Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
One-writer camera rigs for Three.js WebGPU. Use for bounds-derived perspective or orthographic framing; control and cinematic handoffs; temporal jitter and reset ownership; or camera-relative large-world coordinates.
Use when playing animations, crossfading between animation states, or loading skeletal animations from GLTF in Three.js. Prevents the common mistake of not calling mixer.update(delta) every frame, wrong crossfade setup, or missing Clock. Covers AnimationMixer, AnimationClip, AnimationAction, KeyframeTrack, crossfade, blending. Keywords: animation, AnimationMixer, AnimationClip, AnimationAction, crossfade, skeletal, GLTF animation, keyframe, blend, Clock, camera animation, smooth camera, fly to, tween, GSAP.
Conduct pure research for YouTube video topics by analyzing competitors, identifying content gaps, and documenting strategic insights. Use when you need to research a video topic before planning. Produces concise, insight-focused research documents that identify the biggest opportunities for video performance.
Two modes: ① Direct conversation: When the user says “Talk with Musk,” “Analyze this product from Jobs’ perspective,” or “What would Confucius think about this?”, immediately activate the corresponding person’s cognitive operating system and respond as that person, without requiring any Python environment. ② Distill a new person: When the user says “create a skill,” “distill XX,” “turn these materials into a skill,” “analyze this video and generate a skill,” or uploads a file asking to extract someone’s thinking patterns, run the distillation pipeline to generate a new SKILL.md. Trigger keywords: talk with XX, from XX’s perspective, what does XX think, create a skill, distill, generate a skill, extract thinking patterns
Physically based materials in Blender 5.2 - metal/roughness rules, Principled BSDF inputs, color spaces (sRGB vs Non-Color), measured albedo/F0 values, texture-set auto-wiring, ORM channel packing, DirectX vs OpenGL normals, alpha modes, displacement, view transforms (AgX, Khronos PBR Neutral), engine-ready material rules. Use when creating, fixing, or exporting materials and textures.
Generate cinematic videos with native synchronized audio using ByteDance Seedance 2.0 (Fast) via EachLabs. Supports text-to-video (bytedance-seedance-2-0-text-to-video-fast) and image-to-video (bytedance-seedance-2-0-image-to-video-fast). Use when the user specifically asks for Seedance 2.0, wants native audio with the video, realistic physics, director-level camera control, or 4–15 second clips up to 720p.
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.
Generate images, videos, and SVGs using x402-protected AI models at StableStudio. USE FOR: - Generating images from text prompts - Generating videos from text or images - Editing images with AI - Vectorizing images to SVG - Creating visual content TRIGGERS: - "generate image", "create image", "make a picture" - "generate video", "create video", "make a video" - "edit image", "modify image" - "vectorize", "convert to svg" - "stablestudio", "nano-banana", "sora", "veo", "grok", "flux", "seedance", "gpt-image" ALWAYS use `npx agentcash@latest fetch` for stablestudio.dev endpoints.
Turn long-form videos into short clips and post them to social platforms using the OpusClip API. Use when the user wants to clip a YouTube video, upload a local video for clipping, manage clip collections, list brand templates, share projects publicly, censor profanity, post clips to social media, schedule social posts. Triggers on phrases like "clip this video", "create shorts", "opusclip", "make clips from video", "upload to opusclip", "post to youtube", "schedule post", "publish clip".
Plan and generate controllable Seedance video using Seedream 5.0 Pro storyboards and Seedance 2.0 today, with a Seedance 2.5 route when available. Use for consistent people, products, objects, food, or scenes; storyboard-to-video; reference-to-video; first-and-last-frame image-to-video; extensions; and Atlas Cloud media generation
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".
Turn AI-written Japanese back into human-written prose. Use for drafting, editing, and reviewing. Beyond full-width dashes and favorite words, it also fixes the absence of a subject, proposition-style H2 headings, grandiosity, listing both sides, and uniform rhythm.
This skill provides three-act screenplay structure with beat placement. Covers opening image, inciting incident, midpoint, all is lost, climax, and page targets for a 110-page feature screenplay. Use when: planning screenplay structure, analyzing narrative arc, placing story beats, or validating structural integrity.
Curated aphorism collection with CRUD — content-based matching, themed search, thinker research, DB maintenance. Quotes organized by author/theme/context/usage to prevent repetition. Four workflows: FindAphorism, AddAphorism, ResearchThinker, SearchAphorisms. Themes: Stoicism, Wisdom, Truth-seeking, Excellence, Resilience, Curiosity. USE WHEN aphorism, quote, find a quote, research thinker, add aphorism, quote for newsletter, what did X say about, quote bank. NOT FOR creative writing or social posts.
Provider-independent asset continuity and version management for generated-media production. Use when an agent must track generated or reference assets, prompts, seeds, model/tool versions, manifests, approvals, edit decisions, derivatives, localization variants, metadata/provenance, and continuity QA across image, video, audio, avatar, product-ad, social, explainer, or film-style pipelines.
Provider-independent cinematic trailer production for AI agents creating movie-style trailers, teaser trailers, launch trailers, game trailers, documentary trailers, series promos, and high-impact generated-media previews. Use for trailer strategy, structure, shot planning, voiceover/title-card copy, music and sound-design direction, generated-video prompt translation, edit pacing, platform/runtime choices, delivery handoff, rights/claims caveats, and trailer QA.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer
Build, validate, or incrementally update a reusable writing style profile from article samples by the same author or public account. Use when the user requests style modeling, extracting a writing formula, deconstructing articles, learning an author's style, or creating or updating a style library. Do not use this skill if the user only wants an article written directly and does not need a style profile
Coordinate Three.js WebGPU/TSL final-image graphs. Use when effects share scene-pass signals or output ownership, when choosing MRT versus reconstruction or narrow passes, when admitting temporal history, or when whole-graph budgets and lifetimes decide the design.
Use when enabling shadows in a Three.js scene or debugging shadow artifacts like acne, peter panning, or low resolution. Prevents the common mistake of wrong shadow camera frustum, too many PointLight shadows, or missing castShadow/receiveShadow flags. Covers shadow map types, per-light config, bias tuning, CameraHelper debugging. Keywords: shadows, shadowMap, shadow acne, peter panning, bias, normalBias, castShadow, receiveShadow, PCFSoftShadowMap, shadow camera, shadows not showing, shadow artifacts, enable shadows.
Animate semantic state with deterministic Three.js WebGPU/TSL motion. Use for launch or staging kinematics, seekable transform timelines, recurrent fixed-step motion, frame-rate-independent follow, GPU-resident instance motion, moving-frame docking or reparenting, and environment-driven actors.
Humanize LLM output so it reads like a careful human wrote it. Subtracts AI-isms (sycophancy, tricolons, em-dash overuse, "delve"/"tapestry"/"testament", hedging stacks, tidy five-paragraph shapes), engineers burstiness and calibrated uncertainty, and preserves technical accuracy. Supports intensity levels: subtle, balanced (default), full, voice-match, anti-detector. Use when user says "humanize this", "make this sound human", "de-slop this", "rewrite without AI tone", "match my voice", "less robotic", or invokes /unslop. Also auto-triggers when text-quality is requested.
WeWrite writing module: once the WeChat Official Account topic is settled, produces the article brief, claims and evidence, materials, and first draft. Called by the main flow, or responds to "write the body for this topic". Generic writing, blog, and short-video copy do not trigger it.
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
Edits raw recordings into videos for social media using Remotion. Best for Instagram Reels (9:16), but also suitable for other platforms like TikTok, LinkedIn, and YouTube (including 16:9). Use for any video edit, caption, title, graphic, overlay, transition, or animation, or to copy the style of a video.
Provider-independent captions and media accessibility direction for AI agents producing or finishing generated videos, ads, social clips, explainers, avatar videos, documentaries, podcasts/video recuts, training media, and localized content. Use when planning, authoring, reviewing, localizing, burning in, exporting, or QAing captions, subtitles, SDH, transcripts, audio description, flashing/motion safety, caption readability, or accessible media handoff files.
Create a complete product ad video through CawCut's 5-stage AD Video wizard (Product → Config → Idea → Storyboard → Video) via the `cawcut ad-video` CLI. Use when: "/cawcut-ad-video", "ad video", "video ad", "product ad", "广告视频", "商品广告", "带货视频", "产品宣传视频", "make an ad for <product URL>", "turn this product page into a video", or the user wants a multi-shot marketing video built from a product link with script/storyboard review. Requires `cawcut` installed and `cawcut auth login` completed. NOT for: single-prompt image/video generation (use cawcut-generate), talking-head avatar videos (use cawcut-avatar-video), running published Apps (use cawcut-app-run), or listing/deleting/sharing existing Video Ad projects (not exposed to the CLI)
Hosted ChatCut plugin only (`chatcut` or `plugin:chatcut:chatcut`). MANDATORY Claude Code prerequisite: invoke this Skill before the first hosted ChatCut MCP tool call and wait for loading. Also invoke when video editing or creation should remain editable in ChatCut, even if the user does not mention ChatCut. Covers project/editor access, local media import, timeline editing, captions, transcription, talking-head cleanup, B-roll, overlays, motion graphics, generation, audio, translation, export, and verification. Use when hosted tools are missing, unavailable, unauthenticated, or fail to connect; includes connection evidence diagnostics. For `chatcut_desktop*`, follow Desktop instructions unless the user explicitly selects the hosted plugin/web surface.
Generate animated HTML pages for educational and popular-science flowcharts, concept diagrams, and principle demonstrations. Draw nodes and connectors with CSS/SVG, with animation effects such as flowing arrows, step-by-step appearance, and hover highlighting. Suited to technical explanations, science videos, and PPT illustrations.
Professional writing assistance for blogs, research articles, fiction, essays, and marketing copy. Use when users want to write, edit, or improve any form of written content. Triggers: 'write a blog', 'write an article', 'help me write', 'write a story', 'write a chapter', 'draft an essay', 'creative writing', 'improve my writing', 'edit my writing', 'write copy', 'content writing'
Provides local TTS workflows built around Qwen3-TTS. Supports single-sentence speech generation (CustomVoice/VoiceDesign/VoiceClone) and batch voiceover generation for long scripts (article → voiceover script JSON → batch TTS → merge). Use cases: speech generation, audiobook narration, video voiceovers, multi-character dialogue reading, and voice cloning.
WeWrite multi-platform rewriting module: rewrite a WeChat official account article (or a specified source draft) at the content level into versions for other platforms, currently supporting Xiaohongshu (image-and-text notes) and Douyin (spoken scripts), and checking editorial quality and similarity to the source draft. Trigger keywords: rewrite for Xiaohongshu, Xiaohongshu version, Douyin version, spoken script, multi-platform distribution, one draft for many platforms, platform rewriting. Should not be triggered by "translate", "abbreviate", "change the title" — those are single-platform editing actions.
Remove AI writing patterns from prose. Use this skill when writing, drafting, editing, reviewing, or revising any text to eliminate predictable AI tells, slop, and formulaic patterns. Trigger this skill whenever the user asks you to "deslop", "de-AI", "make it sound human," "remove AI patterns," "remove AI tropes," "clean up AI writing," fix "slop," "deslop" text, or review prose for authenticity. Also use when the user asks you to write or draft anything and wants it to sound natural rather than AI-generated. Common use cases include scientific writing (manuscripts, abstracts, cover letters, grant narratives, discussion sections, peer review responses), blog posts, newsletters, memos, reports, and any other substantial prose.
Complete video transition system. PROACTIVELY activate for: (1) xfade transitions (40+ types), (2) Fade in/out effects, (3) Crossfades and dissolves, (4) Wipe transitions (directional), (5) Slide and push effects, (6) Circle/iris transitions, (7) Multi-clip transition sequences, (8) Slideshow creation, (9) Custom transition expressions, (10) Audio crossfade synchronization. Provides: Complete xfade type reference, offset calculation formulas, multi-clip examples, custom expression guide, troubleshooting for resolution/framerate mismatches. Ensures: Smooth professional transitions between video clips.
goodcase.ai (好案例) AI viral case and Prompt lookup Skill. Use when the user wants to find "AI 爆款案例", "好 case", "这类图怎么做的", "这种视频怎么生成的", "找个 XX 的 prompt", "有没有现成的提示词", "Veo 案例", "即梦案例", "Midjourney 案例", "Kling / 可灵案例", "Seedance 案例", "GPT Image 案例", "AI 图像案例", "AI 视频案例", "AI 编程 UI 案例", "AI 文案案例", "爆款 prompt", "复刻这个效果", "这个效果的提示词", "AI case", "viral AI examples", "AI prompt examples", "how was this AI image/video made", "find me a prompt for X", or any AI creation case/prompt query. This Skill should also trigger even if the user only says "有什么好玩的 AI 案例", "给我找个能抄的 prompt", "最近什么 AI 图很火". It is also used for model evaluation scenarios such as "用 goodcase 测一下 XX 模型", "抽几个案例评测模型", "新模型出了跑一下 goodcase 题", "benchmark this model with goodcase". The Skill directly curls the public REST API to pull real case data (including full Prompt, stability score, cost tier) and requires no API Key. **When in doubt, trigger more often**—if the user asks about AI creation cases and you make one up from training data, you are giving the user a fake case and fake Prompt, which harms the user.
Generate posters from text/images, multi-style and multi-size with layout, supporting reference images and editing text/background/elements of existing posters. Trigger when the user mentions 海报, 宣传图, 广告图, Banner, 推广图, 营销图, 活动海报, 促销海报, or poster.
Generate faceless content video prompts for Seedance 2.0 on Higgsfield. Use for faceless YouTube channels, TikTok content without showing face, anonymous creator content, narration-driven videos, stock-footage-style AI content, or any video where the creator doesn't appear on camera. Triggers on faceless, no face, anonymous, narration, stock footage, b-roll, background video, voiceover video.
Sculpt reference-image objects into procedural Three.js models. Use for reconstruction feasibility, procedural build planning, code-native implementation, or animation-, collider-, and destruction-ready structure from one or more object views.
Use when creating 3D shapes, custom geometry, or instanced meshes in Three.js. Prevents the common mistake of forgetting dispose(), not setting needsUpdate on BufferAttribute, or using non-indexed geometry when indexed is better. Covers BufferGeometry, BufferAttribute, all 21 built-in geometries, InstancedMesh, ExtrudeGeometry, custom geometry. Keywords: BufferGeometry, BoxGeometry, SphereGeometry, PlaneGeometry, InstancedMesh, BufferAttribute, geometry, shape, extrude, custom mesh, particles, point cloud, particle system, create shape.
CapCut-style animated word-level captions for viral video with FFmpeg. PROACTIVELY activate for: (1) Word-by-word caption highlighting, (2) Animated subtitle effects, (3) CapCut-style captions, (4) Karaoke-style text, (5) Bounce/pop text animations, (6) Color-changing words, (7) Emoji integration in captions, (8) Multi-style caption presets, (9) Trending caption styles, (10) Social media caption optimization. Provides: ASS subtitle generation scripts, word-level timing workflows, animation presets, color schemes, font recommendations, and platform-specific caption styles for TikTok, YouTube Shorts, and Instagram Reels.
Collect validated Xiaohongshu image assets from normalized XHS datasets into local manifests and downloaded files. Use this when you need reproducible local media artifacts from note covers or other already-exposed remote asset URLs.
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.