Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Develop an independent visual language and turn the human-chosen direction into a production-ready graphic, brand, campaign, publication, web, or product system. Use when originality and differentiation matter enough to escape generic AI and Big Tech aesthetics. Guides a minimum-evidence start, ten isolated typography-led HTML design directions made only from type, color, and space, visual-first human judgement, explicit commitment, and concrete Round 2 production. Do not use for routine UI fixes, small components, or applying an existing design system.
Write game shaders from cross-engine fundamentals — the vertex→fragment pipeline, coordinate spaces, UV math, and common 2D/3D effects (tint, UV scroll, dissolve, outline, fresnel rim, vignette) in GLSL with HLSL equivalents. Use when the user mentions shaders, fragment/pixel shader, vertex shader, UV, GLSL, HLSL, or effects like dissolve, outline, or rim light.
Build branching dialogue and narrative — a node/choice graph with conditions, variables, and localization hooks — and choose between authoring tools Ink and Yarn Spinner or a custom data-driven runner. Engine-neutral. Use when the user mentions dialogue system, branching dialogue, conversation tree, choices, Ink (.ink), Yarn Spinner (.yarn), or NPC dialogue.
MSW (MapleStory Worlds) game-planning mode — for BOTH starting a brand-new game from scratch AND continuing/resuming an in-progress prototype. Narrow the idea with guided questions, ground it in the MSW genre catalog (3 map types, ~180 core mechanic tags, build-effort hints), and produce or advance an implementation-ready GDD / roadmap (markdown). Trigger proactively (even without the word 'planning') whenever the user wants to decide WHAT to build, scope an MVP, or continue/resume a phased build — INCLUDING when a Docs/*-GDD.md or *-Phase*.md already exists and the user says to continue: do NOT treat that as plain implementation and jump straight into the phase doc; a continue/resume runs through this skill's resume flow first. Match triggers by intent, not exact wording — variants like 'what now?', 'where were we?', and their equivalents in ANY language fire it too. A comprehensive build request spanning multiple implementation pieces, made while no GDD exists, is ALSO a planning trigger — not a plain implementation request, with NO 'small/simple game' exception; implementing that without a plan is the exact failure mode this skill prevents. Triggers: 'plan a new game', 'GDD', 'what game should I make', 'scope an MVP', 'planning mode', 'continue my game', 'resume my game', 'what should I work on next', 'next task'. (Plans & manages the game's build across its milestones — GDD · standing milestone roadmap · phase plans · progress · revisions; does NOT write code — implementation (.mlua/.model etc.) uses msw-general/msw-scripting.)
Animate in Godot 4.7 in three ways: AnimationPlayer for keyframed clips (including call and signal tracks), AnimationTree with state machines and blend spaces for character animation, and Tween for short procedural/UI tweens via create_tween(). Use when working with AnimationPlayer/AnimationTree nodes in a .tscn, blending character states, sprite-sheet animation, or code-driven Tweens.
Write Godot 4.7 shaders in the Godot Shading Language: canvas_item shaders for 2D and spatial shaders for 3D, with vertex/fragment functions, uniforms (source_color, hint_range), TIME/UV animation, and screen-reading via hint_screen_texture. Use when authoring .gdshader files, writing fragment/vertex code, making 2D/3D visual effects, or porting 3.x shaders (SCREEN_TEXTURE, hint_color) to 4.x.
Query work/account data from links or share text on platforms such as Douyin, Xiaohongshu, and WeChat Channels, and extract voice transcripts, archiving them as Markdown by author and title. Use when the user asks to parse a platform video or obtain data or transcripts; requires TikHub and 轻抖 credentials, and does not cover local chapter navigation or navigation video rendering.
Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API. Use when cleaning up noisy recordings, removing music or background ambience from dialogue, isolating speech from field recordings, preparing audio for transcription, extracting vocals, or any "denoise / clean up / isolate voice" task.
Content caster (铸). Transforms text into PNG through precise HTML typography and, when the mold needs it, generated raster imagery. Four molds: -l (default) long reading card, -f source-faithful full text, -c comic, -w whiteboard. USE WHEN user says '铸', 'cast', '做成图', '做成卡片', '做成海报', '原文排版', '全文卡片', '漫画', or '白板'.
Play and mix audio in Godot 4.7: AudioStreamPlayer (2D/3D variants), audio buses with volume/mute and effects, music vs SFX routing, db/linear volume, and precise sync-to-beat playback timing. Use when playing sounds or music in a Godot project, routing AudioStreamPlayer nodes to buses, adjusting bus volume via AudioServer, or syncing gameplay to the beat.
Set up a Godot 4.7 3D scene: Node3D transforms, Camera3D, lighting (DirectionalLight3D/OmniLight3D), WorldEnvironment for sky/ambient/tonemap/post, MeshInstance3D materials, and GridMap for tile-based 3D levels. Use when building a 3D scene in a Godot project, placing cameras/lights, configuring environment and post-processing, or working with Node3D/.tscn 3D content and GridMap.
One topic, one roundtable: a host invites 3–5 real people, sets the opening, and moderates round-by-round exchanges, capturing an ASCII structure diagram each round. The user controls the pace with commands (go / stop / go deeper on this section / introduce a new person). Afterward, the full text is saved in a Markdown note. Use when the user says “圆桌讨论”, “圆桌”, “roundtable”, “辩论”, or wants to explore a topic through structured debate from multiple perspectives.
Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer (speech-to-speech) API. Use when converting one voice to another, changing the speaker/narrator of an existing recording, dubbing a voice-over in a different voice, creating character voices from a scratch performance, anonymizing a speaker, or any "voice conversion / voice transfer / speech-to-speech" task. Make sure to use this skill whenever the user mentions voice changing, voice conversion, speech-to-speech, swapping a voice in audio, re-voicing a clip, or applying a different voice to an existing recording - even if they don't explicitly say "voice changer". Do not use this skill to create or clone a new voice from a voice sample - that is voice cloning (IVC/PVC), a separate feature; this skill only converts an existing recording into an existing voice_id
Writing engine. Turns an idea into a 1000-1500 character Chinese article that is understandable, transferable, and stands up to counterexamples. Use when writing articles, refining thought content, developing an argument, or rewriting into logically progressive Chinese. Not for ordinary summaries, fact lookups, or structure drills (use ljg-structure).
Use when the user asks to write a novel, create a story, write chapter by chapter, develop an ongoing plot or a long-form novel, or continue or validate an unfinished novel project. Supports Chinese-language writing across genres, including mystery, romance, fantasy, science fiction, and historical fiction.
Drive Unity 6.3 LTS character animation with Animator Controllers: states, transitions, parameters, blend trees, animation layers, and humanoid Avatar IK. Use when wiring an Animator, setting parameters from script (SetFloat/SetBool/SetTrigger), building blend trees, or when the user mentions Animator, Mecanim, state machine, blend tree, or .controller.
Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o image
Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative
Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capabilities: text-to-image, image editing, LoRA styles, multi-image compositing, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna, p-image, pruna image, fast image generation, optimized flux, pruna ai, p image, fast ai image, economic image generation, cheap image generation
Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI. Models: HappyHorse T2V, I2V, R2V, Video Edit. Capabilities: text-to-video, image-to-video, reference-to-video, video editing with natural language, character preservation, 720P/1080P, up to 15 seconds. Use for: physically realistic video, video editing, character-consistent content, product demos, social media. Triggers: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba happyhorse, video editing ai, ai video editor
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio
Load glTF/GLB models in three.js with GLTFLoader and play their skinned animations with AnimationMixer, including DRACO/Meshopt-compressed meshes and KTX2 textures. Use when importing 3D models into three.js — when the user mentions glTF, GLB, GLTFLoader, AnimationMixer, animation clips, DRACOLoader, or "load a 3D model". For scene/camera/renderer setup use threejs-scene-setup; for materials and lights use threejs-materials-lighting.
Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when the user mentions “小红书图片”, “小红书种草”, “小绿书”, “微信图文”, “微信贴图”, “image cards”, “图片卡片”, or wants a social media infographic series.
AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires the banana extension installed. Use when user says "generate image", "OG image", "social preview", "hero image", "blog image", "product photo", "infographic", "seo image", "create visual", "image-gen", "favicon", "schema image", "pinterest pin", "generate visual", "banner", or "thumbnail".
Light and shade a three.js scene: choose materials (MeshStandardMaterial PBR vs unlit MeshBasicMaterial), add ambient/hemisphere/directional/point/spot lights, turn on shadow maps, and use an environment map (IBL) for realistic reflections. Use when a three.js model looks black, flat, or wrong — when the user mentions three.js materials, MeshStandardMaterial, lights, shadows, envMap, or PBR. For renderer/loop setup use threejs-scene-setup; for loading models use threejs-gltf-loading.
Build and script 2D tilemaps in Unity 6.3 LTS: the Grid + Tilemap components, the Tile Palette, tilemap colliders, rule tiles, and runtime SetTile/GetTile painting. Use when painting tile levels, adding a TilemapCollider2D, using rule or animated tiles, generating tilemaps from code, or when the user mentions Unity tilemap, tile palette, rule tile, or Grid.
Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.
Turn an article or spoken script into a click-driven 16:9 web presentation that “looks like a video,” with optional synthesized narration. Workflow: source article → **produce once** a narration script + outline development plan → user **aligns once** on 5 items (script / outline / theme / assets / development mode) → web development (chapter-by-chapter / sequential / parallel) → optional audio synthesis (provider-agnostic: built-in MiniMax mmx-cli + OpenAI TTS, switchable to ElevenLabs / edge-tts / Azure / your own TTS). **The outline plans pacing and information density only, not animation** — animations are designed on the fly during chapter development according to PRINCIPLES + ANTI-AI rules. Each click advances one beat of the narration script; each step occupies the full screen; the progress bar stays hidden except on hover. Use cases: making a video with a web page (dynamic PPT but not like PPT), turning a spoken script / article into an interactive explainer, recording screen-capture tutorials for Bilibili / YouTube / Channels, and creating cinematic product / talk demos. This Skill captures a design methodology + collaboration workflow — it is not tied to any particular style / font / color — so it can be reused for any theme or aesthetic.
Rewrites Korean text that sounds AI-generated into natural human writing. Detects translationese, AI clichés, excessive nominalization and passive voice, the rule of three, exaggerated significance, formulaic conclusions, chatbot residue, and Korean-specific AI tells such as dashes and curly quotation marks; classifies them by severity (S1/S2/S3) and rewrites while preserving meaning. If you provide a target length (e.g. "1000 characters", length=1000), it expands or shortens the text accordingly. Use for requests like "make it sound less AI-generated," "make it sound human," "polish it naturally," "fix translationese," "fix awkward phrasing," or "adjust it to N characters."
Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image
Image generation and editing skill for GPT Image 2. Available in 3 environments: (A) Garden local mode, which generates images directly through an OpenAI-compatible interface and saves them to disk; (B) Host-Native mode, which uses this Skill as prompt-engineering guidance and passes the rendered prompt to the host Agent’s built-in image tool; (C) Advisor mode, which becomes a high-quality prompt advisor when the host has no image tools. Includes 80+ structured templates across 18 categories, covering posters, UI, products, infographics, academic illustrations, technical architecture diagrams, comics, avatars, storyboards, film storyboards, IP merchandise, and editorial workflows.
Create video ads to exact platform specifications for TikTok, Instagram, YouTube, Facebook, and LinkedIn. Covers dimensions, duration limits, the AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, TikTok ad, Instagram ad, YouTube ad, Facebook ad, LinkedIn ad, video creative, ad specs, paid media, video marketing, ad production, Reels ad, Stories ad, pre-roll, bumper ad
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
Create and control VFX in Unreal Engine 5 with Niagara: systems and emitters, modules and the spawn/update stages, exposed User parameters, and spawning or driving effects from Blueprints or C++. Use when building particle effects, NS_/NE_ assets, spawning a Niagara system at runtime, setting User parameters, or when the user mentions Niagara, VFX, or a particle system in Unreal.
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image
Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-image generation, edit/transform existing images, apply style transfer, generate images based on reference photos, interleaved text-image content, mentions Wan/Qwen Image models/AI art creation, or explicitly invokes this skill by name (e.g. use qianwen-image-generation). DO NOT TRIGGER when: user wants to understand/analyze existing images or OCR (use qianwen-vision), video generation (use qianwen-video-generation), text-only tasks.
Film and video storyboarding with shot vocabulary, continuity rules, and panel layout. Covers shot types, camera angles, movement, the 180-degree rule, and annotation format. Use for: video planning, film pre-production, ad storyboards, music video planning, animation. Triggers: storyboard, storyboarding, shot list, film planning, video planning, pre-production, shot composition, camera angles, scene planning, visual script, animatic, storyboard panels, video storyboard
Understand images and videos with Qwen vision models. TRIGGER when: the user wants to analyze, describe or extract information from images or videos, OCR text extraction, chart/table reading, visual reasoning, multi-image comparison, screenshot understanding, video comprehension, or explicitly invokes this skill by name (e.g. use qianwen-vision). DO NOT TRIGGER when: the user wants to generate/create images (use qianwen-image-generation), generate videos (use qianwen-video-generation), text-only tasks without visual input, or non-Qwen vision tasks.
Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real page screenshots + 2.5D camera moves + beat-synced cuts + sound design). Use when the user asks to turn a frontend project or webpage into a product video, says “use video-shotcraft to make a video/promo,” names the Ink Press template or asks to reproduce its effect, or wants a single shot card's motion.
Run an organizer's own standing podcast or video channel as a cross-edition media property - whether to sustain a channel at all, the cadence commitment and its named owner in the quiet months, guest sourcing from the speaker pool outward, the two-way feed with the event cycle, and the wind-down or handover when organizers change. Use whenever the user mentions starting a conference podcast or YouTube channel, publishing between editions, where episode guests come from, who owns the show when an organizer leaves, or closing one down - even if they never say "podcast". Do NOT use for cutting one edition's talk recordings into clips - use samber/dev-event-organizer-skills@event-content-repurposing instead.
Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration, read text aloud, build TTS applications, mentions speech synthesis/voice generation/audio output from text, or explicitly invokes this skill by name (e.g. use qianwen-audio-tts). DO NOT TRIGGER when: user wants speech recognition/ASR, text generation without audio, non-Qwen audio tasks
Writes opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, newsletters, essays. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including punching up a flat intro or draft opening — or for a post title, titre d'article, or headline. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky), READMEs, taglines, email subjects, ad copy, landing-page headlines, press releases, SEO meta, or body rewrites. Do NOT use for end-of-article CTAs — use samber/cc-skills@copywriting-cta instead.
AI product photography with studio lighting, lifestyle shots, and packshot conventions. Covers angles, backgrounds, shadow types, hero shots, and e-commerce image requirements. Use for: product photos, e-commerce images, Amazon listings, packshots, lifestyle photography. Triggers: product photography, product photo, packshot, e-commerce photography, product shot, product image, studio photography, lifestyle product, amazon product photo, product listing image, hero shot, product mockup, commercial photography
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.