Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Russian-language project editorial policy: a short interview, extracting voice from examples, and a `.agents/redpolitika.md` file for editorial skills. Use this skill whenever the user asks to create, update, remember, formalize, or apply a project editorial policy, tone of voice, style guide, vocabulary, forbidden words, or reusable writing context. Triggers: «настрой редполитику», «редполитика», «запомни мой стиль», «создай гайд по стилю», «tone of voice», «ToV», «настрой скилл под наш проект», «как нам писать», «зафиксируй голос», «добавь в редполитику», «обнови правила тона», «словарь проекта», «запрещённые слова», «пиши в нашем стиле», «сохрани правила редакции». Also suggest this skill when redaktura, statya, or ux-copy lacks project context and the user will keep working with the same product. For editing a finished text, see the redaktura skill; for writing articles from scratch — statya; for interfaces — ux-copy.
Get AI-generated videos ready to post, without touching a single slider. Upload your written text (TXT, DOCX, PDF, SRT, up to 200MB), say something like "turn this blog intro into a 30-second video with visuals and background music", and download 1080p MP4 when it's done. Built for marketers, content creators, educators who move fast and want to produce videos without filming or editing skills.
Get Hindi text videos ready to post, without touching a single slider. Upload your text script (TXT, DOCX, PDF, SRT, up to 200MB), say something like "create a video from this Hindi text with visuals and voiceover", and download 1080p MP4 when it's done. Built for Hindi content creators who move fast and need to create Hindi videos without recording or editing skills.
Diagnose and transform any authorized video URL, upload, recording, transcript, podcast, interview, presentation, screen recording, webinar, ad, or published video into the strongest justified content portfolio. Use for video audits, format recommendations, long-form editing, mid-form explainers, Shorts and Reels, teasers, tutorials, case studies, paid cutdowns, captions, packaging, delivery, or publication preparation.
Edits a complete talking-head video end to end with free tools (Remotion, whisper.cpp, ffmpeg) - a vertical short (1080x1920) or a full horizontal YouTube video (1920x1080). Use when the user says edit, cut, captions, subtitles, motion design, montage, "make it a short", "edit my YouTube video", render, or gives a recording from video-agent/takes/. Transcribes locally with word timings, cuts silences and retakes against the script, adds punch-in zooms, word-by-word captions in the creator's accent color, a hook card, callouts and a progress bar, levels the voice to -14 LUFS, and writes an .srt, a cut list for CapCut or Premiere, chapters for a long video, and the post copy.
generate text or images into animated cartoon videos with this skill. Works with MP4, MOV, PNG, JPG files up to 200MB. students, content creators, social media users use it for generating cartoon videos from text prompts or images for free — processing takes 1-2 minutes on cloud GPUs and you get 1080p MP4 files.
Turn three product photos and a logo file into 1080p finished MP4 videos just by typing what you need. Whether it's generating polished videos from images or clips without manual editing or quick social content, drop your video clips or images and describe the result you want. No timeline dragging, no export settings — 1-2 minutes from upload to download.
Tired of juggling clunky software just to record your screen and share it? The video-screen-recorder skill lets you capture screen activity, trim recordings, add annotations, and export clean video files without the usual setup headache. Whether you're creating tutorials, bug reports, or product demos, this skill handles mp4, mov, avi, webm, and mkv formats. Built for developers, educators, and remote teams who need polished recordings fast.
trim video clips into trimmed video clips with this skill. Works with MP4, MOV, AVI, MKV files up to 500MB. casual video editors use it for cutting and trimming video clips to exact lengths — processing takes 20-40 seconds on cloud GPUs and you get 1080p MP4 files.
Plan and govern images, video, generated visuals, hero media, asset sourcing, visual proof, and content-media fit for UI/UX projects. Use when a site or app needs premium visual direction, photo/video asset plans, generated imagery prompts, before/after media, or visual asset QA before implementation, Stitch, Pencil, Figma, or code handoff.
World-class voiceover expertise combining the narrative craft of documentary producers, the commercial precision of advertising agencies, and the accessibility of modern AI voice technology. Voiceover is the invisible art that makes or breaks video content. Great voiceover isn't just speaking clearly—it's performing the script in a way that creates the intended emotional response. The best voiceover work understands pacing, tone, emphasis, and the subtle art of making scripted words sound natural. It knows when to use human talent versus AI, and how to get the best from both. Use when "voiceover, voice over, VO, narration, narrator, voice recording, voice talent, voice actor, AI voice, text to speech, audio narration, voice direction, voiceover, audio, narration, voice, recording, AI-voice, talent, direction" mentioned.
Expert in building 3D experiences for the web using Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and adding depth to web experiences. Use for: 3D websites, three.js, WebGL, react three fiber, and 3D experiences
Skip the learning curve of professional editing software. Describe what you want — apply a jiggle bounce effect to this image to make it look animated — and get jiggle animated videos back in 20-40 seconds. Upload MP4, MOV, JPG, PNG files up to 200MB, and the AI handles AI jiggle animation automatically. Ideal for TikTok creators who want to add fun motion effects without editing software.
Detect AI-isms in written content and score it on a 1-10 AI-voice scale (1-2 green / human, 3-6 yellow / mixed, 7-10 red / machine-cadenced). Use when the user asks to check for AI voice, AI-isms, ChatGPT-isms, LLM tells, machine-cadenced prose, or wants a "humanness" / "AI-voice" rating on a piece of writing.
This skill should be used when the user asks about "sound design", "foley", "film sound", "sound effects", "audio post-production", "spatial audio", "sound mixing", "act as a sound designer", "sound design mode", "Dolby Atmos", "ambience design", "sound map", "music supervision", "dialogue editing", "sound for film", "surround sound", or needs expertise in sound design planning, foley workflows, music supervision, spatial audio, and mixing strategies for film. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
Blender automation with geometry creation, materials, modifiers, and Mixamo animation retargeting. Core Features: WebSocket-based real-time control, automatic bone mapping with UI review, two-phase confirmation workflow, quality assessment, multi-project support, comprehensive CLI commands. Use Cases: Create 3D primitives (cube, sphere, cylinder, etc.), manipulate objects (transform, duplicate, delete), manage materials and modifiers, retarget Mixamo animations to custom rigs with fuzzy bone matching.
Create and check long-running video material evaluation tasks. Use this skill when the user wants to submit videos for evaluation, check an existing video evaluation task list, or fetch the result of a previously created video evaluation task. This skill is not a general-purpose video upload skill because upload is allowed only as an internal step of task creation. Authentication uses an API key passed as an Authorization bearer token.
This skill provides character arc development frameworks and techniques. Covers the core arc formula (flaw to strength, want to need, lie to truth), positive change arcs, negative arcs, and supporting character development. Use when: developing character transformations, tracking character growth, analyzing protagonist journeys, or building supporting character arcs.
Character design for Chinese web novels. Use when the user wants to design protagonists, antagonists, supporting characters, or couples; create character profiles, biographies, character arcs, or relationship maps; or address characters who feel unconvincing, stereotypical, or inconsistent. Produces memorable character profiles with growth arcs that serve the story’s satisfying payoff.
When the user wants to turn one piece of content into many, repurpose a video/podcast/post for other platforms, create social posts from long-form content, or says things like 'repurpose this,' 'turn this into,' 'social posts from,' 'newsletter from this video,' 'clips from this.' Takes one input and multiplies it across platforms.
Expanding Chinese web-novel manuscripts. Use when the user wants to turn an outline/chapter outline into full text, expand a chapter, continue with the next chapter, turn a synopsis into scenes, or "write 3,000 words following this detailed outline". Produces publish-ready web-novel text matching the platform's word count and pacing while keeping characterizations and foreshadowing consistent.
Draw an animated figure—boxes, arrows, and moving data—as a self-contained SVG for a GitHub README, PR, issue, or blog post. Use when a change or explanation needs a diagram, such as showing request flow, what a background job does, or what a feature changed; also use when the user asks for a diagram, figure, animation, or to “show it visually.” For pages on the docs site itself, use the interactive player instead (see step 4).
Generate and edit images using Google Gemini's native image generation models (Nano Banana / Nano Banana Pro). Supports text-to-image, image editing with reference images, multi-image composition, and character consistency. Use when the user asks to generate images via Gemini, create AI illustrations, edit photos with Gemini, or needs high-quality image generation with the Google API. Requires GEMINI_API_KEY. Triggers: "generate image with gemini", "nano banana", "gemini image", "create illustration", "AI generate picture", "text to image".
Get animated video clips ready to post, without touching a single slider. Upload your static images (JPG, PNG, WEBP, HEIC, up to 200MB), say something like "compare top image-to-video AI models and generate a clip from my photo", and download 1080p MP4 when it's done. Built for AI enthusiasts, marketers, content creators who move fast and want to find the best-performing image-to-video model before committing to one.
Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok
Download and save Instagram posts as high-resolution files. Use when asked to download, save, or archive an Instagram post, reel thumbnail, or carousel. Produces saved high-res images in a named folder, with carousel slides stitched into a single PDF; supports batch downloading of multiple URLs at once.
Skip the learning curve of professional editing software. Describe what you want — animate this image into a short video clip with smooth motion — and get animated video clips back in 30-60 seconds. Upload JPG, PNG, WEBP, HEIC files up to 200MB, and the AI handles AI video creation automatically. Ideal for social media creators who want to bring still photos to life without complex animation software.
A creation archive and memory system for Chinese web novels. Use when the user wants to record or save outlines, character profiles, or settings; continue writing a book across sessions; asks “Where did I leave off?” or “Was this plot thread resolved?”; create a version snapshot of a book (like git); or manage progress across multiple books. Maintains persistent archives in each book’s folder for shared read/write access by all writing skills.
Chinese web-novel character naming. Use when the user needs names for protagonists, female leads, villains, supporting characters or elders, wants to rename them, finds the names too common/too AI/overused (such as 叶辰苏念林婉儿), or says "I can't come up with names". Produces fitting, memorable character names by genre/era/status/gender, avoiding the cookie-cutter names churned out by web-novel pipelines.
Use when creating game worlds, lore, factions, geography, timelines, or establishing world consistency rules. Genre-agnostic — works for fantasy, sci-fi, modern, or abstract settings. Triggers: lore, factions, geography, world bible, world creation.
Design outlines for Chinese web novels. Use when the user wants to create a novel, volume, or detailed chapter outline; plan main and subplots; design foreshadowing; or pace the story. Produces layered plans from the overall book structure to individual chapter details, maintaining long-term coherence and satisfying story beats.
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
Turns products, knowledge points, or copy into cinematic web demo animations in a "phone system UI style" — the audience watches what looks like a carefully choreographed screen recording of a real phone: lock screen notifications, chats, settings pages, control center, and app screens revealed shot by shot, with HyperOS/MIUI-level tactile motion effects plus a virtual clock player, recordable full-screen as a finished video. Use this skill whenever the user mentions phone UI demos, phone screen-recording style animations, app demo web pages, turning a product into a demo inside a phone, lock screen notification animations, system UI style demo pages, or asks to revamp and upgrade a batch of phone-style demo pages. Content is fully open with no limits: any product feature, course knowledge, or science narrative can be translated into "what happens inside a phone".
Professional Markdown to WeChat Official Account (公众号) publisher with visual style presets. Use this skill whenever the user wants to: publish an article to WeChat, create a 公众号 draft, format a blog post or technical tutorial for WeChat, apply a visual style to Markdown, or says anything like "发布到微信", "推送到公众号", "微信文章", "publish to WeChat", "WeChat draft", "公众号推文", "wechat article", "微信公众号". Also trigger when the user asks to convert Markdown to a styled HTML document for WeChat, even if they don't say "publish" explicitly. Also trigger for translation/repost requests: "全文翻译", "转载", "translate and publish", "repost", or when the source article is in English and the user wants to publish it to WeChat. Also trigger for "视频号", "短视频", "竖屏视频", "生成视频", "video", "short video", or "WeChat Channels". This skill handles credentials, image uploads, 13 style presets (3 core + 7 extend + unlimited custom), automatic cover generation, full-article translation, and draft creation end-to-end.
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.