Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Transcribe video or audio to JSON, SRT, and VTT with speaker diarization and time codes, using OpenClip. FREE with just an OpenClip account, no subscription. Use when asked to “transcribe this”, “get me a transcript”, “make subtitles”, “generate an SRT”, “who said what in this recording”, “pull quotes from this video”, or “what was said at 4:30”.
Short Russian-language posts for Telegram, LinkedIn, Instagram and other social networks: a post from scratch, a post from an article, a channel announcement, rewriting the first line, strengthening the hook and the ending. Use this skill whenever the user asks to write, rewrite, draft, shorten, or improve a Russian social media post, Telegram channel post, LinkedIn post, Instagram caption, channel announcement, post from an article, or first-line hook. Triggers: «пост в телеграм», «пост для канала», «пост в LinkedIn», «пост в Instagram», «короткий пост», «напиши пост», «анонс в канал», «пост из статьи», «первая строка не цепляет», «перепиши пост». For articles and longreads, see the statya skill; for landing pages and sales pages — promo; for interfaces — ux-copy.
Generate professional studio or lifestyle backgrounds for product photography that match product aesthetics, brand positioning, and target audience. Use when creating product shoots, fashion photography, or e-commerce visuals requiring contextual backgrounds.
Extract anonymized frame-by-frame body and hand trajectories from an authorized reference video, with skeleton previews, confidence evidence, and machine-readable keypoints. Use when the user asks to 提取博主动作, 提取人体动作轨迹, 做姿态参考, 生成骨架视频, or prepare motion control data for an avatar; do not route graphic-animation replication here.
Use this skill when the user wants to generate videos, images, or audio using the Runway API. Covers product ad videos, text-to-video, image-to-video, video-to-video, character performance, image generation, sound effects, TTS, speech-to-speech, voice dubbing, and voice isolation.
Story decision capture and mining — recording what was decided, what was rejected, and why, inline with the artifacts they relate to. Use whenever story direction is being chosen, brainstorm options are being narrowed, character or world choices are being made, or past decisions need to be recovered from session history.
Record polished Screen Studio style videos of web apps (smooth cursor, click ripples, eased zooms, padded frame) with the takeone MCP server, CLI or TypeScript SDK, including installing and setting it up from nothing. Use this whenever the user wants a demo video, product walkthrough, feature clip, tutorial recording, launch video or screen recording of a website or web app, even if they don't name takeone, and whenever a project has takeone scenario files or a .takeone folder.
Block out, edit, check and render 3D staging scenes on the local machine with the topview-3d-cli command: simple primitive props, built-in mannequin characters, static library poses, story cameras plus a bird's-eye layout camera, numerical checks and PNG renders; building and rendering run offline in a project directory. After the renders it offers an image or video generation from the frames, run only once the user confirms. Use when the user asks to stage, block out, lay out or storyboard a scene in 3D; place people, props or cameras; pose characters; check framing, grounding, spacing or collisions; render views of a scene as a reference for video generation; or works in a directory that contains `.topview-3d/`. Also use when a topview-3d-cli command fails or topview-3d-cli still has to be installed. The Codex plugin is shown as Topview 3D Builder. Change the 3D scene only with topview-3d-cli. After a scene is built, open the local Studio in the In-App Browser to view it, not to edit it.
Translate video subtitles to any language with native-quality refinement. Full pipeline: transcribe → translate → refine → embed RTL-safe subtitles. Use for: translate video, תרגם סרטון, video translation, foreign subtitles, Hebrew subtitles, translated captions.
Research current trends and preferences on Chinese web fiction platforms in real time. Use when the user wants to know which genres, popular tags, ranking formulas, or reader preferences are trending on platforms such as 番茄, 晋江, 起点, UC, 知乎盐选, and Webnovel, or wants market research before choosing a topic and tracking trends. Prioritize web searches for the latest data and provide actionable topic and tag suggestions.
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts
Weibo hot search ranking query tool. Calls the Redfox API to get Weibo's current hot search ranking, displays hot search titles and jump links by rank, and performs creative inspiration analysis and summary on the hot search content. Use when users need to view Weibo hot searches, the Weibo hot list or Weibo trending topics. Trigger words: 微博热搜, 微博热榜, 微博热门话题, 热搜榜, 微博热搜榜.
WeChat Official Account content creation and publishing workflow, covering topic selection, drafting, polishing, illustrations, layout, publishing, and review. For personal subscription accounts without verification, publishing guides the user to operate manually in the backend. Use when: "公众号", "写文章", "发文", "选题", "涨粉", "内容运营", "草稿箱", "帮我写篇公众号", "最近公众号没什么灵感", "公众号文章", "发布到公众号". Proactively suggest when the user mentions writing articles, content creation, or WeChat Official Account related tasks.
Download videos, audio, playlists, and channels from YouTube and 1000+ websites using yt-dlp. Supports quality selection, format conversion, subtitle download, playlist filtering, metadata extraction, thumbnail download, and batch operations. Use when downloading YouTube videos in any quality (4K, 8K, HDR), extracting audio as MP3/M4A/FLAC, downloading entire playlists/channels, getting subtitles in multiple languages, converting to specific formats, downloading live streams, archiving content, or batch processing multiple URLs. Optimized for reliability with automatic retries, rate limiting, and error handling.
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (22+ premium voices, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation, voice transformation, delivery mode control, character voices. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility, gaming NPCs, avatar audio, UGC. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs, eleven labs, natural voice, realistic speech, voice ai, voice changer, inworld, inworld tts, character voice, npc voice
This skill should be used when the user asks about "AI voice design", "ElevenLabs", "voice cloning", "text to speech", "AI narration", "voice over AI", "Eleven v3", "audio tags", "voice library", "voice design from description", "speech to speech", "voice changer", "AI dialogue", "voice acting AI", "stability slider", "similarity slider", "style slider", "act as a voice designer", "voice designer mode", "AI voice direction", "emotional voice generation", "podcast voice", "audiobook narration", "multilingual TTS", "voice performance", or needs expertise in designing and directing AI voice performances using ElevenLabs. Part of the AlterLab FC Skills collection (GenAI pack).
This skill should be used when the user asks about "social media content", "content calendar", "Instagram posts", "TikTok scripts", "Reels", "social media strategy", "hashtag strategy", "content creation", "social media captions", "platform-native content", "act as a social content creator", "social content mode", "content planning", "social media copywriting", "engagement strategy", or needs expertise in creating platform-optimized social media content and editorial calendars. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).
Compile user intent, scene beats, and reference assets into compact, controllable Seedance 2.0 prompts executed through the AnyCap CLI. Use when creating, testing, iterating, troubleshooting, or continuing Seedance 2 / Seedance 2 Fast video generations with AnyCap, especially when prompt structure, reference consistency, image/video/audio role mapping, product or character identity, multi-modal references, continuation, retakes, or generated-video review matter.
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Use when the user needs to turn content (articles, notes, screenshots, data, product descriptions) into Chinese image-and-text card sets — Xiaohongshu / Rednote 3:4 vertical images, WeChat official account covers, social cards. Provides three exclusive visual languages (Still Paper 本手记 / Signal Proof 证据层 / Bridge Canvas 跨平台桥): Claude reads the content and writes brief.json itself, then hands it to a deterministic engine that renders a card set that is striking at first glance, instantly recognisable, and ready to use out of the box in China.
Book cover design with genre-specific conventions, typography rules, and AI image generation. Covers fiction and non-fiction genres, sizing, thumbnail testing, and iteration workflows. Use for: self-publishing, ebook covers, print covers, audiobook covers, cover mockups. Triggers: book cover, cover design, ebook cover, book art, novel cover, self publishing cover, kindle cover, audiobook cover, book jacket, cover illustration, fiction cover, nonfiction cover
Unified visual content system for cardiology thought leadership. Automatically routes requests to the optimal tool—Fal.ai for blog imagery, Gemini for infographics, Mermaid for flowcharts/pathways, Marp for slides, Plotly for data visualization. One skill handles all visual needs within Claude Code.
Transform long-form content (YouTube videos, podcasts, interviews, articles) into engaging short-form and long-form narratives. Extracts core insights and presents them in two styles: concise social media posts (300-800 characters with numbered emoji lists) and detailed narrative articles (1500-3000+ characters with story arcs). Use when users provide YouTube links, podcast transcripts, long articles, or interview content and want summaries, key insights, or content reformatted for different platforms.
A continuity checker that reads a manuscript against its own established facts, world rules, and timeline and flags contradictions — eyes that change colour, a dead character who reappears, a Tuesday that can't exist, a secret someone acts on before they learn it. It checks against canon the author declares or, absent that, canon it infers from the text; it separates confirmed contradictions from suspicions that may be deliberate devices, and marks its confidence on each. Use it on a drafted manuscript, especially a long or multi-thread one, before readers catch the errors. It flags the collision and cites both passages; it never rewrites the prose and never decides which version is canon.
Use when implementing procedural content generation, dungeon or map generation, procedural loot tables, world seeds, noise-based terrain, NPC behavior variation, or wave function collapse. Triggers: procedural, dungeon gen, map gen, loot table, world seed, noise, BSP, wave function collapse, randomization.
Designs original, compact mini-games — rules, controls, scoring, hazards, and difficulty curves — for any input scheme, including one-button (tap / hold / release) games. Use when defining a new mini-game concept, converting creative constraints or seeds into mechanics, choosing an input scheme, checking state-variable necessity, or preventing idle, hold-only, or mashing play from becoming optimal.
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
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
Evaluate fiction against a distilled novel style profile and identify style drift, AI-like prose, and concrete revision targets. Use when the user asks to score, check, compare, evaluate, critique, or revise a draft against a saved novel style.
AI film production pipeline orchestrator for end-to-end content creation. Use when: coordinating production pipeline, generating scripts to film, orchestrating team, production planning, full workflow from concept to final edit. Keywords: film, pipeline, orchestrator, production, workflow.
Generate images with FLUX models (Black Forest Labs) via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA with custom style adaptation. Capabilities: text-to-image, image-to-image, LoRA fine-tuning, custom styles. Triggers: flux, flux.2, flux dev, flux schnell, flux pro, black forest labs, flux image, flux ai, flux model, flux lora
Game design consulting based on Richard Rouse III's Game Design Theory and Practice. Use when helping with game design decisions, player psychology, gameplay systems, storytelling, playtesting, or evaluating fun. Provides frameworks for understanding what players want, creating engaging gameplay mechanics, balancing challenge and fun, non-linear design, in-game storytelling, and effective playtesting practices. NOT for coding or programming - focused on design philosophy and player experience.
This skill enables cross-model dialogue between Claude and Gemini with shared visual memory. Use when the user wants to generate images, have visual dialogues with AI, create scientific illustrations with continuity, or have multiple AI perspectives respond to the same prompt. Key trigger phrases: "generate an image", "visual dialogue", "ask the daimones", "resonance field", "Minoan tarot", "cross-model", "KV cache", "MESSAGE TO NEXT FRAME".
Expert in video composition, editing, and format conversion. Use when the user wants to generate high-quality video, overlay images on video, concatenate clips, create GIFs, or sync audio to video using mcp-avtool-go and mcp-veo-go.
Generate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the content of images, videos, or files. Supports single/multiple inputs, URLs, local paths, and base64 (images only).
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.