Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Apply realistic PBR textures from PolyHaven to any Blender object. Supports metals, wood, concrete, fabric, and more. Trigger when asked to texture an object, apply a material from PolyHaven, make something look like metal/wood/marble, or change object surface.
Use when an application should send image, video, or audio generation through a saved Runway Model Router configuration, or when the user asks to inspect or manage one. Resolve the live config and follow current router docs. For a fixed direct model endpoint, use runway-dev-models instead.
End-to-end Remotion video production from natural language briefs. Orchestrates narrative structure, scene animation, visual style, and rendering to produce complete promotional videos. Use when a user wants to create a complete video (product promo, typographic piece, social media animation) — not just individual animation effects. Coordinates gsap-animation, spring-animation, and react-animation skills as building blocks.
Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.
Scaffolding that helps a writer build a story they already want to tell — fills in structure, hidden wound, theme, and prose from the writer's own material across seven narrative layers, deriving the spine from their notes as proposals they ratify. Bans generic AI patterns; scales short story to multi-book series. USE WHEN write story, fiction, novel, chapter, story bible, character arc, plot outline, creative writing, worldbuilding, draft story, help me write my story, develop my novel, layer my story, build out my book, I have notes for a story. NOT FOR narrative summaries of real content.
Optional, advanced pipeline between Blockbench and Adobe Substance 3D (Designer, Painter and the Substance Automation Toolkit command lines). Use only when the user has Substance installed and asks for it — render .sbsar procedural materials to Blockbench-sized PBR maps with sbsrender, cook .sbs graphs with sbscooker, bake AO/curvature/normal/position/ID maps from a Blockbench export with substance3d_baker, drive Substance 3D Painter over its remote-scripting HTTP API to paint a Blockbench model and export Bedrock MER or glTF maps, and pack results into texture_set.json. Triggers on Substance, Substance 3D, Substance Designer, Substance Painter, SAT, Substance Automation Toolkit, sbsar, .sbs, sbsrender, sbscooker, sbsmutator, sbsupdater, sbsbaker, substance3d_baker, pysbs, bake AO for Blockbench, Painter export to Blockbench. Not needed for ordinary painting, generated textures or derived normal maps.
Apply AI beauty retouching to a single-person portrait photo (skin smoothing, whitening, and facial feature refinement). Trigger only when the user explicitly requests beauty retouching, skin smoothing, whitening, or portrait refinement for a single-person portrait and has provided the portrait photo; vague requests like “make the photo look better” or “touch it up” do not trigger on their own.
When the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or optimize paid media with AI tools. Also use when the user mentions “ad creative,” “performance creative,” “creative testing,” “creative fatigue,” “Meta ads,” “Google ads,” “TikTok ads,” “AI ads,” “ad budget,” “ROAS,” “Advantage+,” or “Performance Max.” This skill covers AI-powered paid creative from generation through performance optimization. Do NOT use for technical implementation, code review, or software architecture.
Hosted ChatCut plugin sessions only (the `chatcut` MCP server). If the conversation is driving ChatCut Desktop (a `chatcut_desktop*` MCP server), load this skill only when the user explicitly chooses the plugin/web surface — desktop sessions otherwise ship their own instructions and tools. Use for ChatCut transcription, transcript readiness, captions, subtitles, transcript repair, filler removal, and speech-led editing setup.
Generate speech from text via POST /audio/speech, and clone a voice via POST /audio/voices. Covers TTS models (Kokoro, Qwen 3, xAI, Inworld, Chatterbox, Orpheus, ElevenLabs Turbo, MiniMax, Gemini Flash, Gradium), voices per model, cloned-voice handles and raw ElevenLabs Voice IDs, per-model output formats (model_spec.supported_formats / default_format), streaming, prompt/style control, temperature/top_p, speed clamping, and language hints.
Transform existing images with Venice. Covers POST /image/edit (prompt-driven single-image edit), /image/multi-edit (compose several images, per-model input cap, quality tiers), /image/upscale (2x–4x upscale with creativity), and /image/background-remove (transparent PNG cutout). Input formats (base64, data URI, URL, multipart), per-model constraints from GET /models?type=inpaint, response headers, and errors.
AI video generation via Seedance, Kling, Gemini Omni, MiniMax H3, and MiniMax H3 Max. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation — or wants to modify / edit / extend an existing generated clip.
Complete short-form video optimization for TikTok, Instagram Reels, YouTube Shorts, and Facebook Reels. PROACTIVELY activate for: (1) TikTok content strategy, (2) Instagram Reels optimization, (3) YouTube Shorts creation, (4) Facebook Reels strategy, (5) Short-form hook creation, (6) Vertical video best practices, (7) Trending audio selection, (8) Loop optimization, (9) Quick engagement tactics. Provides: Platform-specific length recommendations, algorithm insights, hook formulas, trending strategies, caption techniques, hashtag optimization, and posting schedules.
Build a simulation-style video (agents, particles, 3D machines, fly-throughs) as a single HTML page whose render(t) is a pure function of time, then capture it frame by frame to a 60 fps MP4 with sims/capture.mjs. Use when the idea is a simulation or a 3D object rather than motion graphics with text and UI.
Creates screen-photo-style fisheye distortion effects and focus animations: barrel fisheye distortion + fine scan lines/moiré interference + vignette around the edges, producing Remotion video output for any image/video with "push-in focus on a spot + yellow annotation block sliding in". The core is cloning the https://github.com/vibe-motion/fisheye-motion project and rendering with adjusted parameters as needed. Trigger words: fisheye, screen photo, moiré, moire, scan lines, CRT, vignette, push-in focus, highlight annotation animation, screen-photo effect.
Create hand-drawn short films with whole-pose drawings, expressive strokes and intentional exposure in JavaScript and Canvas 2D: ink, pencil, risograph, screen print, or brush-pen doodles on photos. Includes performance animation, real-motion tracing, sand animation and pop-up paper. Use for hand-drawn cartoons, animated explainers, procedural films, rotoscope, sand stories or drawings interacting with objects. Not for UI animation or slide decks.
Set up and tweak Meta Movement SDK (MSDK) retargeting for a character model. Use this whenever the user wants to retarget a humanoid FBX/prefab for Meta VR body tracking, generate a retargeting config, or hand-edit the resulting `<asset>.json` (fix known-joint mappings, exclude joints from auto-mapping, rename target joints, adjust per-joint mapping weights, change a mapping behavior to twist/childAlignedTwist, edit T-pose values). The headless entry point is `Meta.XR.Movement.Editor.MSDKUtilityEditor.RunDefaultRetargetingSetup(GameObject asset)` — call it against a live Editor with unity-cli first, then hand-edit if needed. **Skip** if the user is editing runtime retargeting code, the source `OVRSkeletonData.json`, or non-MSDK files.
Generate professional storyboard image prompts compatible with diffusion models (FLUX/SDXL/Gemini). Validate quality, then split them into separate files, or directly generate Gemini prompt templates with product descriptions. Use when the user says "生成分镜提示词"（generate storyboard prompts）, "校验分镜"（validate storyboard）, "拆分镜"（split storyboard）, "分镜"（storyboard）, "分镜图"（storyboard images）, or mentions video storyboards, shot prompts, or product storyboard templates.
Answer current ChatCut product questions using the latest official Docs, Releases, and Changelog. Use for how ChatCut works; UI layout, buttons, and feature instructions; troubleshooting; feature or fix availability on Web, Desktop, or Agent Plugin and minimum version requirements; credits including costs, balance, usage history, validity, or recent charges; plans, subscriptions, renewals, ChatCut Pro, pricing, card or Alipay (支付宝) payments, and billing; Desktop downloads; Agent Plugin installation or updates for Codex and Claude Code; and manual GUI guidance when an action cannot be completed directly. NOT for live project, asset, timeline, or item state; use the matching read tool instead.
Designs Amazon A+ Content (formerly Enhanced Brand Content) — the 8 module suite that appears below the standard product carousel for Brand Registered sellers. Covers Hero Banner (21:9 / 2388×1024), Pain Points / Selling Points / Technology / Data / How-to-Use / Variants (3:2 / 1536×1024), and Endorsement (21:9), with mobile safe-area rule, 30pt text floor, and cross-module consistency anchored to the main image URL. Use when the user says "A+ page", "A+ content", "Amazon A+", "Brand Content", "Enhanced Brand Content", "亚马逊详情页", "A+ 详情页", "21:9 banner", "Hero Banner", "Amazon detail page module", or any request for the brand-registered detail-page module suite. For the 1:1 main image and carousel secondary images, see the `product-shots-main-image` skill.
Generates a designed portfolio-resume image from resume content provided in conversation text. Extracts optional style instructions, converts the resume into a fixed portfolio-resume layout prompt, and generates the final image through sn-image-base. Use when user asks to create "resume image", "portfolio resume", "简历图", "简历海报", or "个人简历视觉设计".
Use when the user wants to build video-first cold outreach, create personalized videos at scale, implement async selling, or use AI demo generation for prospecting. Also use when the user mentions “video outreach,” “personalized video,” “video prospecting,” “Tavus,” “Sendspark,” “HeyGen,” “video email,” “async selling,” “video demo,” or “made this for you.” This skill covers video-first outreach systems from personalization through conversion optimization. Do not use for technical implementation, code review, or software architecture.
Work with YouTube content end to end — fetch transcripts and turn them into summaries, blog posts, social content, quotes, or show notes; create high-CTR thumbnails (with the user's face from an upload), clone the style of top-ranking thumbnails; and produce SEO-optimised titles + descriptions. Use when the user pastes a YouTube URL, wants to repurpose video content, research competitor videos, make or refresh a thumbnail, or package a video for upload.
Drive ARKit-blendshape-rigged head/face models in Unity with the wearer's facial expressions on Meta VR via Meta Movement SDK (face tracking + A2E). Use when a user has an FBX with the 52 ARKit blendshapes (any prefix, _L/_R suffixes) and wants it to animate from face tracking on Quest Pro / Quest 3 / Quest 3S.
Generate highly detailed, Midjourney-style image prompts optimized for the FLUX 1.1 Pro model on Replicate. Transform basic user descriptions into rich, cinematic prompts with professional photography qualities, dramatic lighting, and editorial-quality aesthetics. Use when users request image generation, need prompt enhancement, or want Midjourney-quality outputs via FLUX 1.1 Pro.
Taste rules for Remotion motion graphics — timing, easing, springs, typography, color, texture, and scene continuity, with concrete numbers. Use whenever you create, animate, retime, or polish a video, composition, scene, or transition in this repo.
Full-process Chinese long-form novel writing skill (v1.0.0). This skill must be used when users want to write a novel or story, continue a chapter, develop a plot, build a world, design character relationships, extract a writing style, or imitate another novel. Covers the complete process from a vague idea to a finished work of 3 million Chinese characters: idea prompting, knowledge graph construction, outline management, storyboard writing, quality gates, cross-Agent review, style calibration, and cascading updates when the outline changes midway. Trigger this skill even if the user only says “Help me write a story” or “I have an idea for a novel.”
Drive the pollo-cli to generate images and videos through the Pollo platform open API — discover a model, read its input fields, submit a generation with local or hosted image inputs, and poll it to a finished URL. Use this whenever the user asks to generate/create/make an image or video, animate a photo, do image-to-video / text-to-video / reference-to-video, check Pollo credit balance or estimate the credit cost of a generation, or asks what Pollo models are available — trigger even if they don't name "pollo-cli" or "pollo" explicitly, e.g. "turn this photo into a video" or "how many credits do I have left". NOT for building the platform API itself (server-side model exposure — use the expose-platform-model-api skill) or wiring a model into the web frontend (use the add-model skill).
Front-door router for the product-shots ecosystem. Clarifies underspecified visual creation requests through a 4-stage state machine, injects platform visual DNA (Amazon + 7 social platforms) and industry visual DNA (7 industries), enforces a unified Negative Constraints prompt patch, then routes to one of five downstream business skills (product-shots-main-image / product-shots-detail-page / product-shots-multi-angle / product-shots-ad-creative / product-shots-social-post). Use when the user says "I need a product image", "design something for my listing", "I need content for Instagram", "make an ad for me", "make a cover image", "create a post", "做一个商品图", "帮我做个详情页", "帮我做个广告图", "做一个社媒图", "做一张图", "帮我设计", "做个封面" — i.e. any underspecified visual creation request that needs clarification before generation. This is the intent-routing hub of the product-shots ecosystem.
Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a `.uproject`, add things around a PlayerStart, create or edit a Blueprint/Widget/Material/Niagara/Control Rig/Sequencer/Behavior Tree/GAS ability, read or write properties on actors (e.g. `bIsLocked` on `BP_DoorActor`), Live Coding recompile after editing C++ (`AActor`, `UMyComponent::Method`, `UPROPERTY`), or modify Static/Skeletal Mesh assets. Treat as Unreal context even without the word "Unreal": asset prefixes `BP_`, `WBP_`, `M_`, `MI_`, `NS_`, `CR_`, `SK_`, `SM_`, `ABP_`; UE C++ types/macros; `.uproject`; Content Browser; Outliner; PlayerStart; "in my game" plus UE signals. Skip for: pure conceptual/docs questions, Unity, Godot, or unrelated uses of "blueprint"/"sequencer"/"widget".
Use when the user wants to post a daily X/Twitter tweet inspired by one of their recently-published 微信公众号 articles. Picks the newest article that hasn't been tweeted yet, drafts 3 tweet candidates from it (different angles — quote / metaphor / one-liner), posts the chosen one via xurl, records to history. Triggers — "每天发一个 tweet", "从文章里发推", "今天的 tweet", "/wjs-tweeting-from-articles"
World-class character and art style consistency for AI-generated images and videos - ensures visual coherence across series, maintains character identity, and provides rigorous QA before deliveryUse when "character consistency, art style, same character, consistent character, visual continuity, series, turnaround sheet, character sheet, reference image, character bible, style guide, anime character, consistent look, face consistency, outfit consistency, lora training, ip-adapter, flux kontext, visual qa, art quality, generation review, style drift, character drift, character-consistency, art-style, visual-qa, ai-art, image-generation, video-generation, anime, illustration, lora, ip-adapter, flux, midjourney, stable-diffusion" mentioned.
Optimize Blender assets for real-time engines — triangle/material/texture/bone budgets per platform (mobile, Roblox, web, VR, console, PC), LOD chains, decimation modes, mesh cleanup, draw-call reduction (material merging, atlases, trim sheets), instancing, vertex-split costs, collision proxies, texture memory. Use when an asset is too heavy, before export, or when targeting a platform budget.
Use when the user wants to turn text content into a set of polished, shareable visual CARD IMAGES or narrated card VIDEOS — knowledge cards, quote cards, 小红书图文, carousel cards, poster cards — rendered as HTML/CSS and exported via Playwright at ratios like 1:1 / 3:4 / 9:16; optionally produces a narrated MP4 video from those cards via `voxflow card render` (per-card TTS + FFmpeg static-image clips with optional subtitle bar / intro+outro cards / BGM mix). Triggers: card / 卡片 / 知识卡 / 文字卡片 / 金句卡 / 图文卡片 / 卡片生成 / make cards / card video / 卡片视频. For article → Slice-themed card VIDEO use voxflow:slice; for short videos / AI clips use voxflow:video; for podcasts use voxflow:podcast.
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc.). Use ONLY when the user explicitly names OpenAI or GPT as the provider: “gpt image,” “openai image,” “generate image with openai,” “用 openai 画图,” “用 GPT 生成图片.” For generic image requests without a provider, use nanobanana-skill instead. Do NOT use for diagrams (架构图/流程图)—draw those with Mermaid or code.
Lightweight GPT Image 2 image generation and editing workflow. Use when Codex needs to configure OpenAI-compatible image API channels, generate or edit images from the command line without Python, print equivalent curl calls, or help users quickly try curated GPT-Image-2 prompt templates.
Use when the user wants text to sound more human, says writing sounds "too AI" or "too ChatGPT," asks to humanize or rewrite a draft to feel natural, or shares content wanting it to feel authentic and less robotic. Also applies to LinkedIn posts, blog drafts, or emails where the user wants a more genuine voice.
Provides comprehensive guidance for Midjourney AI image generation including prompt engineering, image generation, parameters, and best practices. Use when the user asks about Midjourney, needs to generate AI images, create prompts, or work with Midjourney features.
Shared ChatCut entry point for newly generated music, soundtrack, theme music, 配乐, background music, an intro theme, a music bed, BGM, or vocal songs. If vocals are unspecified, ask whether the user wants a vocal song or instrumental music before choosing a generator. Use `submit_music` for either branch, with `generationType` selecting instrumental or song mode.
Build complete product scenes using PolyHaven assets — HDRI environment, textured ground/pedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.
Asynchronous music, sound-effect, and long-form voice generation via Venice. Covers the /audio/quote + /audio/queue + /audio/retrieve + /audio/complete lifecycle, lyrics vs. instrumental and the lyrics optimizer, duration options, seamless loops (ElevenLabs sound effects), voice selection including custom ElevenLabs Voice IDs, language, speed, model capability probing via /models?type=music, pricing models, refunds, and polling.
Alibaba Cloud Media Processing Service (MPS) one-stop video processing skill. Use when users need video processing, transcoding, snapshot generation, content moderation, or video upload. For video distribution scenarios, complete video upload, snapshot, multi-resolution transcoding, and content moderation in a single workflow for efficient standardized video asset production.
Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include "read this aloud", "generate voice for ...", "create a narration of ...", "tts this", "把这段念出来", "做个配音", "合成语音", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys
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.