Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
From an idea to a sellable series design: series engine/franchise, story pattern, character webs that keep generating conflict, pilot types, and the documents that sell them (series engine/franchise/story pattern/character web/pilot types/series bible/springboard/pitch). Merged from Rabkin's four-element franchise and story landmines, Landau's tacit contract and pitch recipe, Oberg's series types and bible specs, Douglas's franchise-plus-springboard and bible tiers, Goldberg & Rabkin's 100-episode test, Blum's concept/presentation/bible ladder, Miller's ten-component treatment, Calvisi's Compelling Crisis, Smith's series format, plus engines read off Sopranos, Fleabag, and Succession. Use when turning an idea into a series, testing whether a premise has legs, choosing premise vs. typical-episode pilot, designing a sustainable character web, writing a logline, pitch document, bible, or treatment, picking a series type, adapting IP into a series, or diagnosing a project that feels “more like a movie than a series.”
State-transition screen-space surface effects for Three.js WebGPU/TSL. Use for persistent touch, frost, or thaw history; full-field or sparse accumulation; static crystalline fields; reduced-resolution blur; or history-gated normal refraction.
Generate on-brand marketing images via Codex's built-in image_generation tool. Trigger when user asks to: (a) create marketing assets (ad / logo / slide / product-mockup / scene / lighting-transform / LinkedIn-or-social carousel) for a specific brand, (b) extract or build a brand profile (DESIGN.md) from URL / Tailwind config / tokens.json / Figma Variables / CSS custom props / description / existing brand asset, (c) maintain on-brand consistency across multiple image jobs for the same brand. Do NOT trigger for: UI code generation, frontend reference imagery (use imagegen-frontend-web instead), video generation, or general image editing without brand context. RUNTIME: Requires OpenAI `image_generation` tool (gpt-image-2 via Responses API). Native to Codex (CLI / App / web). Claude Code users need an MCP server that exposes image generation. If the tool is unavailable, this skill HARD-STOPS with remediation guidance — it does NOT fall back to HTML/CSS/Canvas rendering.
Create academic presentation slide decks and optionally demo videos from research papers. Use when the user asks to "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides", or wants to turn a paper into a visual presentation. Covers slide generation, narration scripts, TTS audio, and video assembly.
Generate free images with Agnes Image 2.1 Flash through the Agnes API, including text-to-image, image-to-image, high-density visual prompts, URL results, and local downloads. Use when the user asks for 免费图片, 免费的图片模型, free image API, Agnes image, Agnes Image 2.1 Flash, free AI image generation, image-to-image via Agnes, or wants a free image model Agent skill.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Retopology and UVs in Blender 5.2 - auto retopo (Quadriflow, Decimate, planar), deformation edge flow, seams, unwrap (Angle Based, Minimum Stretch, Smart), pixel-margin packing, texel density measure/set, lightmap UV2, UDIMs, mirrored UVs. Use to turn sculpts/scans/AI meshes into game meshes or prep UVs for texturing/baking.
Expert knowledge for environment art in games - modular design, visual hierarchy, color scripting, environmental storytelling, optimization, and world-building. From blockout to final art pass, creating immersive, performant, and readable spaces. Use when "environment art, level art, world art, modular kit, kit-bashing, set dressing, prop placement, biome design, visual hierarchy, color script, hero prop, trim sheet, environment composition, skybox, atmosphere, environment, level-art, world-building, modular, kit-bashing, set-dressing, visual-design, game-art, composition, optimization" mentioned.
Invoke when the user asks about game economy, currency design, monetization, virtual currency, inflation, sink/source balance, F2P economy, premium currency, loot boxes, season pass, battle pass economics, dual currency, or resource flow modeling. Triggers on: "economy", "currency", "monetization", "F2P", "premium", "loot box", "battle pass", "sink/source", "inflation", "resource flow". Do NOT invoke for core gameplay mechanics (use game-designer) or legal advice on gambling laws (consult legal counsel). Part of the AlterLab GameForge collection.
Replacing existing text in an image (A → B), supporting simple precise edits and complex edits (stylized/handwritten text, multiple spots, character count changes). Triggered when the user mentions changing text, replacing text, changing A to B, editing text, swapping a character, text replacement, changing a title, changing a price, changing a name, or changing ad copy.
Generate a style-consistent icon set, delivered as transparent PNGs via grid-based image generation, splitting, and background removal. Use when the user needs a full set of custom icons, section icons, or icons matching a brand style; not for a single simple vector icon or small dense functional symbols.
Generate comic- or anime-style images with Tongyi Qianwen · Wanxiang (wan2.6-t2i). Use this skill for requests related to comic-style image generation, such as “generate a comic,” “draw a comic with Wanxiang,” “generate a comic-style image,” or “draw a 2D character with Qianwen.”
Build curved-ray space effects in Three.js WebGPU/TSL. Use for artistic ray bending, Ellis wormholes, Schwarzschild black-hole lensing, accretion disks, physical thin-disk transport, or requests that need the Kerr/rotating-black-hole support boundary.
Procedural fields for coherent scalar and vector causes in Three.js WebGPU/TSL. Use when a task needs shared causes across materials, geometry, or compute; must choose direct evaluation versus a baked field; needs deterministic CPU/TSL parity and footprint filtering; or needs metric signed-distance terrain and coast analysis.
Couple Three.js WebGPU/TSL rain, snow, and wet surfaces. Use for airborne precipitation motion, physical surface deposition, persistent snow or wetness state, weather-driven ripple normals, or impact splashes.
Synthesize broad-band offshore seas with spectral FFT cascades in Three.js WebGPU/TSL. Use for homogeneous directional wind sea or swell, transported foam history, bounded CPU surface queries, or offshore forcing of a separate coastal model.
Create animated logo files (Lottie JSON, GIF, MP4) from static logo images. This skill should be used when users provide a logo image (PNG/SVG/JPG) and request any kind of logo animation, motion graphics, animated logo effect, waveform animation, bouncing logo, rotating logo, pulsing logo, wiggling logo, or ask to "animate my logo" or "make my logo move". Outputs standalone animation files (not React/HTML artifacts). Generates Lottie JSON with automatic GIF/MP4 rendering, perfect loop validation, and professional motion design patterns.
Skill for creating optimized YouTube video opening hooks (first 5-30 seconds) that maximize viewer retention and watch time. Use when planning video scripts, reviewing video openings, or optimizing existing content for better retention metrics.
A creation and conversion skill that organizes one or more images into a layered PSD file. Use this skill when the user needs image2psd, converting images to PSD, combining multiple images into a PSD, splitting a poster or design into multiple layers, turning a white background transparent, splitting layers by color clustering, splitting Codex/AI-generated images into element images and recombining them into a PSD, or wants to output a layered PSD or a layered raster file editable in Photoshop/Photopea. When used in Codex, it combines the imagegen skill by default: first use Codex's vision/image-generation capabilities to understand, complete, or rebuild elements, then use this skill's scripts to produce the PSD.
Geometry Nodes in Blender 5.2 - fields, domains, attributes, instancing, zones (simulation/repeat/for-each), closures/bundles, lists, SDF grids, node tools, baking, plus a JSON-to-node-tree builder and socket inspector. Use for scattering, procedural assets/environments, parametric tools and modifier inputs.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Analyze a story's character relationship network: types, traits, development, and influence on the plot. Use to map relationships and design conflicts and emotional arcs; trigger when character relationships or relationship maps are mentioned.
Provider-independent dialogue editing and ADR direction for AI agents producing generated videos, films, ads, avatar clips, explainers, localization/dubbing, podcasts, recuts, and social content. Use for dialogue prep, repair, room tone, take comping, sync, ADR cueing, dubbing direction, pronunciation, de-essing, plosives, mouth clicks, voice continuity, synthetic voice consent boundaries, captions/transcripts handoff, mix handoff, loudness, intelligibility, accessibility, and QA.
Complete FFmpeg noise reduction and denoising for video and audio. PROACTIVELY activate for: (1) Video denoising (nlmeans, hqdn3d, vaguedenoiser), (2) Hardware-accelerated denoising (nlmeans_opencl, nlmeans_vulkan), (3) Audio noise reduction (afftdn, anlmdn), (4) Film grain removal, (5) Low-light footage enhancement, (6) Compression artifact removal, (7) Broadcast noise reduction, (8) Clean audio recordings. Provides: Denoising filters, parameter tuning, hardware acceleration, quality/speed tradeoffs.
Visual quality review for FrameVideo compositions. Use when checking or fixing material overlap, text overlap, clipped or overflowing text, low text/background contrast, unsafe title/logo/CTA/caption placement, dynamic text fitting, visual collisions during animation, or final composition QA after creating or significantly editing FrameVideo HTML.
Use when writing or editing prose an audience will read — emails, blog posts, articles, marketing and website copy, LinkedIn or social posts, cover letters, newsletters, product descriptions, reports, essays — and when the user asks to humanize text, make it sound natural or less robotic, remove AI patterns, or clean up an AI-generated draft. Applies by default to any audience-facing writing task. Do not use for code, commit messages, config files, or legal documents where formulaic precision is required.
Motion Studio - motion designer, art director, animator, editor and sound designer in one skill. Produces polished motion-graphics MP4s from a brief - product ads, demos, explainers, tech news, trailers, logo reveals, kinetic typography, infographics, documentaries, music visualizers, lyric videos, UI promos, social shorts - in 51 visual styles (minimal, Apple-style, luxury, SaaS, cinematic, horror, cyberpunk, HUD, glitch, VHS, 80s, Y2K, pixel, anime, comic, paper cutout, blueprint, data viz, generative...) and 10 motion languages (cinematic, snappy, elastic, mechanical, organic, glitch, energetic, calm, stop-motion, smooth), any aspect ratio (16:9, 9:16, 1:1, 4:5, custom). Use for any request to make, restyle or compare an animated/motion-graphics video, including "same video in 3 styles", "make this more cinematic" and reproducible benchmark renders. Plans concept + storyboard first, renders deterministic frames, generates beat-synced music/SFX, and runs automated video QC.
Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts. Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting. Use for: better AI outputs, consistent results, complex tasks, optimization. Triggers: prompt engineering, how to prompt, better prompts, prompt tips, prompting guide, llm prompting, image prompt, ai prompting, prompt optimization, prompt template, prompt structure, effective prompts, prompt techniques
A social media operations automation skill supporting content generation, image generation, data management, and automated publishing on platforms such as Xiaohongshu, Douyin, WeChat Official Accounts, and Channels. Includes complete workflows for Tavily API search, content generation, image generation, HAP data management, and automated publishing. Adds a daily trending content recommendation feature. Image generation supports parallel generation, automatic downloads, and improvements such as automatically skipping existing images. Requires reading account persona settings from the HAP “账号人设” table; using local files is prohibited.
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts
Process images, audio, and video files stored in Alibaba Cloud OSS. Supports 14+ image operations (resize, crop, rotate, watermark, blur, format conversion, etc.), image-intelligent features via IMM (blind watermark, face/body/car detection, QR recognition, labeling, scoring), and audio/video processing (transcoding, screenshot, animation, sprite sheet, concatenation, metadata extraction, HLS streaming). Results can be returned as signed URL, downloaded locally, or saved as new OSS object. Also supports plain file upload/download. Use when the user needs to process or transform media files in OSS, such as generating thumbnails, transcoding video, extracting audio, adding watermarks, detecting faces, compressing images, or converting formats. Triggers on media processing requests in English or Chinese (resize, crop, thumbnail, transcode, video convert, audio convert, watermark, face detection, 缩略图, 裁剪, 压缩, 转码, 视频转换, 音频处理, 水印, 盲水印, 人脸检测, 截帧, 拼接).
Produce anime-style and stylized 2D animation with generative image and video tools as a craft discipline, not a filter. Use when a request asks for anime, manga-style, cel-shaded, sakuga, shonen/shojo/seinen/slice-of-life, mecha, or retro-90s-OVA animation; when planning shots, motion, and cutting rhythm to anime convention; when holding a character on-model and preventing style drift across shots or episodes; when choosing prompting vocabulary that actually controls anime look; when pairing voice, music, and impact SFX to stylized action; and when navigating the cultural, IP, and platform-policy sensitivities of AI anime (studio/artist style imitation, fan-art and IP boundaries, disclosure and monetization). This is provider-neutral; models are named only as illustrative options.
Plan, analyze, and build professional DaVinci Resolve social edits from multicam video/audio folders, podcast/interview footage, vertical 9:16 deliverables, branded social promos, burned-in captions, B-roll/overlay coverage, Resolve timelines, FCPXML/EDL handoff, or FFmpeg preview renders. Use when Codex must avoid jump cuts, preserve narrative coherence, keep the speaker in frame, balance dialogue/music, create reviewable edit decisions, or automate Resolve media/timeline setup.
Convert raster images (photos, paintings, illustrations, line art) into SVG vector reproductions. Use when the user uploads an image and asks to reproduce, vectorize, trace, or convert it to SVG. Also use when asked to decompose an image into shapes, create an SVG version of a picture, or faithfully reproduce artwork as vector graphics. Handles graphic/line-art inputs (Kandinsky, architectural drawings, ink work) via a compositional pipeline that extracts lines as SVG strokes. Do NOT use for creating original SVG illustrations from text descriptions — only for converting existing raster images.
General-purpose image generation execution layer supporting three image-generation APIs: MuleRun Nano Banana 2, APImart GPT Image 2, and Atlas Cloud GPT Image 2. Switch with --provider. Supports generation (text-to-image) and edit (image editing with a reference image) modes, with single-image and batch execution. This is an infrastructure skill called by other skills, not intended for end users. When another skill (such as cover-hero or inline-diagram) needs to call an API to generate images, use this skill's scripts/generate.py. Do not use for prompt writing, style injection, or business validation—those are handled by the calling skill
Use when the user wants to generate or edit images with Google's Nanobanana/Gemini image models using the official Gemini API shape, or when they need publication-style scientific figures rendered exactly from data with the bundled Python plotting tool. Prefer this skill for text-to-image, image-to-image editing, multi-image reference workflows, attachment-based recreations, exact bar/trend/heatmap/scatter plots, or when the user wants publication-style figures such as materials-science paper schematics. Use it when the user asks for a materials-science figure, journal-style scientific illustration, graphical abstract, mechanism diagram, device architecture, processing workflow, or paper-ready materials figure.
Structured producer who turns research insights into production-ready slide deck outlines and scripts. Triggers: 'create slides', 'write webinar script', 'build slide deck', 'webinar outline', 'produce webinar', or when user asks for the Producer.
Transforms product documentation into sales-ready packages — a story explanation, charcoal gestural sketch art, and talking points — via a narrative-arc pipeline. USE WHEN sales, proposal, pitch deck, value proposition, sales narrative, sales deck, sales package, turn this into a pitch, create a sales story, sales materials, product pitch, transform docs to sales, sales script. NOT FOR Hormozi $100M frameworks, value equation, irresistible offer, or VOC mining, standalone diagrams or illustrations (use Art), or platform social posts.
Create publication-quality scientific diagrams using Nano Banana Pro AI with iterative refinement. AI generation is the default method for all diagram types. Generates high-fidelity images with automatic quality review. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.
Convert concepts, scripts, ad copy, product ideas, rough stories, or vague video ideas into high-quality storyboard prompts, shot lists, and AI-video-ready multi-shot prompt tables. Use for storyboard, shot script, camera planning, shot list, video storyboard, trailer planning, script-to-storyboard, AI video prompts, and incremental storyboard edits.
Generate subtitles (SRT/VTT) and plain text transcripts from video or audio files using AWS Transcribe. Use when creating captions, extracting spoken content, generating transcripts for notes, or making video content searchable.
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
End-to-end pipeline for writing and publishing an article to WeChat Official Account draft box. Use when user says "帮我写一篇新文章", "写文章发公众号", "配图排版发草稿箱", "直接发公众号", "配图发布", "write and publish", or any combination of writing + illustrating + posting to WeChat without manual confirmation steps.
Use when the user has a video's SRT subtitle file — a 王建硕 monologue / 讲解, OR a 对谈 / 访谈 where 王建硕 is one of the speakers — and wants to mine it into multiple standalone 微信公众号 articles, one article per distinct topic. Triggers — "把这个视频写成文章", "从字幕里挖文章", "这个 SRT 能写几篇", "把对谈写成文章", "/wjs-mining-articles <srt>".
WeChat official account writing | long-form writing | polishing | rewriting and continuation — AI writing for long-form WeChat official account articles, generating a complete draft from a topic or outline, supporting rewriting, continuation, polishing, opening and ending optimization, with DeepSeek / GPT / Claude or an Agent writing on your behalf. For self-media authors, WeChat official account operators, and brand copywriters. Trigger words (triggering alone is limited to edits of an existing draft): 改写, 润色, 续写, 续一段, 往下写, 接着这段写, 重写开头, 改结尾, 调整语气, 这段润色下, 把这段改活泼点, 优化用词, 用 GPT 重写, 用 DeepSeek 重写. To write a new article, use aws-wechat-article-main (main calls this skill internally to generate the draft); for a multi-stage pipeline (write + review + layout + images + publish), also use main.
Stylize existing images (anime, oil painting, watercolor, chibi, cartoon, 3D, pixel, meme sticker, etc.), supporting single-image stylization and two-image reference style transfer. Triggered when the user mentions style conversion, style transfer, turning into xxx style, meme stickers, emoji style, chibi, perler beads, toy style, oil painting style, watercolor style, anime style, 3D style, or preset effects.
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.