Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Detects and revises templated phrasing, posturing, hidden parallelism, structurally identical analytical examples, repeated semantic frameworks, fake rankings, fixed rhythms, and other AI-like expressions in Chinese article body text, while preserving the author's facts, existing heading hierarchy, necessary functional lists, legal terminology, Markdown images, and established voice. Must be used after an article's first draft is complete when the user asks to “remove the AI feel,” “make it sound more human,” “rewrite it based on the author's samples,” or “check the parallelism or tone.” Without author samples, make only minimal edits; do not invent first-person narration, metaphors, punchy one-liners, or experiences, and do not restructure the article under the pretext of removing AI-like wording.
Provider-independent ecommerce product imagery production for marketplace listings, product pages, hero shots, lifestyle scenes, comparison charts, infographics, variant/packaging images, virtual try-on or placement mockups, ads, and AI-assisted product visuals. Use when an agent must plan, generate, edit, review, localize, package, or QA truthful commercial product images while managing SKU continuity, marketplace requirements, claims, rights, releases, accessibility, and approval.
Write Thai-language prose (technical documentation, marketing copy, explainers, blog posts, translations) that reads like a real Thai writer — not generic AI output. Counters training-data skew toward over-formal, over-polite, calqued Thai. TRIGGER when: user asks for any non-trivial Thai prose output (paragraph or longer — blog post, landing page, doc page, README in Thai, email, announcement, section); user asks to translate English into Thai; user asks to edit, rewrite, or review existing Thai prose; conversation is in Thai and user asks for a prose deliverable. DO NOT TRIGGER for: single-word or single-phrase translations, button labels, code identifiers, short UI strings, code comments, or conversational chat replies in Thai that aren't deliverable prose.
Use when drafting, editing, reviewing, or benchmarking prose to remove AI-writing tells while preserving meaning, voice, and density. Trigger this skill for requests about AI slop, humanizing AI-assisted writing, detector-facing validation, unsummarizable prose, voice preservation, or writing that should not sound generic.
Plan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound human on camera, or plan a week around completion rate. TikTok is video-only: the user supplies the video, the skills produce the script, caption, and settings, then publish via Publora.
WeWrite self-learning module: learn writing preferences from the user's manual edits (the playbook flywheel), import sample articles to build a style library, and learn layout themes from WeChat Official Account articles. Trigger keywords: 学习我的修改, 我改了学习一下, 导入范文, 学习这篇文章, 查看范文库, 学习排版, 学排版. Should not be triggered by generic "learn" or "summarize this article" — WeChat Official Account/WeWrite context is required.
3D web graphics with Three.js (WebGL/WebGPU). Capabilities: scenes, cameras, geometries, materials, lights, animations, model loading (GLTF/FBX), PBR materials, shadows, post-processing (bloom, SSAO, SSR), custom shaders, instancing, LOD, physics, VR/XR. Actions: create, build, animate, and render 3D scenes/models. Keywords: Three.js, WebGL, WebGPU, 3D graphics, scene, camera, geometry, material, light, animation, GLTF, FBX, OrbitControls, PBR, shadow mapping, post-processing, bloom, SSAO, shader, instancing, LOD, WebXR, VR, AR, product configurator, data visualization, architectural walkthrough, interactive 3D, canvas. Use when creating 3D visualizations, building WebGL/WebGPU apps, loading 3D models, adding animations, implementing VR/XR, creating interactive graphics, or building product configurators
Hard-surface and prop modeling in Blender 5.2 - blockout-to-detail flow, non-destructive modifier stacks (Mirror, Boolean Exact/Manifold, Bevel, Weighted Normal, Smooth by Angle), mid-poly vs subdivision vs high-to-low workflows, shading/custom normals, cylinder segment budgets, edge attributes from Python. Use for weapons, vehicles, props, architecture, mechanical parts.
Guided webinar creation pipeline from vague idea to production-ready deliverables. Use when creating a webinar from scratch. Triggers: 'create a webinar', 'build a webinar', 'webinar creation', 'new webinar', 'help me make a webinar'.
Provider-independent reference media analysis for generated-media production. Use when an agent must analyze reference images, videos, audio, style boards, product shots, brand assets, mood boards, storyboards, performances, prior cuts, or client examples and translate them into safe, non-copying direction, prompts, QA criteria, provenance records, and handoff notes for image, video, audio, avatar, or post-production agents.
Plan and execute Roblox asset workflows. Use for Creator Store search, inventory/group/universe assets, inserting assets, generated meshes, generated materials, procedural models, uploaded images, thumbnails, icons, decals, style consistency, import security audits, and asset performance budgets.
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
Ground indirect lighting with ambient visibility in Three.js r185 WebGPU/TSL. Use when choosing authored material AO, dynamic GTAO, forward-lighting placement, reduced-resolution reconstruction, temporal AO, or bent normals.
Use when adding sound to a Three.js scene: background music, 3D spatial audio, or audio visualization. Prevents the common mistake of ignoring browser autoplay policy, not attaching AudioListener to camera, or wrong distance model. Covers AudioListener, Audio, PositionalAudio, AudioAnalyser. Keywords: audio, sound, AudioListener, PositionalAudio, 3D audio, spatial audio, music, AudioAnalyser, Web Audio API, play sound, add music, sound in 3D scene.
Builds 3D web experiences with Three.js, WebGPU rendering, TSL shaders, and React Three Fiber. Covers scene setup, asset optimization, performance tuning, and React 19 integration. Use when creating 3D scenes, setting up WebGPU rendering, writing TSL shaders, optimizing draw calls, or integrating Three.js with React and Next.js.
Compile procedural buildings, cities, and semantic site assemblies in Three.js r185 WebGPU/TSL. Use for building massing and facades, city-scale architectural batching and LOD, or deterministic placement of heterogeneous site assets around architecture.
Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG. Triggers on: "create an image of", "export as PNG", "save as SVG", "concept to image", "screenshot this HTML". NOT for interactive HTML; use static-web-artifacts-builder.
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition. Triggers on: "create a video", "animate this", "make an explainer", "manim animation", "motion graphic". NOT for React video, use remotion-video.
Assess the film and television adaptation potential of novels, comics, and other IP based on publicly available online information and the work itself. Suitable for due diligence before acquiring rights and pre-project market assessment; use when you need information on popularity, the author's background, adaptation precedents, or platform performance. If you only have the text and cannot or do not need to access the internet, use novel-evaluator instead.
Product mockups and showcases: photoreal product/packaging scenes via Gemini 3.1 Flash image editing, and pixel-exact device frames (phone, laptop, browser) around real screenshots via HTML/CSS. Covers 3D CSS transforms, lifestyle staging, feature callouts, before/after, and e-commerce product shots. Use when the goal is presenting a product or UI itself; for a marketing graphic that merely includes a product use graphic-design, social-media-graphic, or ad-creative-design. Trigger phrases: "create a product mockup", "device mockup", "phone mockup", "laptop mockup", "product showcase", "screenshot mockup", "app preview", "product presentation", "mockup design".
Inspect and polish SpriteCook sprites after generation or background removal. Use for broken or faint outlines, missing edge pixels, halos, and background debris, and before slicing or animating assets that need edge cleanup. Compare preserved alpha locally and save the selected threshold through MCP.
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
Design and generate production-quality SVG logos in modern minimalist style. Use this skill PROACTIVELY whenever the user asks to create a logo, design a brand mark, generate an SVG icon, make a logomark, create a wordmark, build a brand identity symbol, or needs any kind of vector logo. Also triggers for requests like "make me a logo", "design an icon for my app", "create a brand symbol", "I need a logo for...", "generate SVG logo", or any task involving logo/icon/brand mark creation — even if they don't specifically mention "SVG" or "minimalist".
Solve bounded and coastal water in Three.js WebGPU/TSL. Use for parametric waves, local heightfields, bathymetric wave transport, wet/dry shallow water, two-way body coupling, external free-surface presentation, or water optics and offshore handoffs.
Typecast TTS API expert agent. Provides API key setup, code samples (Python, JavaScript, cURL), Quick Voice Cloning guidance, error troubleshooting, and plan comparison. Use for "Typecast API", "TTS integration", "voice cloning", "quick cloning", "text-to-speech API" questions.
Use when writing an article, newsletter, blog post or long social post that must genuinely be the user's own writing. Triggers on "voiceprint", "write this in my voice", "turn my recording into an article", "cut my transcript down", "make this actually mine", "write from my video". Turns the user's own spoken words into a finished piece by cutting, never by composing.
Shape prose so it sounds like Braden, with conversational precision, rhythm, humor, and earned poetic turns. Use for substantial drafting or revision, an ear pass, and explicit voice or tone work in prose, UI copy, documentation, or messages. Do not use to reopen wording selected for exact use.
JavaScript/TypeScript SDK for Editframe's cloud video API, plus the editframe CLI for the installed local runtime. Create renders, upload media files, sign playback URLs, run video pipelines that transcribe audio, and request exports from the command line.
Research-obsessed strategist for webinar discovery. Use for webinar research, hook generation, topic validation, angle finding, audience analysis, content discovery, competitive landscape. Triggers: 'webinar research', 'find angle', 'webinar hook', 'topic research', 'discovery phase'.
Provider-independent real estate media production for listing photos, virtual staging, property videos, walkthrough reels, floor-plan explainers, neighborhood clips, renovation concepts, agent ads, and generated or retouched property visuals. Use when creating, editing, reviewing, prompting, packaging, or approving real estate marketing content where property truthfulness, listing/MLS compliance, fair-housing risk, staging disclosure, privacy, accessibility, platform variants, or real-estate QA matter.
Rewrite English content into Simplified Chinese. For rewriting English articles, documentation, and blogs into Chinese. Uses deverbalization techniques: understand the original meaning, break away from the English shell, and express it naturally in Chinese rather than word-for-word. Preserves Markdown formatting and AI proper nouns.
Genre anatomy from John Truby's The Anatomy of Genres (类型解剖 / 类型节拍 / 混合类型 / 超越类型) — genres as beat systems with a life philosophy underneath; three rules (hit every beat of your genre, mix three or four genres, transcend the primary genre), the ladder and families of twelve genres (Horror 恐怖, Action 动作, Myth 神话, Memoir and Coming-of-Age 回忆录与成长, Science Fiction 科幻, Crime 犯罪, Comedy 喜剧, Western 西部, Gangster 黑帮, Fantasy 奇幻, Detective and Thriller 侦探与惊悚, Love 爱情), each with its hero/opponent/world/plot-shape template, beat list, hard rules with failure conditions, subgenres and transcendent paths, plus a genre-mixing worksheet and a diagnostic. Kept beside sw-truby-anatomy and the Field/Snyder page maps. Use when choosing or confirming a script's genre, when a genre story feels generic or misses the beats its audience expects, when mixing genres, when a horror lacks pressure, an action lacks plot, a love story lacks opposition or a detective story lacks reveals.
Scale procedural planetary bodies in Three.js r185 WebGPU/TSL. Use when global curvature needs a cube-sphere quadtree, a sustained ground view needs a tangent clipmap, an orbit-to-ground transition needs both, or a gas-giant cloud deck needs body-scale band fields.
Fit scalable directional cast shadows in Three.js r185 WebGPU/TSL. Use when choosing one bounded shadow, CSM, tiled arrays, or cached clipmaps; stabilizing projection, filtering, or bias; or fixing invalidation, caster parity, bindings, or sustained cost.
Apply the Action continuity choreography workflow derived from multiple published GoodCase examples. 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. Read the bundled Case evidence before producing an artifact.
Use this skill when an agent needs to complete Bilibili login, account verification, or video upload via the installed `sau` CLI. Prefer `sau bilibili ...`; the program automatically prepares `biliup` and does not require the user to install it manually.
Analyze images using AI — segment objects, detect objects, extract text (OCR), describe images, and answer questions about images. Use when the user requests "Segment image", "Detect objects", "OCR", "Extract text from image", "Describe image", "What's in this image", or "Image analysis".
Provider-independent provenance, rights, consent, disclosure, and release governance for AI-generated media. Use when producing or reviewing generated images, video, audio, ads, avatars, product content, social clips, documentaries, localization, music, sound, or campaign assets that need source-rights checks, model/provider term checks, likeness or voice consent, trademark/logo review, copyrighted-character/style risk triage, music licensing, C2PA/content credentials, provenance ledgers, release notes, platform disclosures, jurisdiction/client caveats, or rights QA.
Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style continuous motion, shapes that grow / move / rotate as the slide advances. Trigger on: 'morph', 'morph transition', 'smooth transition', 'continuous animation across slides', 'Keynote-style transition', 'animated slide sequence', 'shape continuity across slides'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate 1–5a). DO NOT invoke for a generic deck, pitch deck, or board review without cross-slide motion — route those to officecli-pptx base or officecli-pitch-deck.
Provider-independent production design direction for AI-generated media. Use when translating narrative, brand, advertising, product, social, film, or worldbuilding intent into sets, locations, props, color and material palettes, era research, graphic and environmental design, continuity bibles, image/video prompt planning, reference strategy, production constraints, iteration notes, handoff specs, and QA.
Generate scroll-stopping viral hook video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants viral content, TikTok hooks, Instagram Reels openers, YouTube Shorts, attention-grabbing video, scroll-stopper, pattern interrupt, or any short-form video designed to maximize retention and views. Triggers on any mention of viral, hook, scroll-stop, retention, views, engagement, short-form, TikTok, Reels, Shorts.
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.