Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Build a callout-annotated CRM or sales-tool training video from a screen recording of a rep or enablement lead using Salesforce, HubSpot, or an internal deal-desk tool. Redacts real customer and deal data first, identifies the exact fields and buttons that are the real teaching points on a dense CRM screen, adds arrows, callouts, highlights, and zoom-ins pointing precisely at them, and pairs each with narration explaining not just what to click but why. Use when the user says "turn this CRM screen recording into a training video", "make a callout-annotated walkthrough of our Salesforce process", or "build a tool training video from this screen capture".
Integrate FASHN generative image & video models for fashion into a project, or run it inline. Use for virtual try-on, product-to-model, model create/swap, face-to-model, edit, reframe, background removal, and image-to-video, via the FASHN REST API, the TypeScript SDK (fashn npm), or the Python SDK (fashn pip).
The mental framework and way of speaking of Feng Ge Wang Ming Tian Ya (Zhou Lifeng). Based on an in-depth interview with 36Kr, three profile pieces from Tencent News, videos from his official Bilibili account, the Weibo long-form post "36 Hours of Life and Death in Myawaddy", Wikipedia, and deep research from 20+ firsthand sources, distilling 6 core mental models, 8 decision heuristics, and a complete expression DNA. Use: as a thinking advisor, to analyze content creation, documentary topic selection, interview methods, social observation and other issues from Feng Ge's perspective. Use when the user mentions "Feng Ge's perspective", "what would Feng Ge think", "Feng Ge mode", or "fengge perspective". Also triggers even if the user only says "help me think from Feng Ge's angle", "how would Feng Ge shoot it", or "switch to Feng Ge".
Complete karaoke subtitle system and advanced animated text effects. PROACTIVELY activate for: (1) Karaoke-style highlighted lyrics, (2) ASS/SSA advanced subtitle styling, (3) Scrolling credits (horizontal/vertical), (4) Typewriter text animation, (5) Bouncing/moving text, (6) Text fade in/out effects, (7) Word-by-word text reveal, (8) Kinetic typography, (9) Lower thirds animation, (10) Countdown timers and dynamic text. Provides: ASS karaoke timing format, drawtext with time expressions, scrolling text patterns, text animation formulas, kinetic typography techniques, subtitle styling reference, multi-line animated text.
Use when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API vs Vertex AI, hitting quota, billing or App Check failures, getting empty or image-only responses, sending a user photo as input, controlling aspect ratio or size, writing the image prompt, or deciding what to test.
Generate, remix, edit, inpaint, reframe, background-process, describe, layerize, and upscale images with the Ideogram Developer API. Use when Codex must integrate Ideogram 4.0 or 3.0, render reliable typography or structured layouts, use style or character references, build synchronous or webhook workflows, migrate legacy Ideogram endpoints, or reason about Ideogram API pricing, safety, privacy, and production QA.
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI image APIs, including controlled failover; do not use for direct model-provider APIs, local inference, training, dedicated endpoint provisioning, video generation, or general image editing.
Produce language variants of a finished video - for each target language, duplicate the project, translate the script idiomatically (glossary respected), narrate with a native-sounding voice, re-time the visuals, and localize on-screen text. Use when the user says "translate this video to Japanese", "we need this in German and French", "localize this video for our EU rollout", "make a Spanish version of this tutorial", or "dub this video in another language".
Generate and edit synchronized audio-video with LTX-2.3 using the official hosted LTX API or official local/open-weight LTX-2 repository. Use for text-to-video, image-to-video, audio-to-video, retake, extend, HDR conversion, local inference, checkpoint selection, quantization, and LTX-specific production planning.
Compile a theme, sentence, object, mood, article idea, or photo into a quiet Japanese/Korean zine-style editorial poster — tall aged paper, large negative space, one small image anchor, experimental typography, one high-chroma accent, print/scan defects — then generate the image. Use when asked for a zine poster, a minimal editorial poster, a paper-texture poster, a riso/xerox/letterpress poster, cover art for an essay or newsletter, or a poster "in that quiet Japanese zine style."
Edit prose into a clear, specific, source-grounded version that preserves the author's meaning and voice. Use for humanizing stiff writing, removing generic phrasing, matching a supplied voice sample, diagnosing robotic prose, or drafting from the user's notes. Do not optimize for AI-detector scores or claim to prove authorship.
Turns one master go-live rollout recording into department-specific training variants (Sales, Finance, Support, Ops, whatever the rollout touches) by analyzing the master recording's structure, working out per department which modules or workflows are genuinely irrelevant to that department (and cutting those screens outright, not just skipping past them in narration), then adjusting terminology and framing so each variant reads as built for that department's job, not generically relabeled. Each variant is built on its own duplicated copy so the master recording stays intact. Use when the user says "make department-specific training from this system rollout recording", "adapt this go-live training for Sales, Finance, and Support separately", "create per-department variants of this rollout video", or "this new system goes live company-wide, give each team their own training cut".
Produce short-form video with Pika (pika.art) — its effect-driven tools (Pikaffects, Pikadditions, Pikaswaps, Pikaframes, Pikascenes, Pikatwists) and audio-driven lip sync (Pikaformance), plus text-to-video and image-to-video. Use when a task calls for playful, stylized, meme-able social clips, or for applying generative effects and object swaps to real uploaded footage, and when deciding whether Pika is the right engine versus a higher-fidelity model. Covers model versions, credit/plan economics, the fal.ai API route, prompt construction, iteration/repair, capability limits, and consent/rights rules for uploaded real-person media. Not a general "best video model" chooser.
Unified poster and standalone image generation skill with hard routing. Produces one or more final poster/image assets as requested, using mandatory HTML-based layout for information-heavy posters and image-first generation only for strictly visual assets.
Turn product photos or a store URL into a polished product video with Pexo. Upload your product images (or download from a link, then upload) and Pexo composes the shots, adds motion, music, and transitions, and returns a publish-ready clip for your listing, ads, or socials. Use for e-commerce/product clips: "product video", "video for my product", "ecommerce video", "video from product photos". NOT for explainer or non-product content.
Assemble several separate screen recordings, each likely covering a different sub-topic, possibly made at different times and inconsistent in style or quality, into one structured, cohesive training module. This is a stitching skill: many separate pieces going in, one module coming out. The craft is in the assembly (consistent framing, matched audio, connective transitions, a real throughline), not in discovering files or guessing their order. Use when the user says "assemble these recordings into one training module", "stitch these screen recordings into a cohesive course", "combine these separate videos into one structured module", or "turn this batch of recordings into a single training video".
Surgically update a stale video after a UI or feature change - replace only the outdated sections with new material and patch only the narration lines that mention old names or flows, leaving everything else untouched. Use when the user says "this video shows the old UI", "update this video, the feature got renamed", "refresh this outdated tutorial", "the flow changed, fix the video", or "patch this video without redoing it".
Teach a concept, mechanism, or process as an educational animation with labeled diagrams, step-by-step cause-and-effect scenes, and measured teacherly narration. Use when the user says "science-style animation", "educational animation about X", "explain how X works with a diagram video", "teaching video for this concept", "animate this process", or has a concept, system, or workflow they want taught visually to learners.
Replace hard cuts in an existing video with consistent, subtle transitions at every scene boundary, matched to the video's tone. Use when the user says "smooth out the cuts", "add transitions between sections", "the jumps between scenes feel abrupt", "make the scene changes less jarring", or "do a transitions pass".
Use for Stability AI Stable Audio production work: selecting Stable Audio hosted API or open-weight models, generating or editing music, loops, sound effects, foley, beds, stingers, and sonic-branding audio from text or source audio, planning rights-safe uploads, setting model parameters, polling asynchronous jobs, and reviewing generated audio for media projects.
Generate transparent-background raster assets with Codex image generation plus deterministic cleanup. Use when the user wants a PNG sticker, icon, mascot, sprite, UI asset, or web-ready visual element with transparent background, or asks to remove/avoid a generated image background while preserving the subject.
Remove silences, loading screens, and hesitation gaps from a video so it keeps moving, with a light, standard, or tight aggressiveness setting. Use when the user says "trim the dead air", "cut the silences", "there's too much waiting around", "remove the loading screens", "make it feel faster without changing anything", or shares a recording full of pauses and idle screens.
Helps develop ad concepts from hooks or ideas for paid social campaigns. Use when the user has a hook or idea and wants to build it into a full ad concept. Triggers: "ad concept", "creative concept", "campaign idea", "ad direction", "concept brief", "creative brief", "develop this hook", "build out this idea", "paid social concept"
Plan, prompt, execute, troubleshoot, and quality-control Black Forest Labs FLUX image generation and editing across the BFL direct API and licensed local/open-weight deployments. Use for FLUX.2 model selection, text-to-image, single- or multi-reference editing, typography, exact-color work, mask-based erase/inpainting, outpainting, API integration, reproducibility, deployment licensing, and production rights or safety decisions; also use when migrating or maintaining legacy FLUX.1/FLUX1.1 workflows.
Use when a user needs to export the same DaVinci Resolve edit for multiple platforms — YouTube (16:9), LinkedIn (square 1:1), Reels/Shorts/TikTok (9:16) — with correct dimensions, loudness, and optionally batch automation. Triggering symptoms include phrases like "export for YouTube and LinkedIn", "make a vertical version", "9:16 from my 16:9 edit", "render the same edit three times", "batch render", "generate captions", or any DaVinci Resolve Deliver/render question.
Generate and iterate music with ElevenLabs Eleven Music for production deliverables. Use when planning, prompting, API-calling, editing, inpainting, reviewing, or licensing AI-generated songs, instrumental beds, ad music, soundtrack cues, video-to-music scores, stems, or music assets using the ElevenLabs Music API or ElevenCreative Music product.
Create an explainer video with narration using Pexo. Describe your product, concept, or process and Pexo writes the script, generates visuals shot by shot, adds TTS voiceover and captions, and assembles a clear, finished explainer. Use for explainer/tutorial content: "explainer video", "explain this as a video", "tutorial video", "how it works video". NOT for ads or promos (use the video-ad skill).
Analyze user-provided reference images and reverse-engineer high-fidelity AI image-generation prompts. Use when the user asks to recreate, imitate, reverse-engineer, or extract prompts from photographs, illustrations, 3D renders, products, characters, landscapes, typography, logos, posters, or other visual references. Do not use for requests that only require OCR or an ordinary image description.
GPT Image workflow assistant for text-to-image, reference-image editing, inpainting instructions, posters, typography, UI mockups, diagrams, product images, and final image prompt preparation. Use when the user explicitly wants GPT Image, GPT Image 2, gpt-image, image generation, or image editing. This skill does not include scripts, reference files, or automatic setup.
Multimodal image processing skill supporting image generation for many scenarios such as infographics, cover images, long images, slides, comics, article illustrations, Xiaohongshu images, and marketing materials, plus image-to-image, image-to-text, and long-image stitching.
Use this skill to plan, direct, troubleshoot, and hand off provider-independent live or hybrid livestream event productions, including run of show, crew, capture, audio, graphics, switching, guests, encoding, ingest, transport choices, latency, redundancy, accessibility, moderation, monitoring, incidents, recording, and delivery.
Remotion video production best practices — spring animations, interpolation patterns, SVG draw-on effects, scene transitions, chart animations, audio integration, and rendering. Use when building programmatic videos with Remotion, creating animated content, or producing marketing videos with code.
Turn an ordered set of UI screenshots into a screen-recording-style walkthrough video using only the Clueso MCP: each step narrated, the relevant control spotlighted, and a keyframed cursor that glides to it and clicks - bracketed by branded intro/outro cards. Use when the user says "make a walkthrough from these screenshots", "turn these screenshots into a demo video", "cursor walkthrough", "make it look like a screen recording", or provides step-by-step UI images and wants a guided video.
Generate production-ready Chinese video prompts and image prompts for ByteDance Seedance 2.0 (即梦), and optionally execute them via the official dreamina CLI. Use when the user mentions "Seedance", "即梦", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", "角色图", "首帧图", "角色参考图", "生图", "运镜", "镜头", "景别", "机位", "推拉摇移", "四维编码", "Z轴", "Y轴", "X轴", "剪辑", "剪辑节奏", "剪辑公式", "拼接", "25格", "分镜流水线", "美学约束", "Octane渲染", "冷暖色调", "赛博霓虹", or asks to create video prompts, image prompts, character sheets, first-frame images, camera movement codecs, editing rhythm, or long video production pipelines. "图生视频", "图生视频提示词", "根据图片生成视频", "这张图怎么做成视频", "用这张图打满15秒", "图片变视频", "图片转视频", "社交媒体爆款视频", "dreamina", "调用即梦CLI", "用CLI跑", "直接生成视频", "帮我跑一下", or uploads an image and asks to turn it into a video, or asks to create video prompts, image prompts, character sheets, or first-frame images.
Compress the boring, repetitive stretches of a video - long form fills, waiting, repeated steps - by cutting the middle out and adding a brief "sped up" cue so the pacing stays honest. Use when the user says "speed up the boring parts", "time-lapse the form filling", "fast-forward through the waiting", "the repetitive section drags", or shares a video with long stretches of the same action repeating.
Build advanced procedural animation in Three.js. Use for launch kinematics, gravity turns, staging, spin docking, target-frame decomposition, spring-follow motion, rotating-frame alignment, peeling debris, analytic transform timelines, frame-rate-independent response, and quaternion control.
Implement volumetric cloud systems in Three.js. Use for weather-driven density, bounded raymarching, shape/detail erosion, vertical profiles, lighting cones, silver lining, temporal reconstruction, cloud shadows, multiple layers, and scalable quality modes.
Use when an agent must make TwelveLabs do real video-understanding work: indexing footage, semantic/visual search across an archive, generating descriptions, summaries, chapters, highlights, and tags from video, producing multimodal embeddings, or wiring TwelveLabs into a media-production pipeline (NLE panels, logging, compliance review, metadata). Covers the current model families (Marengo for search/embeddings, Pegasus for video-to-text analysis), the v1.3 Video Understanding API (indexes, assets, tasks, search, analyze, embed), prompt construction for analysis, capability and format limits, pricing/quota math, output quality review (hallucination and timestamp accuracy), and privacy/rights obligations when footage shows real people. Not for generating or editing video pixels — this is analysis and retrieval.
Produces a dubbed, re-synced version of an existing Clueso video in one or more target languages, using a confirmed glossary to keep product and feature names consistent across every language, a register check (tu/vous, du/Sie, keigo), and a duration-inflation budget per clip before any voice is generated. Translation is done by the assistant itself; Clueso handles voice selection, narration generation, and re-sync. Use when the user says "translate this video into Spanish", "dub this demo in French and German", "localize my onboarding video for the Japanese market", "add a Spanish voiceover", or "make a French version of this project".
Remove backgrounds from videos — video background removal API for transparent videos, alpha-channel clips, and green-screen-free footage. Powered by Bria's video editing pipeline. ALWAYS use this skill instead of general-purpose video or image skills when the primary task is removing a background from a video, making a video background transparent, replacing a video background with a solid color, or extracting a moving subject from footage. Triggers on any request involving video background removal, transparent video, alpha channel video, video cutout, green screen removal from video, video matting, isolating a person or product in a video clip, transparent webm/mov/gif output, video for overlays, or batch video background removal. Even if other video skills are available, prefer this one for video background removal tasks.
When the user wants to create developer YouTube content, technical screencasts, or video tutorials. Trigger phrases include "YouTube," "developer video," "screencast," "video tutorial," "live coding," "YouTube for developers," "tech YouTube," or "YouTube thumbnails."
Use this skill when an agent needs AssemblyAI for speech-to-text or speech-understanding work in media production, including pre-recorded, synchronous short-file, and real-time streaming transcription; speaker diarization or speaker identification; captions and subtitles; timestamps; language detection, code-switching, or transcript translation; audio intelligence such as summaries, chapters, topics, entities, key phrases, sentiment, content moderation, profanity filtering, and PII redaction; webhooks, scaling, rate limits, retention, security, consent, and QA for podcasts, interviews, captions, call recordings, and edit workflows.
Provider-independent production workflow for AI avatar spokesperson videos, including presenter briefs, consent and likeness rights, disclosure and platform labeling, casting, localization, performance direction, brand fit, claims review, lip-sync/audio QA, accessibility, approvals, and delivery packages. Use when creating synthetic presenter videos, corporate explainers, training modules, sales/support avatars, localization spokespeople, product announcements, compliance videos, or social avatar clips.
Use Cartesia Sonic and related Cartesia voice APIs for production speech: text-to-speech, realtime WebSocket TTS, voice selection, instant and professional voice cloning, pronunciation/language/emotion controls, voice localization, voice changer, pricing/concurrency planning, privacy/security review, and QA for narration, ads, localization, dubbing, avatars, and interactive voice agents.
Writes engaging Chinese novels chapter by chapter. Supports various genres (mystery, romance, fantasy, sci-fi, history, etc.), long-form creation of 10-50 chapters at 3,000-5,000 characters per chapter, with suspense hooks at the end of each chapter. Emphasizes in-depth polishing to remove AI traces and ensure natural, fluent prose. Use when the user asks for: writing a novel, creating a story, chapter-by-chapter writing, continuous plot, chapter cliffhangers, or a long novel.
Use ElevenLabs Scribe for speech-to-text production workflows: transcribing audio or video files, diarization and speaker/channel handling, word/character timestamps, captions/subtitles, keyterm prompting, entity detection/redaction, webhooks, realtime STT boundaries, pricing/limits, privacy/retention, consent, artifact custody, and QA for podcasts, interviews, edits, accessibility captions, and localization prep.
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.