Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Generate app icons with transparent backgrounds. Triggers include: "generate icon", "create icon", "make icon", "app icon", "favicon", "icon for", "logo icon", "icon set", "icon pack", "transparent icon" Creates square PNG icons with transparent backgrounds suitable for app icons, favicons, and UI elements.
Use this skill for any image-related AI generation or editing task. Triggers include: GENERATE: "generate image", "create image", "make picture", "draw", "visualize", "image of", "create art", "generate art" EDIT: "edit image", "modify image", "change image", "update image", "fix image", "enhance image" ADD/REMOVE: "add to image", "put in image", "remove from image", "delete from image", "add element" STYLE: "style transfer", "make it look like", "convert style", "apply style", "in the style of" PRODUCT: "product photo", "product placement", "place product", "mockup", "put product on" COMPOSITE: "combine images", "merge images", "blend images", "create composite" Supports text-to-image generation, image editing with references, product placement, style transfer, and multi-image composition using Google Gemini (Nano Banana Pro) or OpenAI DALL-E.
Master prompt-engineer for photoreal, artifact-free AI still images on ANY tool (Reve, Midjourney, Flux, GPT-image, Imagen, Nano Banana, Stable Diffusion). Builds prompts that hit National-Geographic-grade realism — true skin/fur texture (no plastic), correct anatomy/hands/faces, physically coherent light/shadows/reflections, clean legible text — while engineering deliberate visual IMPACT (color contrast, composition, awe/adrenaline, a striking point of view). Runs a gated process: lock the point-of-view and build the 8-block Capture Stack BEFORE generating, then run a forensic pre-submit inspection against the known artifact list. Use whenever the goal is a single still image that must look REAL and hold up under close inspection — contest entries, hero shots, product/character/wildlife/architecture/concept art, or any time AI images come out plastic, distorted, or fake. Composes with nano-banana-2 (execution) and director (motion). Hebrew triggers: תמונה, תמונות, פוטוריאליזם, ריאליזם, לייצר תמונה, פרומפט לתמונה, בלי עיוותים, עור פלסטיק, ידיים מעוותות, פרצוף מעוות, חדות, נשיונל ג'יאוגרפיק.
AI video creation. Supports text-to-video (generating video from text descriptions) and image-to-video (animating images), with configurable resolution, duration, and aspect ratio; automatically waits for generation to complete and downloads the video locally. Use cases: user says "帮我生成一段夕阳海浪的视频", "把这张图片生成动态视频", "创作一段1080P的城市夜景延时视频", "生成一个9:16竖版的产品展示短视频", "做一段10秒的水墨山水动态画面", etc. Submits asynchronous tasks through the 聚合数据 (juhe.cn) API, automatically polls for results, and downloads the finished mp4 video file locally once generation completes.
Create, reverse-engineer, expand, repair, convert, evaluate, and batch-generate prompts specifically for Krea 2. Use for KREA2/Krea 2 text-to-image, image-to-image, image reverse prompting, multi-image reference fusion, style or moodboard planning, typography and poster prompts, RAW/Turbo presets, prompt scoring, A/B variants, prompt conversion, and ComfyUI or RunningHub/Qwen3-VL system prompts. Also trigger on Chinese requests such as Krea2提示词、反推、扩写、改写、融合参考图、节点系统提示词. Do not use for unrelated models unless converting their prompt into Krea 2 format.
Turns one long video (YouTube link, podcast, webinar, livestream, or a local file) into finished vertical shorts. Use when the user says long to short, repurpose, long video to shorts, clips from my video, podcast clips, cut my YouTube video into shorts, or gives a long video link. Finds clips that stand alone (one idea, 20 to 60 seconds), scores them, cuts them and edits each one with video-edit (captions, cuts, hook card, callouts, 1080x1920), and writes new scripts in the video-script format from the ideas too spread out to clip. Reads YouTube captions and chapters with yt-dlp, or transcribes a local file with the video-edit studio.
Particle system modifier development framework for Cocos Creator 2.4.x. Used to create, use, and debug custom particle modifiers, supporting modification of particle position, color, size, rotation, velocity and other properties. Use this skill when you need to implement complex particle effect control in Cocos Creator.
Run the PAIDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation. Select for requests about image attribute augmentation, person attribute search, person re-identification data, clothing augmentation, attribute captions, augmentation payloads, run status, or result retrieval. Runs environment setup first when controller readiness is unknown. Not for video or defect-image generation.
Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes, tables, links, paths, numbers, headings, and residual AI-pattern regressions.
The meta-skill that powers all other AI tools. Prompt engineering for creative applications is the art and science of communicating with AI models to produce exactly what you envision—in images, video, audio, and text. This isn't just "write better prompts." It's understanding how different models interpret language, how to structure requests for different modalities, how to iterate systematically, and how to build prompt libraries that encode your creative vision. The best prompt engineers have developed intuition for what words trigger what responses in each model. This skill is foundational—it amplifies the effectiveness of every other AI creative skill. Master this, and you master the interface to all AI creation. Use when "prompt, prompting, prompt engineering, better prompts, prompt optimization, how to prompt, prompt strategy, prompt library, prompt template, make AI understand, prompt-engineering, prompting, meta-skill, ai-creative, foundational, optimization, iteration" mentioned.
Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools. Use this skill whenever the user wants to create any kind of visual from text content — including banners, article illustrations, inline diagrams, infographics, or concept visuals. Trigger on requests like "turn this into a visual", "create an image prompt", "make an illustration for this", "generate a diagram from this article", "I need a sketch for this section", or any request combining content analysis with image/visual prompt generation. Always use this skill when the user provides text content and wants an AI-ready image prompt output.
Chinese internet memes and slang, researched in real time and used naturally. Use when the user wants to add an online feel to a contemporary novel, find out what's trending on Douyin / Xiaohongshu (RedNote) / Weibo / Bilibili, ask whether a meme is still popular, or worry that adding one might feel awkward or dated. Search online for current memes and assess whether to use them, which ones to use, and where to place them based on genre, characters, and platform, avoiding forced or tacky results.
Capture ideas for Chinese web novels and turn them into drafts with one click. Use when the user has an idea to jot down, wants to develop an idea from their idea notebook into an outline or first draft, or says, “Write this idea for me.” Supports quick idea capture and the full idea-to-outline-to-draft process, with configurable total or per-chapter word counts and automatic chapter division.
Entry point and navigation for the web novel workshop. Use when the user says “I want to write a novel,” “I don’t know where to start,” “which skill should I use,” “walk me through the process,” or “help me get started”; is unsure what to do on their first visit; or wants one central entry point instead of memorizing commands. Brings 30+ skills together under four entry points (create/continue/improve/submit), guides the process based on the user’s stage, and automatically invokes the relevant skills.
Main entry point for the web novel toolkit. Automatically routes to the scanning, deconstruction, writing, AI-flavor removal, cover, import and review skills based on user needs, and can launch a local Dashboard to browse the deconstruction library and writing projects. Triggers: /story, $story, /story dashboard, $story dashboard, /网文, 「我想写小说」「帮我写书」「写网文」「英文小说」「中文改英文」「native 化」「海外发行」「打开工作台」「检查更新」。
Novel cover generation. Automatically analyzes the genre and style from the book title and author name, and calls GPT-Image-2 to directly generate a professional-grade web novel cover containing the title and author credit. Triggers: /story-cover, /封面, 「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。
Web novel AI-flavor removal. Detects and removes traces of AI writing from the text while protecting plot facts, foreshadowing, character voice and the author's own hand. Triggers: /story-deslop, /去AI味, 「去AI味」「这篇太AI了」「网文去AI味」「保留我的声线」「只检查改过的句子」.
Import an existing novel in reverse. Parses a written novel, whether unfinished or complete, into a standard project directory structure, compatible with the subsequent story-long-write / story-short-write workflows. Reuses the story-long-analyze / story-short-analyze analysis pipelines internally and automatically routes by length. Triggers: /story-import, “导入小说”, “反向解析”, “导入”, “把我的书导进来”.
Long-form web novel deconstruction. In-depth deconstruction of a hit long novel's golden three chapters, character setup architecture, payoff design and pacing control. Single deep-deconstruction pipeline: after running the golden three chapters (Stage 1), it produces a quick preview report and asks whether to continue the full deconstruction; once confirmed, it resumes from Stage 2 with chapter-by-chapter summaries, aggregate analysis, setting relationships and a summary report, writing all artifacts to 拆文库/{书名}/. Triggers: /story-long-analyze, /长篇拆文, 「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」, or providing a novel text file path — all enter the same pipeline.
Long-form web novel writing. From outline to full text, it assists the creation of Chinese long-form web novels, including worldbuilding, characters, genre contract, plotline management, branch exploration and distillation of the author's style. Triggers: /story-long-write, /写长篇, 「帮我开书」「写大纲」「分支推演」「作者文风蒸馏」「切换写作方法」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」.
Adversarial review from multiple perspectives. In full/lean mode, spawns reviewer agents in parallel when they are deployed; automatically falls back to solo if agents are missing or abnormal, or if spawning fails. Uses the built-in rubric as a fallback when reference files are unreadable. Triggers: /story-review, /审查, “审查一下”, “帮我审一下”.
Infrastructure deployment for the web novel writing toolkit. Provides built-in adapters for Claude Code / OpenCode / Codex / ZCode / TRAE Code / WorkBuddy / CodeBuddy Code / OpenClaw / Reasonix; Web AI / general Agents can use the skills + AGENTS.md file mode. Triggers: /story-setup, $story-setup, 「准备写书」「帮我搭一下环境」「配置写作项目」.
Short-form web fiction analysis. Breaks down popular short fiction across genres such as Tomato short stories, Gushi Hui, Zhihu Yanxuan, pursuit of a wife, social realism, rebirth, and revenge, examining the story core, structure, emotional arc, twists, writing techniques, and resonance. A single end-to-end analysis pipeline: runs Stage 2-6 to produce a complete analysis report, saved to 拆文库/{书名}/. The downstream story-short-write reads the analysis report, plot points, writing techniques, original text, and _meta.json together to write the next story. Triggers: /story-short-analyze, /短篇拆文, “拆短篇”, “拆这篇短文”, “短篇拆文”, “精细拆解短篇”, “8000 字短篇拆解”, “番茄短篇拆文”, “故事会拆解”, “盐言故事拆解”, “分析这篇短篇” — all enter the same pipeline.
Scan rankings of popular short-form web fiction. Analyze trending short-story data from platforms such as Zhihu Yanyan, Qimao, Heiyan, and Dianzhong to identify emerging popular themes. Triggers: /story-short-scan, /短篇扫榜, “短篇什么火”, “知乎故事排行”。
Chinese web fiction submission and acceptance diagnostics. Use when the user wants to submit or sign a contract, find out whether a manuscript can pass editorial review, write a title, synopsis, or tags, self-check the opening three chapters, record why a submission was rejected, or ask “Why wasn't it signed?” or “How can I improve my acceptance rate?” Evaluate against platform signing criteria, review submission records, and use past rejection reasons to avoid repeating mistakes.
Naming Chinese web fiction. Use when the user wants to come up with, choose, or change a title; finds a title too ordinary, too AI-like, too literary, or forgettable; or wants a list of title options. Create web fiction titles with genre keywords, satisfying hooks, and memorable appeal, while avoiding common AI-like pitfalls such as abstract literary phrasing, overused titles, and missing keywords.
Create video clips or images into finished MP4 videos with this skill. Works with MP4, MOV, JPG, PNG files up to 500MB. Content creators and small business owners use it for generating short videos from images or clips without editing software — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Gets a finished video out on YouTube (Shorts or long), Instagram Reels and TikTok - picks the video, makes the light export for Instagram and TikTok, the cover, the caption and the YouTube title, sets the time, shows the plan, then after the creator's yes publishes through Treg on their own connected accounts (setup included), or hands a ready-to-post kit when Treg isn't set up. Use when the user says publish, post it, schedule, upload to YouTube, put it on Instagram, TikTok, publier, poster, programmer, mets-le en ligne.
Translates a talking-head take (or a finished video) into another language with the creator's own cloned voice through ElevenLabs Dubbing, using their ElevenLabs API key - sets the key up, trims the take first so no stutter is paid for, estimates the minutes, sends it after a yes, waits, lays the dubbed voice back on the image, then hands the translated take to video-edit for captions in the new language. Use when the user says translate, dub, dubbing, English version, Spanish version, traduis, version anglaise, doublage, ElevenLabs, or wants a second account in another language.
Creates product documentation systems with help pages, AI-generated screenshots, Remotion product tours, GSAP animation, narration scripts, TTS, background music, README visuals, and deployment steps. Use when the user asks for product docs, help pages, documentation videos, narrated tours, screenshots, README media, Remotion docs workflows, or webconsulting-style documentation assets.
Skill for creating and editing Youtube thumbnails that are optimized for click-through rate. This skill should not be used directly, instead use the Thumbnail Designer subagent who can also invoke this skill. Use when the user asks to create a thumbnail from scratch or edit an existing thumbnail.
Detects AI-written text, scores it against a detection rubric, provides line-by-line edit recommendations, and rewrites content to sound genuinely human. Use when the user asks to 'humanize' text, detect AI writing, remove 'AI voice,' make copy 'less robotic,' pass AI detection tools, or rewrite content to 'sound human.'
Expert patterns for AI-powered image editing including inpainting, outpainting, ControlNet, image-to-image, and API integration with Replicate, Stability AI, and FalUse when "ai image editing, inpainting, outpainting, controlnet, image to image, remove object from image, extend image, flux inpaint, sdxl editing, image-editing, inpainting, outpainting, controlnet, stable-diffusion, flux, replicate, stability-ai, comfyui" mentioned.
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
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 ai-product-video to make a video/promo", names the Ink Press template or asks to reproduce its effect, or wants a single shot card's motion. 用镜头配方卡 + 已验收模板 + 代码/音频资产制作电影感产品视频（Remotion + 真实页面截图 + 2.5D 运镜 + 节奏卡点 + 声音设计）。当用户要求"用 ai-product-video 做视频/宣传片"、把前端项目/网页做成产品视频、点名 Ink Press 模板或要求复刻模板片效果，或要用镜头卡做单个动效镜头时使用。
This skill should be used when the user asks about "animation", "storyboard", "animatic", "pre-visualization", "previz", "character design", "motion planning", "animation storyboard", "act as an animation designer", "animation mode", "character design brief", "animation pipeline", "2D animation", "3D previz", "frame-by-frame", "keyframe planning", "storyboard pro", "toon boom", "animatic timing", "shape language", "turnaround sheet", "motion reference", "animation layout", "previz workflow", or needs expertise in storyboard design, animatic planning, character design briefs, and motion planning for animation. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "film festival", "festival submission", "logline", "synopsis writing", "director's statement", "festival strategy", "act as a festival strategist", "festival mode", "film submission", "short film festival", "festival circuit", "premiere strategy", "FilmFreeway", "Withoutabox", "press kit for film", or needs expertise in festival submission materials, loglines, synopses, director statements, and festival circuit planning. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "AI dubbing", "video translation", "ElevenLabs dubbing", "Dubbing Studio", "translate my video", "multilingual dubbing", "automatic dubbing", "dub into Spanish", "dub into Turkish", "dub into Japanese", "speaker detection", "subtitle translation", "video localization", "act as a dubbing specialist", "dubbing mode", "lip sync dubbing", "YouTube dubbing", "language pair quality", "dubbing QA", "post-delivery QA", "dubbing review checklist", or needs expertise in AI-powered video dubbing workflows, transcript editing, multi-speaker voice matching, language-pair quality assessment, and timing synchronization on ElevenLabs. Part of the AlterLab FC Skills collection (GenAI pack).
This skill should be used when the user asks about "AI motion design", "Higgsfield effects", "AI VFX", "style transfer video", "Ghibli anime style", "watercolor animation", "draw to video", "sketch animation", "Soul Inpaint", "Kling Video Edit", "AI video transitions", "video effects layering", "motion pacing", "act as a motion designer", "motion designer mode", "AI video compositing", "Canvas workspace", "batch video generation", "video style consistency", "multi-shot sequencing", "social media motion graphics", "Higgsfield presets", "effect presets", "visual identity guide", "content series branding", "Sora 2 VFX", "Kling 3.0 effects", "Veo 3.1 motion", "Higgsfield Assist", "Soul Cast", "content scoring", or needs expertise in AI-powered motion design, visual effects, and style transfer using Higgsfield. Part of the AlterLab FC Skills collection (GenAI pack).
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.