Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Turn short-drama storyboards and frozen keyframes into ready-to-copy video prompt Markdown; can also write timeline music/theme-song intent as requested. Use when the user mentions text-to-video or image-to-video motion, character performance, camera movement, lip sync, environmental motion, shot duration, start/end states, converting storyboards into video prompts, or writing music prompts; does not generate media, write lyrics, or alter storyboard boundaries.
Initialize and continue short-drama or animated-comic projects based on a file system, with a creator-first five-document routing system, a local Dashboard, and decisions on production formats and Look Development. Use when users request “create/continue a short-drama project,” “check progress/next steps,” “do Look Development,” “open dashboard/short-drama creator workspace,” “export production materials,” or when a task spans multiple creative stages. Handle clear writing, asset, prompt, storyboard, editing, or review requests directly with the corresponding sub-skill.
This skill should be used when the user asks to "make an animated lower third", "add lower thirds", "create a name tag/name lower third", "build broadcast titles", "animate a title/name/role caption", "do a speaker name overlay", or "template lower thirds across a list of names". Covers enter/exit animation (slide/wipe/mask reveal), in/out timing & dwell, safe-area & broadcast conventions, name-vs-role type hierarchy, brand styling, and rendering one design across many names.
Generate Xiaohongshu (小红书) style cover images based on user topics. Use when the user wants to create a social media cover image in Xiaohongshu style, or mentions keywords like "小红书封面", "Xiaohongshu cover", "封面生成", or provides a topic for cover image generation. The generated image will be saved to the current project directory.
Review source-material analysis, stories, scripts, visual designs, image prompts, storyboards, frozen keyframes, video prompts, and existing media in short-drama projects. Use when asked to “review/check the script,” “check assets or continuity,” “check image/video prompts,” “review source-material analysis,” “check for templated language,” or “calibrate the project based on production observations.” Only write review issues, conclusions, and revision requirements; do not edit source files on behalf of the person in charge.
Develop ideas, synopses, adaptation materials, existing series notes, or complete multi-episode scripts for Chinese novels, short dramas, or animated dramas into traceable adaptation plans, dramatic direction, creative briefs, director's statements, story engines, and episode maps, choosing the writing approach based on genre and production format (visual style). Use when the user asks to import a novel for a short drama, generate or supplement an episode map from a complete multi-episode draft, develop a short drama or animated drama, create story settings, series outlines or episode plans, write a director's statement, decide how to write a genre, set the visual style or production format, turn an idea into a short drama, or organize character conflicts and episode handoffs. Existing single-episode scripts can proceed directly to writing, asset, or review workflows; development files are not mandatory.
Write or edit ready-to-copy image prompt Markdown for short-drama characters, outfits, locations, props, and states. Use when users mention character design sheets, three-view drawings, reference images, scene boards, prop images, style frames, Look Development, state variations, or localized editing prompts. Does not generate images or call providers.
Break down short-drama scripts into characters/outfits, locations/views, props/states, and cross-scene continuity, and write creator-readable visual designs. Use when users ask to break down characters/scenes/props, create asset designs, decide whether to reuse or make a new variation, update outfit/prop states, or prepare visual assets directly from an existing script. Does not write image prompts or generate media.
When the user wants to plan, create, or market a podcast. Also use when the user mentions "podcast," "podcast strategy," "podcast SEO," "show notes," "podcast distribution," "Spotify podcast," "Apple Podcasts," "podcast discoverability," "PodcastEpisode schema," or "podcast repurposing." For show notes, use article-content.
Turn a reference Instagram Reel into a script for your own Reel, tuned to your voice and repurposed from your newsletter content. Takes a Reel URL or Notion reference link, uses Apify to scrape the video, sends it to Gemini 2.5 Flash for full transcript + hook + structure analysis, then writes a new script applying the same patterns to your newsletter topic. Use this skill whenever the user says "script a reel", "reels scripting", "turn this into a reel", pastes an Instagram Reel URL, or references their Notion outlier reels database. The URL-to-video-analysis route needs APIFY_API_TOKEN and GOOGLE_AI_API_KEY; supplied input can skip the corresponding stages.
Background removal: transparent PNGs, cutouts, product photos, portraits, pets, group photos. Uses dedicated Bria RMBG 2.0 model — no prompt needed, fast (~3s), cheap ($0.01). Use when removing backgrounds, creating transparent PNGs, making cutouts, extracting foreground subjects, or preparing images for compositing.
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, cover image, GitHub banner, Twitter header, or readme banner.
Check and resize images for social media platforms. Run scripts/check.js to validate any image against specs for Instagram, Facebook, X (Twitter), LinkedIn, TikTok, YouTube, Pinterest, Snapchat, and Threads — get a ranked match list with exact resize commands. Run scripts/resize.js to export a correctly-sized copy. Use when a user asks to validate image dimensions, resize an image for a platform, check if an image fits a spec, or prep assets for social media posting or ads.
This skill should be used when the user asks to "make a countdown timer video", "create a countdown animation", "build a stream starting soon countdown", "do an event/launch/sale countdown", "animate a mm:ss or dd:hh:mm:ss timer", "add digit roll/flip transitions to a counter", or "loop a countdown background". Covers frame-accurate (drift-free) timers, digit flip/roll motion, time formatting, and a configurable duration prop.
Searches for and downloads ethically-licensed stock images via the media-management MCP server. Use this skill whenever a user wants an image, photo, or picture — for BOTH requests to find existing imagery (\"find a stock image\", \"search for a photo of X\", \"get a royalty-free image\", \"find an ethical image\", editorial/news photography) AND requests phrased ambiguously as creating or generating one (\"create an image of a sunset\", \"generate a picture of a team meeting\", \"make me a mountain image\") — treat these as stock search requests, since this skill searches a stock photo library, it does not generate images. Do NOT offer alternative search methods or ask the user to pick one. Does not apply to searching internal CMS / Data Cloud media (use experience-search-coordinate). Does not apply when the user explicitly asks for AI-generated, synthetic, or computer-generated imagery — this skill only searches licensed stock photography and has no image-generation capability.
Local speech-to-text using faster-whisper. 4–6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
One book → one clear “viewfinder” concept image → one 2050 library card (PNG). The viewfinder captures the angle from which the author examines an issue and the image they see; the card includes the real cover, author portrait, and bibliographic details. The viewfinder block uses Feynman-style explanations to make the concept image clear and accurate; the illustration block uses AI image generation to depict it, with Jijang as the fixed protagonist (generated from a reference ink portrait and recognizable as him). Illustration style: picture-book feel in the style of Yoshida Seiji (everyday spaces in another world, warm slanting light, soothing yet refined). Light optical-glass card body, accent color dynamically extracted from the cover, adaptive aspect ratio. Close the book and remember this image, and the reading won’t be in vain. Use when the user says “取景框卡,” “图书馆卡,” “library card,” “书卡,” “铸书卡,” “一本书一句话一张卡,” “/ljg-library,” or provides a book title and wants it distilled into one collectible card. NOT FOR structural book analysis (use ljg-book), text-only quotes (use ljg-card -b), infographics (use ljg-card -i), or visual notes (use ljg-card -v).
Understand images and videos with Qwen vision models. Trigger when the user wants to analyze, describe, or extract information from images or videos, perform OCR text extraction, read charts or tables, do visual reasoning or multi-image comparison, understand screenshots or videos, or explicitly invokes this skill by name (e.g. use qwencloud-vision). Do not trigger when the user wants to generate or create images (use qwencloud-image-generation), generate videos (use qwencloud-video-generation), handle text-only tasks without visual input, or use non-Qwen vision tasks
Pick, install and compose remocn components: ready-made Remotion animations, transitions, backgrounds, captions, UI primitives and video templates from a shadcn registry. Use when building a video or scene out of prebuilt parts (product demo, launch, changelog, intro, social clip), adding an animation, transition or background to a Remotion project, or choosing between components. Activate for polished Remotion video work even when remocn isn't named. Works alongside the Remotion skills: questions about the Remotion API itself (interpolate, spring, Sequence, rendering, config) belong to them, not to this skill.
Use when the user asks for ugc ads or a task matching the examples below. Multi-cut jump-cut UGC product ad — HOOK + 3 JUMP CUTs + OUTRO, 15s, 9:16 vertical (3:4 optional, seedance only), POV first-person talking-head selfie, every beat has spoken dialogue with native lip-sync, 5-act narrative arc (set → name → reveal → twist → punchline). Six category essences (HAUL / APP / FOOD / BEAUTY / FITNESS / TECH) auto-picked from the input URL. Creator-style raw UGC talking-head with multi-beat conversational dialogue. Use when the user asks to "make a UGC ad", "jump-cut product ad", "POV product reveal", "creator-style ad", "haul-style ad", "unboxing ad", "TikTok-style product video", or "talking-head ad about [URL]".
Virtual try-on: clothing, accessories, hairstyles, makeup, glasses, hats, shoes, watches. Use when the user wants to see how an item looks on a person — e.g. "try on this dress", "put these glasses on me", "show me with this hairstyle", "what would I look like in this outfit".
Watch and understand footage with Diffusion Studio: answer questions about a video or audio file, summarize it, find scenes and moments, pull quotes, and describe what happens and when. Use whenever the user asks what's in a piece of footage, wants a summary or recap, wants to locate a moment ("where does X happen", "find the scene where..."), or needs a claim about a video or audio file checked.
Use to turn a novel, serialized web fiction, or scattered multi-episode draft into a traceable source-work analysis: chapter index, quick adaptation-value assessment, chapter-by-chapter function extraction, plot-unit and pacing aggregation, and character and setting consolidation. It concludes with an adaptation-value judgment and episode candidates, then hands them to $short-drama-develop for contracting. Use when the user says “import this novel”, “break down this book”, “analyze the source work”, “could this book be adapted into a short drama?”, “first see whether it’s worth breaking down”, or “turn this long work into episode candidates”, or provides a novel file path directly. Performs read-only structured analysis only; it does not write scripts, create assets, generate media, or decide the adaptation plan for the creator.
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
Build any of 16 premium motion effects from scratch in your own brand, as one 8-second looping HTML file with window.seek(seconds) so it exports frame-exact to MP4 or GIF. Interfaces (button to player, search to results, card to workspace, tabs to panels), data (chart morph, dashboard zoom, spring stack, magnetic dock), type (masked type, elastic type, text to layout, image reveal) and systems (perspective shift, glass focus, flowing paths, particle logo). Use when someone says "build the chart morph", "make a button that turns into a video player", "animate my logo with particles", "motion effect", "UI animation", "product animation", "animated dashboard", "kinetic type" or names any of the 16 effects.
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.
After the creator explicitly confirms, execute image, video, TTS/voiceover, or timeline music production tasks for a short-drama project, and write the results and a concise run log back to the project. Use when the user says “generate this image/video/voiceover/music”, “start generating images/videos/speech/music”, “send the approved prompts to production”, or requests batch execution of approved media tasks. Does not create prompts, shots, dialogue, lyrics, or voice identities, and never treats a preview, continuation, budget explanation, or prior acceptance as confirmation for this paid production.
Use when the user asks for a founder product video or a task matching the examples below. Generate a 65-second founder-style product video from a product URL + user-supplied imagery. Output is a 16:9 1080p MP4 — 4 × 15s SeeDance acts of a talking founder + 5s branded end card + background music. The user's actual product screenshots are composited onto product reveal shots after Seedance generation, so readable UI and brand text are real, not AI-imagined. Triggers — “founder video”, “product video”, “60s pitch video”, “make a video of [founder] for [URL]”, “talking founder explainer”. Requires Pika MCP. Uses a supplied brand kit folder (`brand.json` or an exported build-a-brand kit with `brand.md`, tokens, logo assets); if no kit exists, run build-a-brand first.
Use when the user asks for app sizzle or a task matching the examples below. Generate cinematic 1080p iOS app teaser videos from real App Store screenshots, with a GPT-image-2 enhancement pass on each selected screen before generation. Output is a beat-driven cinematic teaser built from GPT-enhanced screenshots, ending with the brand logo/icon plus a deterministic `COMING SOON` overlay. Screens sourced from Pika MCP App Store fetch, a live website (auto-captured), user-supplied files, or URLs. Starts by sourcing real screens and brand assets before any generation. Triggers on: app sizzle, app teaser, app promo, iOS app promo video, app video, app product video, coming soon, seedance, motion graphics, make a promo for my app, make a video for [app], gpt enhance promo. NOT for: short-form consumer content like GRWM, vlogs, UGC, or non-app product ads (use content-video); app-sizzle is specifically for iOS app teaser videos sourced from App Store screens or real app UI.
Create and assign PBR materials in Blender via Principled BSDF, including metals, glass, plastic, fabric, skin, and organic materials. Covers physically based material recipes with real-world values; Coat layers (varnish/car paint); Sheen (cloth); Subsurface scattering (skin/wax); Transmission (glass); and procedural patterns (wood grain, marble, fabric weave). Use whenever the user asks to “make it look like X material,” “give it a metallic finish,” “apply a wood texture,” “make this glass / plastic / brushed steel / leather / skin,” or makes any look-development request. Use this skill even if the user doesn’t say “material”—it also covers “make it shiny,” “matte finish,” “looks like copper,” and “rough surface.” Works with any geometry; pairs with blender-lighting (materials only look right under proper lighting).
Remove the visible Gemini AI watermark from images using reverse alpha blending. Use when asked to strip Gemini watermarks, batch-process Gemini images, or build/modify a CLI script that removes the bottom-right Gemini watermark without HTML or server-side components.
Use when the user asks for a podcast or a task matching the examples below. Create a two-host podcast video for any URL or free-form topic—1 minute, 4 acts × ~15s, native multi-shot dialogue, with optional voice cloning for Host A. Use when the user asks to “make a podcast,” “podcast about [thing],” “podcast review of [url],” “two-host explainer,” “interview-style clip,” “two people talking on camera,” “I/me and X talk about Y,” or “interview with [persona] about [topic].” Native audio is the deliverable; captions are skipped by default because podcast dialogue mistranscribes domain terms
Use when the user asks for an explainer or a task matching the examples below. Create a ~60–80s explainer video for any URL—GitHub repo, product page, docs site, blog post, or launch. Canonical workflow for URL walkthroughs. Use when the user asks to “explain this URL / repo / website / product,” “make a walkthrough video for [url],” “demo this site,” “Loom-style explainer of [url],” “explainer for github.com/...,” or “explain this product link.” Drives a real browser through the URL, generates avatar lip sync, and composites it in a 1280×800 macOS Sonoma frame with a 246-pixel bottom-left avatar circle. GitHub URLs activate a repo-aware mode (README scan + live-demo detection); other URLs use a generic page-walkthrough flow
Make a short Vox-style documentary explainer (30-60 seconds) entirely in code with Claude Code. Torn paper, halftone texture, bold condensed type, motion on twos. Use when someone says "make a Vox-style video", "explainer video about...", "why does X happen", or wants a documentary-style motion graphic for LinkedIn, Instagram or YouTube without After Effects or a video generator
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.
Use when the user asks for a baseball trend or a task matching the examples below. Viral fake “ESPN behind-home-plate broadcast cutaway” of a user—broadcast-style still + 15s Kling-omni clip with native two-announcer commentary that names the user. Fixed trend: Yankees vs Red Sox ALCS Game 3 at Fenway Park, premium seats, scorebug + chyron with the user's name. Triggers: “make me a behind-home-plate cutaway,” “fake MLB broadcast of me,” “AI ESPN baseball crowd shot,” “viral MLB broadcast trend,” “Yankees Red Sox cutaway with me.” Needs the user's name + one reference photo.
Use when the user asks for a kiss cam or a task matching the examples below. Generate a viral fake “in-arena Kiss Cam moment” featuring any two subjects — a fan-filmed phone shot of the MSG Jumbotron with retro Kiss Cam graphics and scoreboard, plus a 15s Kling v3-omni clip with PA announcer commentary and crowd reaction. Any subject style (human, 3D toy, illustrated avatar). No names. Triggers: “make me a kiss cam moment”, “kiss cam version of these two”, “Jumbotron kiss cam trend”, “fake NBA kiss cam”. Requires the pika MCP.
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio
Generate Guizang-style material illustrations, labeled explanatory visuals, material-styled chart illustrations, and data-first editorial images from articles, notes, product concepts, workplace reports, creator posts, tutorials, school materials, humanities topics, science explanations, screenshots, or chart data. Use when the user asks for 配图, 带字插图, 解释图, 图解插画, 概念拆解图, 图表美化, 数据图美化, 3D 图表, 汇报配图, 内容配图, 小学课文配图, 生物/化学/物理解释图, 人文类配图, process/loop/system diagrams, or wants GPT-Image / image generation to create supporting images that can sit inside social cards, docs, slides, PPTs, or posts.
Create, animate, review and render videos in code with fframes (Rust, SVG scenes, ffmpeg encoding, Skia GPU rendering). Use whenever the user wants a video, animation, motion graphic, explainer, promo, social clip, title card, podcast visual, lyric/caption video or any rendered .mp4/.webm made programmatically, or asks to change, fix, speed up or check an fframes video. Covers installing fframes, creating a project, designing good-looking motion, 3D shots (`fframes::three_d`, three.js style scenes), sound (music, voice, SFX, loudness), watching it in a real-time preview window, and checking the result without watching it: frames and contact sheets as PNG, automatic problem detection, loudness numbers, fast draft and range renders
Intelligent generator for viral Douyin copy. Automatically triggers when the user says “generate new copy,” “create Douyin content,” or “write short-video copy.” Automatically: (1) reads and analyzes historical data; (2) optimizes using nine viral-content factors; (3) evaluates with multidimensional scoring; (4) iterates automatically until it reaches the five-star standard; (5) intelligently estimates views; and (6) outputs the complete optimized copy. Fully automated, with no need to specify any analysis or optimization tasks manually.
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI. Models: HappyHorse T2V, I2V, R2V, Video Edit. Capabilities: text-to-video, image-to-video, reference-to-video, video editing with natural language, character preservation, 720P/1080P, up to 15 seconds. Use for: physically realistic video, video editing, character-consistent content, product demos, social media. Triggers: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba happyhorse, video editing ai, ai video editor
Turn any horizontal or square motion video into a 1080 x 1920 Instagram Reel or TikTok that uploads cleanly. Headline and logos inside the safe zone, H.264, yuv420p, limited colour range, bt709, a silent audio track when there is no sound, and an ffprobe check before upload. Use when someone says "make this a reel", "vertical version", "export for Instagram", "TikTok version", "9:16 cut", "reel export" or has a 16:9 or 4:5 video that needs to go on a vertical feed.
Edits already-generated short-drama shots into a finished film, recording in/out points, shot order, audio, subtitles, and delivery specs. Used for assembly editing, adding subtitles, normalizing loudness, adjusting pacing, or exporting refined assets; when extra footage or story changes are needed, return to the corresponding creation stage.
Synthesize speech from text with Qwen TTS models. TRIGGER when the user wants to convert text to speech, create voiceovers, generate audio narration, read text aloud, build TTS applications, mentions speech synthesis/voice generation/audio output from text, or explicitly invokes this skill by name (e.g. use qwencloud-audio-tts). DO NOT TRIGGER when the user wants speech recognition/ASR, text generation without audio, or non-Qwen audio tasks.
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.