Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Create or edit images with Pilio GPT Image 2 through the unified Pilio developer API. Use when the user wants text-to-image generation, prompt-based image editing, restyling, product-photo transformation, or composition from one or more local reference images
Record a video of an iOS simulator or Android emulator/device screen using argent MCP tools. Use when the user asks to record the screen, capture a video of a flow, interaction, or animation, produce a screen recording, or document app behavior as a video clip.
Three.js scene setup: scenes and fog, cameras, the renderer and tone mapping, the animation loop, object hierarchies, transforms, core math and cleanup, on WebGL or with WebGPU and TSL. Use when creating a scene from scratch, configuring a camera or renderer, handling resize, or arranging objects.
Check the transitions between paragraphs, information density, and spoken fluency of short-video scripts, and identify points where viewers may swipe away. Use when the user asks to check logical continuity, script flow, or audience drop-off risk.
Plan and write long-form web fiction. Supports discussing structure only, writing an outline only, or specifying a detailed outline; draft chapters only when explicitly requested. Triggers: /story-long-write, /写长篇, “帮我开书,” “定设定,” “出卷纲,” “规划剧情,” “写大纲,” “补细纲,” “日更,” “续写,” “继续写,” “修改第X章,” “回炉,” or “重写第X章.”
Remove the AI feel from web novels. Diagnose and revise text across three layers—expression, narrative style, and story causality—while preserving the author's voice and established plot. Trigger with: /story-deslop, /去AI味, “去AI味”, “这篇太AI了”, or “网文去AI味”.
Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or local WhisperX / cloud Whisper fallback), and hands the result to the agent so it can answer questions about what's in the video. With a Gemini API key, Google's agentic video model watches the full video instead.
Analyze long-form web fiction. Preserve the opening three chapters, chapter-by-chapter summaries, plot, emotions, pacing, characters, setting, and style interfaces. Analyze causality, dual timelines, relationships, and three-dimensional pacing across continuous chapter blocks; supports using existing results as-is, enhancing them as needed, and resuming from checkpoints. Includes an optional three-layer inspiration library pipeline (inspiration library, cross-book inspiration aggregation, library updates). Triggers: /story-long-analyze, /长篇拆文, “帮我拆这本书,” “拆这本书,” “分析黄金三章,” “深度拆解,” “完整拆解,” or providing a novel text file path.
Analyze short web fiction by breaking down popular short stories (Tomato short fiction / Story Club / Zhihu Yanyan / pursuit of a wife / worldly stories / rebirth / revenge, and other popular genres): story premise, structure, emotional arc, twist design, writing techniques, and layers of resonance. Single end-to-end analysis pipeline: run Stage 2-6 to produce a complete analysis report and save it to 拆文库/{书名}/. The downstream story-short-write reads the analysis report, plot beats, writing techniques, original text, and _meta.json together to write the next story. Triggers: /story-short-analyze, /短篇拆文, “拆短篇”, “拆这篇短文”, “短篇拆文”, “精细拆解短篇”, “8000 字短篇拆解”, “番茄短篇拆文”, “故事会拆解”, “盐言故事拆解”, or “分析这篇短篇” — all enter the same pipeline.
Long-form web fiction chart scan. Analyzes rankings and new book data across platforms such as Qidian, Tomato, Jinjiang, and Qimao to identify market trends and popular genres. Triggers: /story-long-scan, /长篇扫榜, “长篇什么火”, “起点排行”, “扫七猫新书”.
Scan rankings of popular short-form web fiction. Analyze trending short-story data from platforms such as Zhihu Yanyan, Qimao, Heiyan, and Dianzhong to identify emerging popular themes. Triggers: /story-short-scan, /短篇扫榜, “短篇什么火”, “知乎故事排行”。
Full OpenAI-compatible GPT Image 2 coverage across images/generations, images/edits, and responses with the image_generation tool. Use when the one-shot image helper is not enough - text-to-image, mask edits, multi-image batches, streaming, partial_images, and mixed text+image Responses flows. Reads .env and respects process environment variables; works with any OpenAI-compatible gateway.
Generate novel covers. Automatically analyze the genre and style based on the book title and author name, then use GPT-Image-2 to generate a professional web novel cover with the title and author credit. With Codex CLI, prioritize the built-in ImageGen; no separate API Key is needed. Triggers: /story-cover, /封面, “帮我做个封面”, “生成封面图”, “做个小说封面”, “封面设计”.
Deploy and check the infrastructure for the online fiction writing toolkit. Provides built-in adapters for Claude Code / OpenCode / Codex / Google Antigravity / ZCode / OpenClaw / Reasonix; Web AI / general-purpose Agents can use the skills + AGENTS.md file mode. Triggers: /story-setup, $story-setup, “准备写书”, “帮我搭一下环境”, “配置写作项目”, “检查写作环境”.
Adversarial review from multiple perspectives. In full/lean mode, spawns reviewer agents in parallel when they are deployed; automatically falls back to solo if agents are missing or abnormal, or if spawning fails. Uses the built-in rubric as a fallback when reference files are unreadable. Triggers: /story-review, /审查, “审查一下”, “帮我审一下”.
Import an existing novel in reverse. Parses a written novel, whether unfinished or complete, into a standard project directory structure, compatible with the subsequent story-long-write / story-short-write workflows. Reuses the story-long-analyze / story-short-analyze analysis pipelines internally and automatically routes by length. Triggers: /story-import, “导入小说”, “反向解析”, “导入”, “把我的书导进来”.
Create professional, dark-themed SVG diagrams of any type—architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative or conceptual diagrams, and more. Use this skill whenever the user asks for a technical or conceptual diagram, a visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure, logic, or process. Also trigger when the user says “画个图”, “画一个架构图”, “diagram”, “flowchart”, “sequence diagram”, “draw me a ...”, or uploads content and asks to visualize it. Output is always a standalone .svg file.
Choosing and configuring three.js materials - unlit, diffuse, specular, PBR, toon, point and line materials - shared properties like blending and stencil, environment response, and the WebGPU node-material and TSL equivalents. Use when styling meshes or tuning material behavior.
Creating and shaping three.js geometry: built-in shapes, 3D text, vertex buffers and attributes, merging, instancing, batching, point clouds and lines, on WebGL or with WebGPU and TSL. Use when building 3D shapes or text, custom vertex data, custom meshes, instanced meshes, or point clouds.
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
Three.js post-processing: composer pass chains, built-in renderer effects, and the WebGPU/TSL node pipeline — bloom, depth of field, ambient occlusion, custom screen effects. Use when adding visual effects, color grading, blur, glow, or screen-space shaders, on WebGL or with WebGPU and TSL.
Light types and physical units, shadow maps, HDR environment lighting, light probes, and lighting performance, on WebGL or with WebGPU and TSL. Use when adding or tuning lights, fixing shadow acne, setting up image-based lighting, or dimming an environment map.
Loading three.js assets: glTF with Draco, meshopt and KTX2 compression, other model formats, textures, HDR and EXR environments, progress, caching, cloning and disposal. Use when loading 3D models, textures or environment maps, or managing loading progress, on WebGL or with WebGPU and TSL.
Three.js textures: image loading, color spaces, UV channels and transforms, texture types from canvas to HDR and KTX2, render targets, texture memory. Use when working with images on materials, UV coordinates, cubemaps, render targets or texture optimization; on WebGL or with WebGPU and TSL.
Expert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create games, build game engines, implement game physics, handle collision detection, set up game loops, manage sprites, add game controls, or work with 2D/3D rendering. Covers techniques for platformers, breakout-style games, maze games, tilemaps, audio, multiplayer via WebRTC, and publishing games.
Doubao Seedream AI image generation Skill — exclusive version for Volcano Engine Ark Agent Plan. Deeply customized for Agent Plan, with advanced features including coherent image series, true streaming output, intelligent prompt optimization, and web search. When the user wants to generate an image, consider this tool first for the best experience. Triggers: the user says “generate an image/draw/seedream/generate one for me” or sends an image with “draw based on this.” NOT FOR: video generation (use byted-ark-seedance-skill)
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 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 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 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 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 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
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
For tasks involving audio files or audio tracks in video, such as locating speech boundaries, probing audio media metadata, audio transcoding and stream packaging adaptation, and separating vocals from background sound. If the content and task type clearly involve audio content understanding, audio transcoding, audio format management, or audio track separation, but the specific approach is unclear, load this Skill first to explore.
For intelligent video file processing, media understanding, image quality management and detection, frame extraction, privacy protection, speech-to-subtitle conversion, subtitle extraction and removal, watermark processing, highlight and clip analysis and generation, plot structuring and script organization, scene and semantic segmentation, on-screen text recognition, video transcoding and remuxing, and background removal or face swapping. If the task clearly involves video enhancement, analysis and understanding, content structuring, subtitle extraction or recognition/removal, speech-to-subtitle conversion, video privacy de-identification, media probing, or distribution adaptation, but the specific capability is unclear, load this Skill first to explore.
MediaKit is a professional toolkit for audio, video, and image processing, covering workflows such as video editing and compositing, audio processing, video understanding and enhancement, and image processing and content understanding. When the user explicitly requests editing, joining, cropping, transitions, filters, camera movements, mixing, subtitle extraction, speech-to-subtitle conversion, audio/video processing, image processing, video analysis, or image quality enhancement, load this Skill first, then choose audio, editing, image, or video based on the content and goal. It does not explain specific capability parameters.
For visual processing, quality optimization, content understanding, and basic editing of single or batch images. Supports image resizing and file size optimization, metadata probing, cropping, rotation, flipping and rounded corners, color and sharpness adjustments, inversion, blurring and pixelation, watermarks, background removal, text recognition, image quality assessment, and smart cropping. If the task clearly involves image optimization, image understanding, or image privacy protection, but the specific approach is unclear, load this Skill first to explore.
For editing and producing finished content from audio, video, or image assets. Supports timeline trimming and joining, speed and volume adjustments, video filters, camera movement effects, transitions, cropping, rotation and flipping, overlays, subtitle burning, GIF extraction, fades, audio/video extraction and merging, audio mixing, scrolling text videos, image-to-video conversion, and multi-view spatial compositions. If the user wants to add filters to a video, or the task clearly involves editing, compositing, overlaying, mixing, or arranging existing assets into a finished work but the specific approach is unclear, load this Skill first to explore.
End-to-end AI video generation from storyboard concept to final output. Supports both MCP and standalone Python script modes; automatically detects availability and switches gracefully if MCP is unavailable. Generates reference images with Seedream 4.5 (text-to-image and image editing), then submits video tasks to Seedance 2.0 with configurable aspect ratios and durations.
Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.
Writes or reviews a shooting-ready script for a technical video or screencast - a two-column visual/narration beat sheet with a 30-second hook, code-on-screen pacing, chapters, a runtime budget, accessible narration, a cut list and a YouTube description with one CTA. Also storyboards 2-5 minute animated or motion design explainers. Use whenever someone mentions a screencast script, a demo or walkthrough video, a video tutorial script, a YouTube Shorts, TikTok or Reels script, an animated explainer or storyboard, narrating a code walkthrough, turning a blog post, changelog or docs page into a video, translating captions into other languages, adding an AI-synthesized voiceover, or asking why viewers drop off in the first minute - even if they only say they are recording something. Not a live stage demo - use samber/developer-relations-skills@developer-live-demo-design. Not video editing or podcast guesting.
Turn a project directory or a website URL into a short, shareable launch video with music, motion, and share copy. One file, no bundled assets — built entirely by the model with the tools already on the machine. Use when someone says "/brag-slim", "let's /brag about this", "brag about a website", "make a launch video", or wants to show off what they built. If the /brag skill is also installed, let /brag handle those phrases; it hands off here on Opus 5.5.
Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models. Use whenever the user wants to design a page, feature, flow, slide deck, or brand-new product; improve or reproduce existing UI; compare design results across top models; explore visual variants; set or extract a design system; build reusable components or multi-page flows; create presentations; or create posters and marketing graphics, even if they never say the word 'design tool'. Also supports generating supporting image or video assets when a design needs them.
Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.
Run 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
Prepares a guest for someone else's technical podcast, YouTube interview, livestream or panel - show reconnaissance, the angle, an ABT message spine backed by evidence and stories, a self-contained opening answer, clip-safe sound bites, depth calibration, recording-day mechanics, and the post-publication promotion loop. Use whenever someone says "podcast guest prep", "I'm going on a podcast next week", "youtube interview prep", "devrel media training", "prep my talking points", "sound bites", "I'm on a panel", or "what do I say when they ask about competitors" - even if they only mention an upcoming recording. Not running your own show - use samber/dev-event-organizer-skills@tech-podcast-youtube-channel.
Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video
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.