Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
This skill provides screenplay action and description writing techniques. Covers present tense formatting, visual storytelling, action sequences, and paragraph structure for scene descriptions. Use when: writing scene descriptions, crafting action sequences, describing visual storytelling, or formatting action paragraphs in Fountain format.
A comprehensive suite of protocols, meta-prompts, and orchestration tools designed to streamline software development workflows, project management, and team collaboration. Includes the VibeCode Protocol Suite with web interface, user manuals, and reusable templates for efficient development processes
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
Interview-driven blog post drafting for technical product audiences. Use when user wants to write a blog post, article, or essay and needs help developing their thesis, structure, and initial draft. Triggers on "write a blog post", "draft an article", "help me write about X", "blog drafter", or when user has a topic they want to turn into written content. Conducts structured interviews using AskUserQuestion to extract the user's unique insights before generating drafts.
Write essays and micro-essays using the user's World Code voice and worldview. Use this skill whenever the user asks to write an essay, micro-essay, short-form prose, or insight-dense writing about a topic. Also trigger when the user says "write about X", "essay on Y", "micro-essay about Z", "write something about", "explore this idea", or any content creation request that should feel like cross-domain, opinionated prose. If the user mentions essays, writing about concepts, or creating insight-driven content of any kind, use this skill.
Resizes, scales, and adjusts video resolution and dimensions using GPU-accelerated NVENC encoding via Volcengine LAS. Video resizing, video scaling, video upscaling, and video downscaling — change video resolution, enlarge or shrink video dimensions, and adjust video size for different platforms and screens. Video compression by reducing resolution and video transcoding and re-encoding with specific dimension constraints. Supports flexible min/max width and height ranges with aspect ratio preservation strategies (increase, decrease, or disable), including landscape to portrait conversion. Async submit-poll workflow with batch support. Use this skill when the user wants to resize or scale video resolution (upscale/downscale), change video dimensions for different platforms, compress videos by reducing resolution, transcode/re-encode videos with GPU NVENC, adjust aspect ratio including landscape-to-portrait conversion, adapt videos for mobile/web/social media, or batch process multiple videos.
Control camera behavior in Decentraland scenes. CameraMode detection, CameraModeArea (force first/third person in regions), VirtualCamera (cinematic scripted cameras), MainCamera (read position/rotation), and camera-triggered events. Use when the user wants camera control, cutscenes, cinematic views, forced camera modes, or camera tracking. Do NOT use for input restriction during cutscenes (see advanced-input for InputModifier).
Create beautiful visual artworks in .png and .pdf formats using a design philosophy. Use this skill when the user asks for posters, artworks, design pieces, or other static works. Create original visual designs; never copy existing artists' works to avoid copyright infringement.
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.
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.
This skill should be used when the user asks to "compress this video", "reduce file size", "make this video smaller", "optimize for web", "shrink this video", "compress to under X MB", "reduce bitrate", "make it smaller without losing quality", "encode with H.265", or "re-encode this video".
Train a model on a novel, then continue writing in that novel's world — with memory of characters, places, and recent events. Load this skill whenever the user asks to train/fine-tune/learn the style of a novel or .txt, mentions Echo-Quill / Alchemist / 炼金 / 双塔, asks to open the training dashboard, asks how the system works, asks to stop or restart the training services, asks to write/continue text (with or without memory), asks to train an additional chapter or continuation they wrote, or asks to roll back to the original-novel state. The skill manages a local FastAPI backend + Vite/React dashboard, dependency installation, .env scaffolding, training, memory-mode continuation, pure-style continuation, and rollback — the user supplies a novel path or a passage, the skill handles everything underneath.
Conversational video editing: transcribe, plan edits using transcript analysis, and render. Use when: (1) User wants to edit a video by reviewing its transcript (2) User asks to trim, cut, or rearrange video segments (3) User wants to create a highlight reel or narrative cut from a longer video (4) User mentions EDL, transcript analysis, or video editing workflow (5) User wants to remove filler, dead air, or silence from a video (6) User wants to combine multiple clips into one video Triggers: "edit video", "transcribe video", "trim video", "cut video", "EDL", "video editing", "remove filler", "combine videos", "stitch clips", "multiple clips", "add captions", "shorts captions", "burn captions"
Video and audio processing with FFmpeg. Covers transcoding, resizing, trimming, speed adjustment, compression, audio extraction, concatenation, cropping, thumbnails, and probing. References available for codec/filter lookup, audio processing, streaming formats, Remotion integration, and platform export.
This skill provides comprehensive film and television industry terminology. Covers production terms, script coverage vocabulary, development jargon, and professional communication standards from A-Z. Use when: encountering unfamiliar industry terminology, writing professional correspondence, understanding script coverage or notes, or communicating with industry professionals.
Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls `runcomfy run openai/gpt-image-2/edit` through the local RunComfy CLI. Triggers on "gpt image edit", "gpt-image-edit", "chatgpt image edit", "edit with gpt image 2", or any explicit ask to edit with this model
Generate Chinese-language illustrations built on "Xiaohei + real objects + physical action + narrative whitespace". Default output is a 16:9 inline illustration for internet-worker relatability images, workplace anxiety in the AI era, the situation of programmers/product people/creators, and visual metaphors for article arguments; for "easter egg mode / long-scroll story image / extra-wide format / personal experience / project retrospective / product evolution / growth path", output a Xiaohei long-scroll story image. Standard mode defaults to a #FFFFFF pure white background; easter egg long-scroll mode uses a premium near-white background and one real-object life line. Samples are high-quality template masters and quality benchmarks for output; proportions, whitespace, action clarity, and narrative relationships must be aligned with them, but their object combinations, spatial topology, Xiaohei poses, or label positions must not be replicated.
Describe images, screenshots, diagrams and charts from visual inspection. Preserve visible text, counts, labels, directions and uncertainty; distinguish observation from interpretation. Use for image summaries, screenshot explanations and diagram descriptions.
Write multi-chapter books (technical, tutorial, monograph, etc.) end-to-end. Handles outline planning, per-chapter drafting that stays coherent across long manuscripts, chapter review, and final HTML/PDF build. Trigger when user mentions "写书", "写一本书", "出书", "技术书", "book writing", "逐章写作", "O'Reilly", "mdbook", or wants to author a multi-chapter book.
Interact with Narrative Lion — generate notes from YouTube, search your knowledge base, chat with notes, produce AI video shot pipelines, generate short-form video scripts, and export. Use when the user wants to "create a note from this video", "search my notes", "chat with my notes", "create a filmwork project", "generate a reel/short script", or "export my notes".
Use when the user wants to generate images from the current agent context through configured PicGen providers. Trigger directly only on explicit image-generation requests or when the user names PicGen; ask for confirmation for strong visual-output intent; only suggest PicGen for weak visual exploration intent.
Plans and builds a roughcut, sequence, or scene from a library. First walks the user through shaping a plan (concepts, beats, length, footage), then builds the timeline as YAML and exports XML for Final Cut, Premiere, or Resolve. Use when the user asks for a "roughcut", "sequence", or "scene".
Seedance 2.0 AI video generation via EvoLink API. Three modes — text-to-video, image-to-video (1-2 images), reference-to-video (images + videos + audio). Auto audio (voice, SFX, BGM). Works with OpenClaw, Claude Code, Cursor. Powered by ByteDance Seedance 2.0.
Generates walkthrough videos from Stitch projects using Remotion. Downloads screenshots from Stitch screens, builds a Remotion composition with transitions and text overlays, and renders to MP4. Use with stitch-mcp-list-screens and stitch-mcp-get-screen for screen discovery.
Generate article or newsletter thumbnail candidates using the Gemini API from inside Claude Code. Claude reads article copy, proposes composition concepts, writes image generation prompts incorporating brand specs, calls Gemini to generate the images, evaluates the results via computer vision, and returns ranked candidates with rationale. Use when asked to create thumbnails, generate cover images, or produce visual candidates for an article or newsletter.
Downloads videos from YouTube, TikTok, Douyin, Bilibili, Instagram, XiaoHongShu and 1000+ platforms. Primary: yt-dlp. Fallback: agent-browser + GreenVideo for Douyin/TikTok when yt-dlp fails. Use when user says "download video", "save video", "grab video", "watermark-free download", or pastes a video URL. Do NOT use for AI video generation or video editing.
Transform song lyrics into vivid visual scene descriptions and image generation prompts. Use when user says "visualize these lyrics", "turn this song into images", "create visuals for this track", or provides song lyrics and asks for imagery. Filters for concrete imagery and renders each distinct scene as a numbered canvas.
Analyze writing samples to create a codified voice style guide. This skill extracts patterns, techniques, and characteristics from example writing and generates a reusable voice skill that can be used with anti-ai-writing for consistent, authentic content creation. Use when establishing a new voice style from scratch.
End-to-end writing assistant for WeChat Official Account articles. Supports trending topic selection, article writing, AI de-flavoring polish (removing the machine feel), image suggestions, and one-click publishing to the Official Account drafts folder. Suited to technical bloggers, self-media creators, and corporate Official Account operations. Use this skill when users need to write Official Account articles, polish content, find images, or publish to WeChat.
A writing-style DNA profiling skill for WeChat official account authors. Builds a reusable style profile from 3-10 reference articles, outputting a 14-dimension analysis, punctuation preferences, chunking habits, paragraph recipes, a narrative method system, content progression approaches, and a default DNA file, with user calibration to ensure the profile can be called directly by writing skills.
Generate, derive, optimize, and diagnose structured AI image prompts for luminous cinematic Eastern xianxia environments under one inherited master canon with measurable divine scale, fixed five-layer space, 40–60% content-bearing breathing air, monumental Eastern architecture, railing-free edges, and coherent immortals and costume. Cover one-location scenic landmarks, immense inhabited celestial realms, cloud-borne palace cities, high-key Eastern sky-megastructure imagery, and the explicit `仙界大境原典` creative route. Use for Chinese fantasy scenery, places where immortals live, heavenly capitals, colossal celestial gates, architectural fragments above cloud seas, measurable divine scale, unusual framing, color and lighting direction, style-preserving variants, prompt rewrites, diagnosis, or direct image generation. Support 16:9, 21:9, 4:3, 3:2, 4:5, and 9:16; default to 16:9 for one prompt and never infer a nine-image series from a vertical ratio.
AI developer release assistant — automates the full GitHub project release workflow. Collect competitor information → AI-generate project cover image → one-click publish an in-depth analysis article to WeChat Official Account. Activated when the user needs to "release an open source project", "write a release announcement", "make a product introduction", or "generate a project cover".
Complete AI video production workflow skill. Use when: 1. the user asks to "make an AI video", "do AI video", or "AI video creation" 2. the user mentions "video workflow" or "video production process" 3. the user needs systematic guidance for AI video production. Core: a seven-step process + polishing checks throughout every step + prompt templates
Script creation - short video scriptwriting and storyboard design. Responsibilities: produce content based on viral templates, design golden 3-second opening options (3 or more), write storyboard scripts (including camera language / scene atmosphere / character actions / lines / BGM), design talking points, memes and emotional hooks, plan the ending call to action, automatically recommend Vidu video generation settings (model version / generation method / duration / aspect ratio), ensure character consistency, and pass complete storyboard information to video generation (Leo). Use cases: (1) short video scriptwriting (2) storyboard design (3) content creation (4) video planning
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.