Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
The pre-production system — turn a video idea into a shootable, editable plan: the two-column AV script, the storyboard as a decision document, the numbered shot list, the batch-shoot plan, and the paper edit. Use when shoots are chaotic, edits drag, videos feel static ("just me talking"), someone wants to batch-film a week of content in one session, needs a storyboard but can't draw, is planning a multi-shot AI video sequence, or scripts keep running long. Uses the SCENE framework. Reads idea-generation-and-ideation + short-form-video-script or the long-form skill + brand-profile first. A words-only script plans half the video; the storyboard is a decision document, not art; the shot list grouped by setup enables batch shooting. The agent writes the plan; the HUMAN shoots/generates and judges; WoopSocial publishes. Never stages candid-as-real moments or lifts another creator's script. Distinct from short-form-video-script, talking-head-and-piece-to-camera, capcut/descript, luma.
Orchestrate a fail-gated, source-locked Blender reconstruction of mascots, logos, brand avatars, and stylized flat characters from wireframes, texture packs, and orthographic views. Use when the user requires a 1:1 brand/model match rather than a plausible stylized interpretation.
Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text descriptions, generate artwork in various styles, create visual content for creative projects, or need AI-powered image generation capabilities
Ensure textures and decals cover all visible surfaces of a closed or extruded Blender asset, especially front/back caps and sidewalls, instead of relying on partial projected planes, curves, or linework overlays. Use when back textures do not fill the model, side textures are missing, spin/turntable views expose plain sidewalls, or a model needs separate UV treatment for caps and side surfaces.
This skill should be used when the user asks to "create a character", "update a character", "add a character", "build a family tree", "character relationships", "character timeline", "character arc", "character profile", "relationship graph", "name a character", or needs to manage characters in a story project. NOT for recording or checking character voices (use voice-style), rewriting dialogue so the voices differ (use line-editing), or a thematic arc's lie, truth, and arc type (use theme-craft).
Determine whether front/side/back/top reference templates can be satisfied by one rigid 3D Blender model, choose a canonical source policy, and emit constraints before rebuilding. Use when multiview bboxes, silhouettes, part counts, or depth ratios contradict each other.
Transform a user-supplied photo into a vertical 3:5 Gathered Scenes Zine poster that anchors truthful photography inside a spacious source-derived abstract illustration field, aggressively compresses dense foliage and other micro-detail into a few large quiet forms, integrates one high-chroma hue as compositional structure, and preserves a visibly hand-torn fibrous photo-to-paper edge. Use when the user wants a tactile minimal paper collage with simplified illustration, active negative space, restrained English-default, Chinese, or bilingual micro-text, and an unmistakable but quiet torn-paper boundary.
Discovers viral content trends and trending formats on TikTok using apidojo's TikTok scraper on Apify. Triggers when the user asks to: find trending content formats on TikTok, discover what is going viral on TikTok in a niche, identify viral TikTok hooks or video styles to adapt, research TikTok trends for a product category, find what content formats are performing best on TikTok right now, discover trending sounds or concepts in a niche on TikTok, or analyze what drives viral TikTok engagement in a specific category. Returns trending hashtags, view counts, engagement metrics, content format patterns, and hook analysis. Ideal for TikTok content creators, brand social teams, and video content strategists.
This skill should be used when the user asks to "write a chapter", "next chapter", "chapter outline", "draft chapter", "continue the story", "write a scene", "outline a chapter", or wants to write prose for a story project. NOT for planning a scene's structure, subtext, or outcome (use scene-craft), drafting without an outline (use discovery-drafting), or revising existing chapters (use revision-continuity).
Design graphic assets with Efecto — presentations, pitch decks, event posters, email headers, blog images, open graph cards, business cards, resumes, menus, infographics, invitations, newsletters, and documents. Use when asked to "design a poster", "create a pitch deck", "make a presentation", "design a business card", or any graphic design task. Requires Efecto MCP server.
Validate and repair source-locked Blender models using named landmarks such as leaf tips, shell corners, eyes, smile, rim thickness, aura center/radius, and view-specific depth markers. Use when bbox/IoU is insufficient and the model must align to templates at designed feature points.
Use when preparing, submitting, polling, or debugging Seedance 2.0 or 2.5 video generation jobs from prompts, opening/ending frames, multimodal references, storyboard images, UGC scripts, or voiceover copy. Use for selecting an unambiguous scene endpoint, uploading references, composing submit flags, submitting through PostPlus Cloud, polling predictions, and handing off local render paths.
This skill should be used when the user asks to "start a new story", "initialize a story project", "create a story", "new book", "set up a story", or wants to begin a new fiction writing project from scratch. NOT for a sequel or prequel (use series-continuity), or for finding the idea before a project exists (use premise-workshop).
Reshape source-locked mesh boundaries so the geometry fits texture-atlas or decal contours 1:1 before final UV/material work. Use when textures look off because the model behind them does not match the source texture region, or when the mesh must adapt to the texture instead of stretching the texture onto an approximate mesh.
Export auto-editor's edit or microphone recording to a video editor (Premiere, DaVinci Resolve, Final Cut Pro, ShotCut, Kdenlive), to individual clips, or to auto-editor timeline files (.v1/.v2/.v3); and import timeline/XML files to render them. Use when someone wants an editor-ready project, a preserved microphone source, split clips, or timeline files instead of a finished video.
Segment overlapping visual parts from source images, wireframes, texture atlases, and decals before mesh reconstruction. Use when a mascot/logo/template contains touching or overlapping components and exact structural part masks are needed before contour-to-mesh, UV fitting, or landmark repair.
ElevenLabs AI music generation - create original music from text prompts via inference.sh CLI. Capabilities: text-to-music, custom duration up to 10 minutes, genre/mood/instrument control, royalty-free commercial use. Use for: background music, soundtracks, jingles, podcasts, video scores, game audio. Triggers: elevenlabs music, eleven labs music, ai music, generate music, music generation, compose music, ai composer, create song, soundtrack, background music, jingle, elevenlabs compose, music ai
Use this skill when applying visual filters or post-processing effects in Phaser 4. Covers bloom, blur, glow, color matrix, barrel distortion, displacement, custom shaders, and the filter pipeline. Triggers on: filter, post-processing, shader, bloom, blur, glow, color effects.
Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts. Use when the user mentions capcut, jianying, subtitles, video editing, draft_content.json, draft_info.json, or cutting videos — in English or Chinese (剪映, 字幕, 草稿, 剪辑, 切片, 视频编辑).
This skill should be used when the user asks to "make a YouTube intro", "create a channel intro", "build a logo sting/bumper", "design an outro / end screen / end card", "add subscribe and next-video cards", "make an intro animation", "build a reusable intro template", or "sync the logo reveal to an audio sting". Covers the 3-5s branded intro, the last-20s end-screen outro inside YouTube's element safe zones, timing conventions, audio-sting sync, and a swap-the-brand template.
Produce media assets using AnyCap: generate images, videos, music, speech, dialogue, and complete audio scenes from text or reference inputs, refine images through interactive visual annotation, and deliver finished assets. Covers the full production workflow from concept to delivery across all media types (image, video, music, audio). Use when creating images, videos, music, voice content, dialogue, complete audio scenes, or any visual/audio content -- including iterative refinement with human feedback. Also use for image-to-image transformation, video generation from images, audio generation from references, and annotation-driven precise edits. Trigger on: media production, asset generation, generate image/video/music/audio, create visual content, produce assets, iterative image editing, annotate and refine, creative workflow, content creation, or any task requiring AI-generated media output.
Eva-skill 2.5.0, a tool for self-media creators. Use it only when invoking /eva, naming an Eva sub-entry, or explicitly requesting Eva's thinking, positioning, creation, teaching, review, learning, commercial-order, retrospective, memory, collection, or audience-acquisition tasks; it also answers questions about Eva-skill's author, maintainers, contributors, acknowledgements, source, license, commercial use, modified redistribution, monetised output, privacy, legal liability, trademarks, and official identity. It does not take over other projects' Q&A, code, finance, deployment, file processing, or unrelated tasks; execute the target entry within the same turn. Entries: /eva, /eva-teaching, /eva-positioning, /eva-think, /eva-audience-finder, /eva-create, /eva-preflight, /eva-learn, /eva-brief, /eva-link, /eva-review, /eva-lens. Compatible: /eva-new-user, /eva-reframe, /eva-benchmark-copy, /eva-memory, /eva-persona-memory, /eva-product-service, /eva-user-voice, /eva-ai-check. Identify natural-language tasks using the table below; disambiguate bare requests like "build a personal brand / craft a persona / IP" only in an Eva context, and handle "next step, choose an entry, give the workflow" only within the current Eva task.
A complete FFmpeg-powered video editing agent. Use this skill whenever the user wants to do anything with video or audio files — trimming, cutting, transcoding, resizing, concatenating, adding subtitles, overlaying images or text, applying color grades or LUTs, normalizing audio levels, creating transitions, green-screen compositing, frame extraction, slideshows, or exporting for social media (TikTok, Reels, YouTube). Also use it for codec questions (H.264, H.265, VP9, AV1, ProRes, FFV1), hardware-accelerated encoding (NVIDIA NVENC, Intel QSV, VAAPI, Apple VideoToolbox), and any ffmpeg or ffprobe command construction. Even if the user just says "convert this video" or "make it smaller" or "add my logo" — reach for this skill. Reference documents in references/ cover filters, codecs, transitions, and hardware acceleration. Helper scripts in scripts/ handle probing, concatenation, and normalization.
Identify and remove AI-generated traces in Chinese text so it reads more naturally, like human writing. Detects AI writing patterns specific to Chinese contexts, including clichés, excessive embellishment and mechanical structure. Based on the Wikipedia "Signs of AI writing" guide, localized for Chinese.
The narrative-craft layer -- apply story structure (tension, transformation, resolution) to make any social content stick and travel. Use when someone wants to tell their brand/founder/customer story, make a flat post land, build an emotional or narrative-driven piece, or structure a story across formats. Uses the BEATS framework. Reads brand-profile + voice-builder first. The agent finds the real story, structures the arc (setup -> turning point -> payoff; audience = hero, brand = guide), anchors concrete specifics, and shapes it to the format. Feeds the format writers (reels-script, carousel-writer, linkedin-post-writer, thread-writer, caption-writer) and hook-writer; serialized arcs map into content-calendar; WoopSocial publishes. NOT the IG/FB Stories format (that's story-writer). Never fabricates a customer story or testimonial; never guarantees virality. Distinct from story-writer, hook-writer (the opening it pairs with), the format writers, and campaign-and-launch-planning.
This skill should be used when the user asks to "edit a video to music", "create a beat-synced edit", "make a montage", "sync cuts to beats", "cut a video to the beat", "make a music video edit", "edit clips to a song", "build FFmpeg filters for video editing", or mentions combining video clips with audio tracks using timed cuts. Provides knowledge of the EditPlan format, FFmpeg filter_complex construction, and beat-sync editing workflows.
The long-form-to-Shorts + sound-off captions mini-skill (Opus Clip / CapCut / Submagic). Use when someone wants to "clip my podcast/webinar/long video into Shorts," "make TikToks/Reels from a YouTube video," "add captions/subtitles to a video," "repurpose long-form into short-form," or "auto-generate clips." Tools clip and caption; a human reviews; WoopSocial schedules/publishes. Below the ai-video router; sibling to veo-3, heygen, ai-voiceover. This is the general craft: route OpusClip-specific pipelines (credits, Virality Score, tiers) to opus-clip, hands-on short-form editing to capcut, and the long-form talk edit itself to descript. Export clean (no watermark); disclose AI-edited video.
Design and validate texture-state transitions for Blender animations without ugly whole-image crossfades, texture popping, misregistered morphs, or target-engine-incompatible Python-only swaps. Use when animating between multiple source textures, mascot/logo states, style states, lightmaps, decals, or UI skins.
Generate self-contained HTML visual explanations for systems, code changes, plans, data, and technical concepts. Use for diagrams, architecture overviews, diff or plan reviews, project recaps, comparison tables, slide decks, animated explainers, narrated MP4 videos, and other visual explanations.
This skill should be used when the user asks to "make a photo slideshow", "turn photos into a video", "create a photo montage video", "make a picture slideshow with music", "build a memories/recap video from photos", "add Ken Burns pan/zoom to photos", "sync slide changes to the music beat", or "render a video from a folder of images". Covers per-photo Ken Burns motion, transitions, beat-synced timing, mixed aspect-ratio handling, captions/dates, intro/outro cards, and templating a photo folder into a finished video.
Create tasteful circular/orbital HUD and aura animations around a Blender subject using source-derived arcs, dots, dashes, opacity, parallax, and restrained motion. Use when decorative circles, halos, orbit markers, scanner rings, or HUD effects must correlate with a logo/mascot rather than looking like random oversized rings.
Complete toolkit for programmatic video creation with Remotion + React. Covers animations, timing, rendering (CLI/Node.js/Lambda/Cloud Run), captions, 3D, charts, text effects, transitions, and media handling. Use when writing Remotion code, building video generation pipelines, or creating data-driven video templates.
Edit, transform, upscale, and enhance images using EachLabs AI models. Supports image editing, style transfer, background removal, upscaling, inpainting, face swap, virtual try-on, 3D generation, and image analysis. Use when the user wants to edit or transform existing images.
Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o image
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
Generate images with Pruna P-Image models via inference.sh CLI. Models: P-Image, P-Image-LoRA, P-Image-Edit, P-Image-Edit-LoRA. Capabilities: text-to-image, image editing, LoRA styles, multi-image compositing, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna, p-image, pruna image, fast image generation, optimized flux, pruna ai, p image, fast ai image, economic image generation, cheap image generation
Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative
Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video
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
This skill should be used when the user asks to "make an audiogram", "turn a podcast into a video", "create a waveform video", "make a podcast clip video", "convert audio to video", "animate a waveform/audio bars", "add a moving waveform to my voiceover", or "make a square/vertical clip for a podcast quote". Covers amplitude-driven waveforms, frequency bars, synced captions, cover-art layout, a progress bar, and 1:1 / 9:16 social framing.
Creates, edits, and publishes Salesforce CMS content of any kind — any domain, any topic. Single and bulk: create many in parallel, edit one or many, publish all or a subset. Use this skill ANY TIME a user asks to create, generate, write, draft, author, or add content, OR to update, edit, or revise a content record, OR to publish it, OR to delete/remove a content record. Triggers like "create a <thing> about X", "create 5 <things>", "update content <id>", "publish content <id>", "publish the record <id>", "make <id> live", "delete content <id>" — where <thing> is any user-named content type. Activates FIRST whenever content authoring, editing, publishing, or deletion is mentioned, regardless of subject. Handles the full workflow: finding the content type, resolving the workspace, creating content, editing or publishing it — including a record identified by its variantId. Does not apply to defining a content type / schema (use experience-cms-content-type-generate), cloning, versioning, workspaces, or media.
This skill should be used when the user asks to "revise a chapter", "continuity check", "find inconsistencies", "audit character state", "check timeline consistency", "developmental edit", "structural revision", "reverse outline", "cut a subplot", "revision passes", "what pass next", "pacing check" as a revision pass, "clue check", "cut to a word count", or "length pass", or to prepare existing story material for the next revision pass. NOT for planning book structure (use plot-structure), scene-level craft (use scene-craft), voice consistency (use voice-style), or reconciling a chapter drafted by discovery (use discovery-drafting).
Interactive novel creation workflow combining RPG-style storytelling with professional EPUB ebook production. Use when users want to: (1) Create interactive stories/RPG games with branching choices, (2) Write full novels from story concepts, (3) Generate novels with time-travel/fantasy/romance elements, (4) Convert markdown stories to EPUB ebooks, (5) Create Chinese web novels with ancient poetry paired with modern lyrics, (6) Write light novels or serialized fiction. Triggers: "write a novel", "create a story", "interactive fiction", "RPG story", "make an ebook", "穿越小说", "写小说", "创作故事", "制作电子书"
A general-purpose Chinese writing and revision skill. For Zhihu answers, forum long posts, WeChat official account articles, blogs, comments, character stories, historical narratives, news and industry commentary, popular science, tutorials, reviews, personal narratives, novels, stories, dialogue, voice-over scripts and speeches. By default it writes in the voice of someone who has seen things, checked the source material and is willing to explain how things came to be, keeping the human feel and natural Chinese rhythm of long answers and long posts on the Chinese internet, and avoiding empty institutional tone, slogan-like oratory, marketing tone and model tone. Non-fiction long pieces first check whether the material is sufficient; when it is not, research, ask follow-up questions or shorten the piece, and never pad the length with repeated explanations. Real-world content additionally gets facts, quotes, data and the user's firsthand experience verified; fictional content may invent characters, scenes, dialogue, psychology and plot. The finished body text strictly forbids colons, dashes, "not… but…" constructions and similar reversal sentences, and strips business jargon and model jargon. It does not create author personas, personal rule libraries or personal writing skills.
Transcribe a media file or live microphone to text or subtitles with auto-editor's whisper subcommand, then edit by spoken content — cut to keep (or drop) sections whose subtitles match a word or regex. Use when someone wants a transcript, captions, live speech transcription, or to cut a video based on what is said rather than on loudness.
Generate AI sound effects from text descriptions with ElevenLabs via inference.sh CLI. Capabilities: text-to-sound-effect, custom duration, royalty-free audio. Use for: video production, game audio, podcasts, films, presentations, social media. Triggers: sound effects, sfx, sound generation, ai sound effects, generate sound, foley, audio effects, sound design, text to sound, elevenlabs sound, eleven labs sfx, ambient sound, cinematic sound, game sound effects
Builds an interactive isometric machine page. Each station of one invented machine stands for one step of a process. A pure, tested state model drives the motion, the readouts, and the copy. The page has controls and a verification loop. Trigger phrases: “isometric explainer,” “machine explainer,” “explain this as a machine,” “interactive isometric figure,” “explorable explainer,” “show how it works inside.”
ElevenLabs multi-speaker dialogue generation - create conversations with different voices in a single audio file via inference.sh CLI. Capabilities: multi-voice dialogue, script-based generation, voice direction, conversation audio. Use for: podcasts, audiobooks, explainers, tutorials, character dialogue, video scripts. Triggers: elevenlabs dialogue, eleven labs dialogue, multi speaker, conversation audio, dialogue generation, text to dialogue, multi voice, voice acting, podcast dialogue, character voices, script to audio, elevenlabs conversation, two speakers
Use for any 3D work in Blender through Python or an MCP bridge, headless or in a live session: modeling, sculpting a character or head, retopology, UV unwrapping, baking, texturing, rigging, animating, previs, geometry nodes, lighting and rendering, grease pencil, or finishing an AI-generated mesh into a production asset. Also use before exporting or handing off an asset to check readiness for a game engine, render, or 3D print (floating parts, z-fighting, inside-out normals, unapplied scale, missing UVs). Also use when a bpy script fails due to Blender 5.x API changes, a brush or sculpt operator fails or crashes headless, or a result must be judged like a professional 3D artist would.
ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization
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.