Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Generate Mike-style YouTube thumbnail concepts and final drafts for Convex videos using Mike's local head-and-shoulders photo cutouts and local Convex logo assets. Use when the user asks for thumbnails, YouTube thumbnails, video thumbnail options, or a thumbnail like the Convex static hosting "NO DASHBOARDS" example.
The foundational theory of interactive experience design - loops, motivation, feel, and the art of meaningful playUse when "game design, core loop, game feel, player motivation, game mechanics, meaningful choice, progression system, game economy, game balance, playtesting, GDD, game document, fun factor, engagement, flow state, risk reward, player agency, juice, game polish, 8 kinds of fun, bartle types, MDA framework, game-design, player-experience, core-loop, motivation, game-feel, MDA, playtesting, GDD, systems-thinking, player-psychology, engagement, flow-state" mentioned.
One-time project setup for creative writing: interview the author about the project, writing samples, and voice, then create the AGENTS.md, kb/ layout, and style files every writing agent reads. User-invoked; run it once when starting a project.
Use SpriteCook saved presets through MCP. Use when the user explicitly asks to use a preset, refers to one of their saved SpriteCook presets, asks for the same style/settings as a saved preset, or asks to save a private preset for future consistent asset generation.
Write a YouTube video script from a raw idea: hook options based on 21 formulas, scored, followed by the full spoken script with retention beats marked. Use whenever the user wants a video script, a hook, an opening line, asks “what should I say” or “write my next video,” or is about to record without having the first fifteen seconds yet.
AI creative director that turns a user's natural-language idea into a complete storyboard and generates all assets — images, video clips, and audio — automatically. The user only describes what they want; all prompt engineering is handled internally.
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
Generate pixel-art self-portrait, profile card (自画像卡), emoji GIFs, and meme stickers. Use when: "生成形象", "画头像", "avatar", "self-portrait", "表情包", "梗图", "贴纸", "sticker", "换一个", "重新生成", "不喜欢", "regenerate". Also use when Cola wakes up — display existing avatar or prompt user to generate. Also use when repairing sticker behavior — if ~/.cola/avatar/ has sticker files but AGENT.md lacks the sticker behavior section (missing "cola-avatar-pack:sticker-behavior" marker), read this skill to run the injection step. Do NOT use when discussing third-party platform avatar settings or searching for external stickers.
Choose the right fal.ai endpoint for a given task. Modality-organized catalog of production endpoint defaults, text-to-image, image-to-image, text-to-video, image-to-video, and more. Use when the user has not named a specific model, or asks "which model for X", "best endpoint for Y", "what should I use for Z".
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema Studio 2.5/3.0, Vibe Motion, troubleshooting failed generations, credit optimization, Photodump, or any mention of higgsfield.ai. Also trigger on generic "write me a video prompt" or "make me an AI video prompt" requests when Higgsfield is the user's configured platform.
Design 3D-printable parts as Python functions with nurb. Use when the user wants a part designed, changed, or checked for 3D printing (a bracket, mount, holder, enclosure, shelf, or any STL/STEP to print), and in any directory with a parts/ folder. The user describes the part and judges it in a browser; you model it.
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams and method illustrations with a Claude-supervised iterative refinement loop. Use when the user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
Use when a task involves game textures or materials through the Scenario MCP: seamless or tileable textures, themed texture packs (brick, wood, stone, floors, hand-painted), PBR materials (albedo, metallic, roughness, normal) on 3D assets, retexturing a mesh, material iteration from reference images, texture upscaling that must preserve tiling, or sizing textures for game engines. Keywords: seamless texture, tileable, PBR, material, retexture, texture upscale, surface.
Correct subtitle files (.srt) generated from speech recognition. Use when the user uploads subtitle files and asks to correct, fix, or proofread subtitles, especially for technical content like programming tutorials, AI/ML courses, or any content with domain-specific terminology. Supports Chinese and English subtitles with intelligent error detection and correction while preserving exact timeline information.
A library of creative mechanics — the structural patterns that define how an ad constructs meaning between its hook, visuals, and narrative. Use this whenever designing ad concepts, briefing creative, or trying to explain why a specific ad works beyond just its hook or format. Trigger when a user describes an ad they saw and wants to understand or replicate what made it work, when building a creative concept from a messaging angle, or when execution needs more than a hook and a format — it needs a structural idea. Creative mechanics sit between hooks and visual formats in the Creative Strategy Engine: hooks say what, formats show how, mechanics define the cognitive or emotional mechanism that makes the concept land. Always pair with Hook Writing for opening line execution and Hook Tactics for tactic classification.
Deep pixel art expertise covering fundamentals, limited palettes, dithering patterns, subpixel animation, tile design, retro hardware constraints, and HD-2D hybrid techniques. Knowledge Claude wouldn't normally have from indie masters like Pedro Medeiros (saint11). Use when "pixel art, sprite art, dithering, limited palette, subpixel animation, tileset, autotile, pillow shading, selective outline, selout, hue shifting, color ramp, NES style, SNES style, HD-2D, Aseprite, retro game art, 8-bit, 16-bit, pixel-art, sprites, animation, retro, indie-games, dithering, palettes, tiles, subpixel, aseprite, NES, SNES, GBA, HD-2D" are mentioned
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is my intro/hook". Use this for deterministic extraction from the index — chapters with timestamps, a fileable bug report with the exact frame, or a scored hook analysis.
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
Use AutoAE when the user wants to find or customize a video template for an animated segment—such as an intro, outro, transition, title, lower third, logo animation, or product showcase—using their own text, images, or videos; or wants to preview, render, download, inspect Credits, or report feedback in an existing AutoAE workflow.
Rewrite a given document to remove AI-like writing. Automatically selects the most suitable humanizing strategy (humanizer-zh / humanize-chinese / technical-writing) and iterates until the result meets the standard or up to 42 iterations. Applies to de-AI-ifying Chinese text, including general articles, technical documentation and academic papers. Use when the user says: "humanize this", "去AI味", "降AIGC", "人性化改写", "改成人话", "去除AI痕迹", "humanize document", "make text human-like", "去机器味", "降低AI率", "过AIGC检测"
The ultimate YouTube creator skill. Covers channel audits, video SEO, retention-engineered scripts, hook writing, thumbnail briefs, content strategy, content calendars, Shorts optimisation, analytics interpretation, monetisation planning, competitor research, cross-platform repurposing, upload metadata packages, and data-driven video idea generation. Triggers on: “youtube”, “channel”, “video”, “views”, “subscribers”, “watch time”, “shorts”, “thumbnail”, “CTR”, “retention”, “monetize”, “script”, “hook”, “upload”, “youtube audit”, “video ideas”, “content calendar”, “competitor analysis”, “repurpose video”, “youtube seo”, “youtube strategy”, “youtube analytics”.
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
Creative-writing domain knowledge for durable story state. Load when preserving or retrieving project memory — fact extraction, context scoping, reference writing, artifact layout, and issue tracking. If you are a knowledge agent such as kb-lead, load this for the fiction-specific categories and conventions your general methodology doesn't cover.
Expert patterns for 3D level design using GridMap with MeshLibrary, CSG constructive solid geometry, occlusion, and runtime GridMap builders. Use when building 3D levels, modular tilesets, or BSP-style geometry. For sky/fog/Environment recipes, route to godot-3d-lighting. Trigger keywords: GridMap, MeshLibrary, set_cell_item, get_cell_item, map_to_local, local_to_map, CSGCombiner3D, CSGBox3D, CSGSphere3D, CSGPolygon3D, OccluderInstance3D, bake CSG.
Maintaining the story knowledge base: creating, updating, and organizing wiki-style reference pages in kb/. Use when capturing finalized story knowledge, updating character profiles, documenting world mechanics, or restructuring the kb.
Generate or edit artwork with built-in Codex image gen, especially transparent PNG ornaments, game sprites, emblems, and UI graphics. Use when the user requests GPT 2.5 Flare, /codex-gpt-image-2-5-flare, or this built-in transparent-asset workflow. Includes alpha verification, prompt preservation, and optional project integration.
Download videos from 1800+ platforms (YouTube, Bilibili, Twitter/X, TikTok, Vimeo, Instagram, etc.) and generate complete resource package with video, audio, subtitles, and AI summary. Actions: summarize, download, transcribe, extract video content. Platforms: youtube.com, bilibili.com, twitter.com, x.com, tiktok.com, vimeo.com, instagram.com, twitch.tv. Outputs: MP4 video, MP3 audio, VTT subtitles with timestamps, TXT transcript, MD AI summary. Auto-installs uv, yt-dlp, ffmpeg. Python dependencies managed by uv.
Build a game-ready 3D asset in Blender from reference images (concept art, photos, turnarounds, sketches, screenshots) for any category, including characters, creatures, architecture, vehicles, props, weapons and environment pieces, through gated phases with rendered evidence compared against the reference. Use this whenever a user supplies or mentions a reference image and wants a 3D model or game asset made from it (modelled, blocked out, sculpted, retopologised, textured, rigged, animated or exported for a game engine), even when Blender is not named. Includes bpy scripts for scene calibration, review renders matched to the reference camera, silhouette measurement, validation, baking, GLB/FBX export with manifests, and clean reimport.
Model-family-specific prompt craft for fal.ai endpoints. Trigger when the user mentions a specific model family by name and asks how to prompt it ("how do I prompt Kling", "GPT Image 2 prompt structure", "Happy Horse tips"), or when prompts to a routed endpoint keep coming back generic and the family's known nuances should be applied. For endpoint selection ("which model for X"), use `fal-models-catalog` instead. This skill is about how to talk to a model once it has been chosen.
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.