Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Multi-speaker dialogue audio creation with ElevenLabs and Dia TTS. Covers speaker tags, emotion control, pacing, conversation flow, and post-production. Use for: podcasts, audiobooks, explainers, character dialogue, conversational content. Triggers: dialogue audio, multi speaker, conversation audio, dia tts, two speakers, podcast audio, character voices, voice acting, dialogue generation, conversation tts, multi voice, speaker tags, dialogue recording, elevenlabs dialogue, eleven labs conversation
Agent Media OS — resolve any media need (BGM, SFX, image, icon) into a frozen local file + ledger record. One verb (`resolve`) handles the full cascade — project cache, global cache, HeyGen catalog search, freeze, register. Keeps search noise on disk, hands the agent a path. Use when a composition needs background music, sound effects, images, or icons.
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
Convert written documents to narrated video scripts with TTS audio and word-level timing. Use when preparing essays, blog posts, or articles for video narration. Outputs scene files, audio, and VTT with precise word timestamps. Keywords: narration, voiceover, TTS, scenes, audio, timing, video script, spoken.
Clone or update https://github.com/sxhzju/ruler-progress-animator and render a ruler progress video with default parameters. Use when users ask for requests like "绘制个尺子进度条", "做个尺子进度动画", "渲染 ruler progress", or ask to export the default demo video from this project.
Use when working with ComfyUI workflows in OpenMontage, including comfyui_image/comfyui_video/comfyui_music, custom workflow_json/workflow_path inputs, output_node selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
Generate short marketing videos for products on Douyin Shop/Douyin using Volcano Engine KickArt’s one-click video creation service. Supports providing product links or product IDs, uploading custom image/video assets, submitting asynchronous video creation tasks, checking progress, retrieving the resulting video, and syncing creative assets. Use this skill when users send a Douyin Shop/Douyin product link or mention “upload assets,” “add image,” “add video,” “one-click video creation,” “generate short video,” “marketing video,” “product video,” “create finished video,” or “check video creation progress.”
Extract useful frames from local video files based on task intent, such as persona research, shot breakdown, product visibility, UI walkthroughs, visual-style review, or CTA/compliance checks. Use when the goal is to select the right still frames and contact sheets for a specific downstream need, rather than perform generic video analysis
Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without an explicit migrate request — treat as fresh build. In doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.
Use when the user asks for a content director or a task matching the examples below. All-in-one content director that bundles FOUR format specialists — talking-to-camera, silent POV, dance, and stitch/duet — behind a single front door. Ingests the user's Instagram or TikTok handle, then in Stage 0 asks which KIND of trend they want to make (talking / POV / dance / duet, each explained), recommends a format from their profile when they're unsure, and can present a cross-format sampler menu (~10 real trend cards with links spanning all four formats) so the user picks one card. Once a format (and optionally a specific trend) is locked, it loads the matching format playbook from `formats/<format>.md` and runs that pipeline end-to-end. Triggers — "be my content director" (when the user wants to choose a format), "what kind of trend should I make", "talking vs pov vs dance vs duet", "show me trends across formats", "content director bundle", "content-director".
Image prompting skill for Nano Banana (NBP/NB2) and GPT Image 2.5 (Flare/Sunburst). Writes ready-to-use prompts with model/quality/size recommendations. Use when: "нарисуй", "сгенерируй картинку", "image prompt", "промпт для картинки", blog covers, slides, posters, product shots, UI mockups, storyboards, character sheets, edit/colorize, style transfer, vision analysis, image-to-prompt, nb, NBP, NB2, gpt-image-2.5, multi-panel grids, ecommerce product photography, fashion editorial, food/beverage ads, cinematic portraits. Do NOT use for: video (use the video skill), 3D models, audio, non-image tasks.
Configures and uses snipgrapher to generate polished code snippet images, including syntax-highlighted PNGs, SVGs, and WebP exports with custom themes, profiles, and styling options. Use when the user wants to create code screenshots, turn code into shareable images, generate pretty code snippets for docs or social posts, produce syntax-highlighted images from source files, or explicitly mentions snipgrapher. Supports single-file renders, batch jobs, watch mode, and reusable named profiles via the snipgrapher CLI or npx.
This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.
Use when the user asks to fix their look or requests a task matching the examples below. Change anything in a video — background, scene, lighting, outfit, weather, mood — from a free-form prompt, while keeping the exact original facial identity, motion, speech, audio, and closest supported output ratio. Edit the first frame with gpt-image-2, then propagate that look across the clip with Kling reference-video using the original clip as the identity anchor. Triggers: "change anything in my video", "edit my video with a prompt", "change the background of this video", "change my outfit in this clip", "restyle this video without changing the person", "put me on a beach", "make this video at night", "/fix-my-look".
An orchestrator skill that polishes Korean text written by AI (ChatGPT, Claude, Gemini, etc.) so it reads "as if a person wrote it". It detects and classifies 85 AI patterns across 10 categories — translationese, excessive English quotations, mechanical parallelism, clichés, overuse of passive voice, overuse of connectives, uniform rhythm, too many emoji/bullets, and more — and rewrites only style, rhythm and expression, leaving the content untouched. The shim's route_hint(light|standard|heavy) decides the path: well-written text takes 1 call, standard 2 calls, and only severe or long text needs 3+ calls (diagnose → targeted polish → finalize). Triggers — "remove the AI feel", "make AI text sound natural", "GPT/ChatGPT style", "fix AI translationese", "polish it like a human wrote it", "AI polish", "remove ChatGPT feel", "detect and polish AI text in Korean", "make AI text read like a human", "remove translationese", "polish text with too many English quotes", "make AI text undetectable", "humanizer", "humanize Korean", "AI detector bypass for Korean". Follow-ups — "redo just one category", "adjust polish intensity", "change the genre", "only this paragraph", "second pass" — all use this skill too. Handle simple spelling and typo fixes yourself, use the translation skill for translation, and a separate writing skill for rewrites that add or remove content.
Generates professional animated CLI demos as GIFs using VHS terminal recordings. Use to create terminal demos, record CLI workflows as GIFs, generate animated documentation, build demo tapes for README files, or showcase any command-line tool visually: record terminal / VHS tape / demo GIF / animate my CLI.
Transcribe audio and video files to text using OpenAI Whisper. Use when: converting podcasts to blog posts; creating video subtitles; extracting quotes from interviews; repurposing video content as text; building searchable audio archives
Replace primitive 3D shapes with real GLB models — animated characters, world props, buildings, and scenery for Three.js games. Use when the user says “add 3D models”, “replace the boxes with real models”, “add GLB assets”, or “make the 3D game look real”. For 2D pixel art, use add-assets instead. Do NOT use for 2D pixel art (use add-assets) or gameplay changes (use add-feature).
AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.
Removes multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B, always offered), and C2PA/EXIF/XMP/container metadata in PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD/TEX. Covers Claude, Gemini/SynthID-class, OpenAI provenance, and open-LLM sampling marks. Use when the user asks to strip watermarks, remove C2PA/Content Credentials, clean AI metadata, remove invisible Unicode, get clean anti-detect AI output, or runs /remove-ai-marks (aliases: /remove-claude-marks).
This skill should be used when the user asks to "create a location", "add a location", "magic system", "political system", "build the world", "add culture", "world history", "technology system", "religion", "economy", "map", "travel times", "routes", "calendar", "moons", "seasons", "naming language", "conlang names", "trade routes", "supply lines", "magic cost", "add a glossary term", "glossary", "invented word", or wants to develop any aspect of a story's world and setting. NOT for a glossary for translators (use adaptation).
Create videos from a text prompt using HeyGen's Video Agent (POST /v3/video-agents). The default for most video requests — AI handles the script, avatar, visuals, voiceover, and captions automatically. Use when: (1) Creating a video from a description or idea, (2) Generating explainer, demo, or marketing videos from a prompt, (3) Making a video without specifying exact avatars, voices, or scenes, (4) Quick video prototyping or drafts, (5) The user says "make me a video" or "create a video about X". For precise control over specific avatars, exact scripts, or per-scene configuration, use the avatar-video skill instead.
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve before it writes any code. Anti-AI-slop.
Creative coding skills for Claude Code, claude.ai and Cowork. Motion, micro-interactions and design systems across Web (GSAP, Motion, Three.js, CSS), Android (Jetpack Compose) and Apple (SwiftUI). Proposes an interaction thesis you approve before it writes any code. Anti-AI-slop.
Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.
Validate Blender animation attempts before accepting them by rendering contact sheets, checking silhouette stability, flicker, framing, subject dominance, layer separation, export compatibility, and motion-design coherence. Use after animation renders or when the user says motion/morph/outside elements look bad.
Generate and edit images with Alibaba Qwen-Image-2.0 models via inference.sh CLI. Models: Qwen-Image-2.0 (fast), Qwen-Image-2.0-Pro (professional text rendering). Capabilities: text-to-image, multi-image editing, complex text rendering. Triggers: qwen image, qwen-image, alibaba image, dashscope image, qwen image 2, qwen image pro
Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs. Triggers: qwen image pro, qwen-image-pro, qwen 2 pro, alibaba image pro, dashscope pro, professional text rendering
Create, extract, and apply portable visual design systems via visual-style.md files. Use when: (1) Creating a visual-style.md design system from scratch, (2) Extracting a visual style from a website URL, video, or PDF brand guide, (3) Applying a visual style to HeyGen videos, HTML slides, Figma, or paper.design, (4) Browsing the gallery of pre-built visual styles (Swiss, Saul Bass, Game Boy, etc.), (5) User mentions "visual style", "design system", "brand style", or "style guide", (6) Styling a HeyGen video with a consistent design language.
Plan, generate, edit, compare, and review images with Google Gemini (Nano Banana) image models, with an exact plan and explicit approval before every paid call. Use when the user asks to create or edit an image, picture, photo, illustration, logo, thumbnail, poster, banner, product shot, mockup, character sheet, infographic, or diagram; keep a character or product consistent across images; add exact text to an image; or compare image models
Turn papers, technical articles, or knowledge content into highly realistic AIGC slides. First create the narrative structure and direct the visuals page by page, then call an image generation model to generate each 16:9 slide image, and finally combine them into PPTX/PDF. Suitable for paper presentations, lab meetings, public lectures, technical talks, and commercial research presentations; use when the user mentions “paper PPT”, “AI-generated PPT”, “PPT that doesn’t look AI-generated”, “high-quality slides”, or “page-by-page image generation PPT”.
Produces human-sounding text that avoids detectable AI writing patterns. Activates on any writing task — tweets, emails, articles, bios, captions, reports, copy, messages, LinkedIn posts, cover letters, README files, or any content where the output must not read as AI-generated. Enforces banned vocabulary, structural variety, punctuation discipline, accuracy rules, and voice calibration. Use when the user says "write," "draft," "rewrite," "make this sound human," "anti-slop," "not AI," or any variation of wanting authentic-sounding output.
Generate custom 3D models from text or images using Meshy AI, then auto-rig and animate them for Three.js games. The preferred source for all 3D game assets. Use when the user says "generate a 3D model", "create a character model", "use Meshy", or needs a custom GLB model that doesn't exist in free libraries.
Generate AI images and videos via the LetzAI API. Images with Nano Banana Pro, Seedream 5, Flux 2, GPT Image 2; videos with Veo 3.1, Kling V3, Seedance 2.0. Includes context editing, upscaling, asset uploads, and custom @model training. Use for content creation apps and automation.
Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or set up OpenChatCut; inspect or edit an OpenChatCut project; work with its timeline, transcript, captions, media, generation, motion graphics, audio, color, or export tools; or recover from an OpenChatCut MCP error.
Harmonize multiple Blender skills into a coherent pipeline with clear activation precedence, handoff artifacts, dependency gates, and conflict-resolution rules. Use when a Blender task spans several skills, when reference-locked work conflicts with generic production workflow, after adding/updating skills, or when repeated failures indicate skill interference or missing inter/intra-play.
Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, 3D print a model, or interact with the Meshy API.
Measure and validate supplied reference images, wireframes, texture atlases, and Blender renders before declaring a reconstruction 1:1. Use when an asset must match a template, when visual feedback says the output is off, when part counts must be exact, or before exporting a brand mascot/logo reconstruction. Pairs with reference-to-3d, contour-to-mesh, orthographic-registration, atlas-uv-fitting, and Blender MCP.
Swap faces in a video using AI via the HeyGen API. Use when: (1) Replacing a face in a video with another face, (2) Face swapping from a source image onto a target video, (3) Creating personalized videos by swapping in a person's face, (4) Working with HeyGen's /v1/workflows/executions endpoint for face swap processing.
Act as an assistive writing coach who guides but never writes for the user. Use when helping someone develop their own writing through questions, diagnosis, and frameworks. Critical constraint — never generate story prose, dialogue, or narrative content. Instead ask questions, identify issues, suggest approaches, and let the writer write
Use to build a reusable voice guide (voice.md) by analyzing a person's or brand's ACTUAL writing samples — so every other social skill can write in their exact voice instead of generic AI prose. Run this when the user says "build my voice," "sound like me," "capture my tone," "analyze my writing," "train on my posts," "ghostwrite in my voice," or when content keeps coming out off-voice or generic. Requires real writing samples; if there are none, use brand-profile's voice interview instead. Works for anyone: founders, creators, executives who are ghostwritten, and brands. Read brand-profile first; this skill produces the deeper voice.md that complements it. This skill DEFINES the voice; to apply it per piece — tone shifts, style edits, de-AI-ing a draft — use writing-style-and-tone.
Makes AI-generated content sound genuinely human — not just cleaned up, but alive. Use when content feels robotic, uses too many AI clichés, lacks personality, or reads like it was written by committee. Triggers: 'this sounds like AI', 'make it more human', 'add personality', 'it feels generic', 'sounds robotic', 'fix AI writing', 'inject our voice'. NOT for initial content creation (use content-production). NOT for SEO optimization (use content-production Mode 3).
DashScope (Alibaba Cloud Bailian / 阿里云百炼) integration — image generation (qwen-image-2.0-pro), text-to-speech (qwen3-tts-flash), and ASR with word-level timestamps (qwen3-asr-flash-filetrans). Use when generating images via Qwen-Image, narrating via Qwen-TTS, or transcribing with word-level timestamps via Qwen-ASR.
Generate storyboard image boards and matching video-generation prompt scripts for specific scenes in a short video plan. Use this skill whenever the user asks to create a storyboard, storyboard image, video prompt script, scene prompt, image-to-video prompt, shot board, or per-scene video-generation package, especially when they specify a scene number, duration, or an existing video plan. This skill saves outputs as storyboard/scene-XX.png and storyboard/scene-XX.md and enforces grid sizing, timing labels, and strict character, wardrobe, prop, and location continuity.
Use this skill when the task is clearly connected to the user's YouMind workspace, YouMind APIs, or the youmind CLI. It helps agents search, inspect, and call YouMind OpenAPI endpoints to work with boards, groups, YouMind files, picks, chats, and YouMind skills.
Calibrate Blender materials, lighting, camera crop, emission/glow, color management, and aura/HUD styling against supplied original/reference images using measurable color, brightness, saturation, bbox, and mask statistics. Use when a product must match the lighting/look of a source image or when audits say the product is too bright, desaturated, wrong hue, wrong glow, or wrong silhouette extent.
Install, verify, troubleshoot, and operate the Adobe Premiere Pro MCP server. Use when a user wants an agent to set up Premiere MCP, connect Claude Code/Codex/Claude Desktop, control Premiere, import media, build sequences, edit timelines, apply effects, or diagnose bridge issues.
AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction, audio repainting, and continuation for video production. Use when generating music, soundtracks, jingles, or working with audio stems. Triggers include background music, soundtrack, jingle, music generation, stem extraction, cover, style transfer, repaint, continuation, or musical composition 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.