renders, era-specific aesthetics (Y2K, 2000s, 1990s), miniature/diorama effects, or any advanced image generation task. Provides proven prompt patterns, technical specifications, JSON structuring, identity preservation techniques, and style-specific templates.
Strip the tells of AI-generated writing from prose so it reads like a person wrote it. Use when asked to humanize text, remove AI-isms, make writing sound less like ChatGPT, edit out “AI slop,” or review a draft for robotic phrasing without rewriting it. Covers em-dash overuse, puffery, filler, and AI vocabulary words
Direct and produce Chinese-first cinematic motion videos with HyperFrames. Use this skill when the user wants a rendered promo film, article-to-video piece, product launch film, website-to-video piece, keynote reveal, kinetic typography sequence, text/icon transition promo, music-synced motion graphic, HTML/CSS/SVG/GSAP video, short-form vertical video, or a landing page/product story turned into motion. Default to Simplified Chinese, vertical 9:16, and 1080x1920 unless the user or platform clearly requires another format. The skill enforces a two-phase workflow: brief first, confirmation second, then assets, composition, validation, snapshots, render, and review report
Write high-quality prompts for the multimodal AI video generation model Seedance 2.0 by 即梦. Trigger when users need to create video prompts using multimodal inputs such as text, images, video, or audio. Covers scenarios including @ reference syntax, camera movement replication, effects imitation, video extension and editing, music beat synchronization, e-commerce ads, short dramas, and science education.
Runs the owner's content operation as a standing process rather than a one-off: maintains a rolling posting calendar, learns the owner's voice, generates on-brand Canva graphics, writes captions in their voice, repurposes one asset for every channel format, and stages posts for approval instead of publishing on its own. Pulls product photos and prices from Shopify when connected; without connectors, drafts the calendar and asset briefs for manual posting. Use whenever the owner talks about posting, content, or social — including “I need to post more,” “we've gone quiet on Instagram,” “what should we post this month,” “make the content,” “give me a month of posts,” “write this in my voice,” “repurpose this,” or “set up our content calendar.” Use it for a single post as readily as for a full quarter. One handoff: a finished, approved campaign brief goes to canva-creator; this skill owns the ongoing operation.
AI design tool for viral WeChat Official Account covers. Based on 100,000+ articles collected daily across the web, it identifies visual elements from popular covers in the same niche, uses AI to analyze high-conversion visual patterns, and generates cover design concepts tailored to the article content and platform aesthetics. Use when designing WeChat Official Account covers, generating cover concepts, or researching patterns in popular covers. Trigger terms: WeChat Official Account cover, cover design, viral cover, cover concept, cover image generation.
Catch-all for anything CawCut-App related via the local `cawcut` CLI: running published Apps, and open-ended requests like "what can <app> do", "what does <app> generate", "what apps are there", "list official apps", browsing/listing available Apps, or checking an App's inputs/outputs. Use when: "/cawcut-app-run", "run my CawCut app", "invoke published app", "list available CawCut apps", "what apps are available", or the user describes a workflow/template-style creative request (ads, campaigns, multi-step templates) that may match a published app. Fetches the live App catalog and scores intent before routing; hands off simple one-step text-to-image/video or image-to-image/video generation with no App match to cawcut-generate, which will hand back here if it later finds a matching App. Requires `cawcut` installed and authenticated. NOT for: OAuth consent alone, or Apps the user cannot access. When unsure whether a request needs an App or raw generation, start here — this skill decides and delegates.
Generate images or videos via CawCut official node capabilities using the local `cawcut` CLI. Defaults: gpt-image-2 for image/edit; Seedance 2.0 for video when live discovery is unavailable. Use when: "generate an image", "make a video", "text-to-image", "text to image", "text-to-video", "text to video", "image-to-image", "image to image", "edit/stylize/remix this image", "image-to-video", "image to video", "animate this photo", "omni-to-video", "omni to video", "/cawcut-generate", or free-form content descriptions (e.g. "a cute little hedgehog"). Supports text-to-image, text-to-video, image-to-image, image-to-video, and omni-to-video. Checks the App catalog first; hands off to cawcut-app-run on a similar App match. Requires `cawcut` installed and `cawcut auth login` completed. NOT for: running an App already chosen (use cawcut-app-run), app discovery/browsing ("what apps are there", "what can an app generate"), OAuth setup alone, or Web UI-only flows without the CLI.
Create personalized live sports broadcast fan-cam videos with genmedia. Use this for realistic spectator cutaways, stadium or arena crowd reactions, broadcast screenshots, sports TV shots, scoreboard overlays, TV channel bugs, and identity-preserving fan reaction videos from a user photo
Create an art bible for an AI short drama (scenes + narrative props): scene design intent, consistency anchors, lighting and time-of-day variants, and empty-scene prompts; prop dramatic function, state variants, scale references, and white-background, no-hands prompts. Outputs art.json, Markdown, and a one-page review report (including exported JSON). Designed for AI generation, not live-action—the environments and props are generated assets, and the deliverable is a consistency plan to keep them looking the same across episodes. All 10 quality gates are checked deterministically by scripts (3–5 anchors, no people or hands, white background suitable for cutouts, scale phrases, English prompts…). If novel-outline has an outline.json, use seed to prefill the scene list and episode appearances. Zero dependencies, zero API keys, no image generation—the deliverable is prompts; image generation happens downstream. Use when asked for scene settings, scene generation, environment bibles, scene consistency, or scene bibles for AI short dramas.
Create NPCs (non-player characters) in Decentraland scenes. Two approaches: the NPC Toolkit library (dcl-npc-toolkit) for GLB NPCs with dialogue, movement, and state machines; and AvatarShape for avatar-look NPCs in wearables, including custom label plates above their name (AvatarNametag). Use when the user wants to add an NPC, shopkeeper, or quest giver—any non-player entity with behavior or dialogue. For live player data (position, profile, wearables), see player-avatar instead
Use this skill when the user asks to create custom Remotion transitions, asks about “cool transitions,” “cinematic transitions,” “striped transitions,” “glitch transitions,” “custom TransitionPresentation,” or wants to build scene-to-scene transitions in Remotion beyond the built-in library. Also triggers for “how to make transitions in Remotion,” “custom transition,” “high-energy transitions,” “energy transitions,” “branded transitions.”
Route design-generation work into the right Open Design workflow mode — prototype, deck, document, or media artifact. Use when the user needs local-first UI prototype generation, presentation deck creation, or design-system-aware HTML/PDF/PPTX artifacts via locally-installed coding agents. Supports 72 built-in design systems, 5 visual directions, 93 media prompt templates, and multi-format export. Triggers on: open-design, local design tool, prototype generation, design deck, design artifact, design agent workflow, open design prototype, design system artifact, UI prototype generation.
Emit particles (fire, smoke, snow, fireworks, magic, trails) from an entity in a Decentraland SDK7 scene with the ParticleSystem component. Do NOT use for procedural entity motion (see animations-tweens), GLTF model effects (see add-3d-models), or 2D UI effects (see build-ui).
Video downloading, stitching, title slides, and YouTube descriptions. Use this skill when downloading videos from Google Drive, creating title slides, stitching multiple videos together, or generating YouTube descriptions with timestamps. Triggers on video course creation, video editing, video compilation, or YouTube upload preparation.
Provider-independent audio mixing and mastering direction for AI agents finishing generated videos, ads, trailers, explainers, podcasts, recuts, avatar clips, music videos, documentaries, and social content. Use when planning, mixing, repairing, mastering, QCing, or delivering dialogue, music, ambience, and sound effects, including loudness/true-peak targets, intelligibility, accessibility, stems, stereo/immersive decisions, platform/client specs, and final audio QA
Interactive design consultant for Roblox objects. Use when the user's request is abstract or lacks structural details. This agent specializes in extracting requirements through dialogue BEFORE any implementation begins. Triggers on: abstract requests like "make a kitchen", "build something cool", or when building-3d-objects detects fatal ambiguity.
Generate images and text via Doubao Web using browser cookies and Playwright UI automation. Use when a user asks for Doubao Web image generation, prompt-to-image automation, text replies, preset aspect ratios (e.g. 小红书封面), or session-based multi-turn workflows.
Starting from a tweet, read related content in depth and turn it into an original sharing post. This is not translation; it involves learning and expressing the ideas in your own words. Use when a user provides tweet URL(s) and wants to create an original post based on the content. Triggers on "帮我整理这条推", "写一条分享帖", "tweet insight", "digest this tweet", or when a user provides x.com/twitter.com URLs and asks to write about them.
Use when setting up URP (or choosing URP vs HDRP), configuring URP assets and quality tiers for PC and phones, lighting a stylized or realistic Unity scene (sun, sky, baked or mixed lightmaps, Shadowmask, Adaptive Probe Volumes, reflection probes), or fixing blurry shadows, light leaks, gray bakes, washed-out images, tonemapping and grading, bloom too expensive on mobile, TAA, STP or MSAA choices, GPU Resident Drawer setup, shader warm-up hitches, or a custom shader that vanished or lost its baked light.
Use when making or fixing real-time VFX in Unity 6.3: explosions, fireballs, projectiles with muzzle, trail and impact, spells, slashes, shockwaves, smoke, sparks, Particle System (Shuriken) or VFX Graph ('VFX Graph explosion', 'particles look bad', 'effect kills fps on mobile', 'too much overdraw'), mesh effects with scrolling textures, an uber VFX shader with LUT ramps, Custom Data and custom vertex streams, flipbooks and VFX textures, pink particles after URP upgrade, VFX budgets and readability.
Generate reference-based videos with Alibaba Cloud Model Studio Wan R2V models (wan2.6-r2v-flash, wan2.6-r2v). Use when creating multi-shot videos from reference video/image material, preserving character style, or documenting reference-to-video request/response flows.
Sun Yuchen (Justin Sun / Sun Ge)'s thinking framework and behavioral logic. Deeply distilled from 1,500+ lines of research across six dimensions (works, in-depth interviews, expression DNA, others' perspectives, decision records, and timeline), yielding six core mental models, eight decision heuristics, five signature phrasing formulas, and a complete expression DNA. Use as a thinking consultant to analyze marketing strategies, the attention economy, crisis PR, narrative manipulation, and methods for riding trends from Sun Yuchen's perspective. Strongly in-character roleplay—arrogant, provocative, confrontational, numerically bombastic, with a success-culture undertone. Trigger when users mention “用孙宇晨的视角,” “孙割会怎么做,” “孙宇晨模式,” “Justin Sun perspective,” or “割神.” Also trigger for requests like “帮我用孙割的角度想想,” “如果孙宇晨会怎么操作,” “切换到割神,” or “用割的视角.”
Generate images with Alibaba Cloud Model Studio Z-Image Turbo (z-image-turbo) via DashScope multimodal-generation API. Use when creating text-to-image outputs, controlling size/seed/prompt_extend, or documenting request/response mapping for Z-Image.
Use when a Unity 6.3 URP task involves shaders: hand-written HLSL, Shader Graph water, toon, dissolve or outline, Custom Function nodes, a renderer feature or full-screen effect on Render Graph, compute shaders, shader variants, keywords, stripping, Shader Build Settings, PSO warm-up, or shader cost; or when a material turns pink or invisible, casts no shadow, ignores extra lights under Forward+, an effect 'does nothing', the game stutters the first time something appears, or builds bloat with variants.
Generate crisp, high-quality images with perfect typography and precise geometric layouts using HTML/CSS. Use when creating social cards, diagrams, certificates, UI mockups, code screenshots, or any image requiring sharp text rendering, exact alignment, or vector-like precision. AI excels at designing symmetric, pixel-perfect layouts as HTML rather than generating raster images directly. Supports Tailwind CSS, Google Fonts, icon libraries, and any web-based design resource.
Manage Alibaba Cloud AIContent (AiContent) via OpenAPI/SDK. Use whenever the user needs AI content generation or content workflow operations in Alibaba Cloud, including listing assets, creating/updating generation configurations, checking task status, or troubleshooting failed content jobs.
Generate or edit images with GPT Image 2.5 through Codex/ChatGPT subscription authentication instead of OPENAI_API_KEY. Use for text-to-image, reference-image editing, or visual assets when the user wants local Codex auth, especially when no native image tool is available. Do not use for official OpenAI API-key billing or OpenAI-compatible gateways.
Use this skill when the user asks about “pantsing,” “discovery write,” “write without an outline,” “discovery draft,” “write into the dark,” “story kernel,” “reconcile a chapter,” “dead end,” “drafting sprint,” or “writing cadence,” or wants to draft a story by discovery with retrospective bible reconciliation. NOT for outline-first drafting, mysteries and other clue-dependent genres where setup must come before payoff (use chapter-writing), reverse outlining an existing linear draft, cutting a subplot, or another revision pass on existing chapters (use revision-continuity).
Use this skill when the user asks to "process beta reader feedback", "alpha reader feedback", "feedback round", "synthesize reader feedback", "reader notes", "beta feedback", "reader readiness check", "review copy", "send the draft to readers", "share with readers who don't use GitHub", "triage the reader panel", or wants to collect, reconcile, and act on external reader feedback for a story project. NOT for running the simulated reader panel itself (use reader-panel), rounds with a professional editor (use editorial-review), or for checking a manuscript is ready to query or publish (use submission or publishing)
Fictional Fengge Wangmingtianya perspective: comments on relationship, workplace, and life concerns in a style blending wandering-jianghu themes, realist disenchantment, and dark humor. Favors “conclusion first, then plainspoken explanation” and reframing bad things as good, while refusing sensitive requests involving privacy, defamation, cyberbullying, illegal acts, or explicit sexual content without breaking character. For users asking for answers “in Fengge Wangmingtianya’s style,” “in Fengge’s style,” or “from the Wangmingtianya perspective,” or wanting jianghu-flavored jokes or travel narration. Triggers: Fengge Wangmingtianya, Fengge, Wangmingtianya, “in Fengge’s style,” “from Fengge’s perspective.”
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.