Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Score a game's combat skills and spells out of 10 with blind judges, then raise the weakest to a bar, for timing and readability (does a skill read as itself, does the blow land when it lands) and for art (detail, light, trails, impact, art direction, judged against a reference such as Diablo IV). Covers filming casts on a stopped, stepped clock, contact strips and close-ups, anonymised two-judge rounds, the levers that moved scores (hero props made from a painted concept with image-to-3D, own schedules and keyed moves, painted additive textures, camera-facing ribbons, light outside the body), the traps that cost points, asset and load budgets, and shipping each skill as its own version. Use when the user asks to score, review, improve, polish or rebuild combat skills, spells or attacks; says a skill "doesn't make sense", "looks bad" or should look like another game; names a target score; or starts a "next skill" thread. Project specifics (review hooks, harness settings, where each skill's code lives, scores so far) go in an optional local references/<project>.md next to this skill.
AI video generation skill with auto model selection across Seedance 2, Kling 3.0, HappyHorse, and 10+ models. Produces finished multi-shot videos (5–120s) from text, images, URLs, scripts, or audio — including AI music, lip sync, and multi-shot sequencing. No prompts to write, no models to choose. USE FOR: video production, AI video, make a video, product video, brand video, promotional clip, explainer video, short video, TikTok video, Instagram Reel, YouTube Short, product ad, text-to-video, image-to-video, video generation, AI video agent.
Build, fix and review character combat animations (melee strikes, bow shots, spell casts, skills, monster attacks, whole move sets) so they read like Diablo IV, Baldur's Gate 3 or Elden Ring and never stretch, lock, wring or break an arm, wrist or hand. A written standard with numbered rules, per-frame tests on the real skinned mesh, keys designed from upper-arm, forearm and blade intents, checks from every camera the player sees, two blind critics plus a blind A/B against the last release, and every critic claim verified against full-resolution frames and live-rig numbers. Use when creating or reworking any attack, skill or move set; when the user says arms, hands, wrists, elbows or weapons look stretched, weird, broken or wrong; when they ask for a standard, rules or tests for animations; or when they ask to score animations or get them to N out of 10.
Create professional music with the Mureka AI API—songs, instrumentals, and lyrics from natural language descriptions in any language. Use when users want to generate a song, create a beat or instrumental, write lyrics, clone vocals, upload reference tracks, or do anything related to AI music creation, even casual requests like “make me a chill lo-fi beat.”
Use when generating images with Midjourney, constructing MJ prompts, iterating on MJ output quality, choosing between --sref/--oref/style codes, scoring image results, or building reusable prompt patterns. Also use when exploring MJ style codes, animating images, or debugging why a prompt isn't producing the intended result.
Score and filter topics for X content creation using weighted criteria. Use when the user wants to evaluate collected materials, filter topics by score, or mentions “filter topics”, “score materials”, “x-filter”, or “选题筛选”. Applies a 10-point scoring system with customizable weights.
Turn a text prompt, a photo, or a live video clip into hand-made-looking p5.js animation — pencil handwriting that writes itself, photos repainted as brushstroke art with paint-on animation and camera moves, and short videos (iPhone Live Photos included) repainted frame-by-frame as a living painting. Trigger on: "handwritten text animation", "paint this photo", "painted video", "sketch effect", "turn my live photo into a painting", "write-on effect". Everything is 100% code: p5.brush strokes rendered headlessly, no image models.
Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."
Image generation, photo editing, background removal — transparent PNG images, cutouts, ecommerce packshots, product catalogs, lifestyle shots via Bria.ai. Build store-ready e-commerce catalogs at scale — shadows, product dimensions images, lifestyle scenes, marketplace listing variants. ALWAYS use this skill when the user wants to generate, edit, or transform any image — hero images, banners, social media visuals, product photos, illustrations, icons, thumbnails, ad creatives, or marketing materials — or to build a product catalog, create a packshot, stage a lifestyle shot, remove a background, make transparent PNGs, or batch-process product photos. Triggers on packshot, product catalog, product shot creator, lifestyle shot, cutout, product dimensions image, inpainting, outpainting, object removal, upscale, photo restoration, style transfer, relight, reseason, sketch-to-photo. Commercially safe, royalty-free.
Start or reuse a self-contained local web gallery for browsing Codex-generated images. Use when the user asks to browse Codex-generated images, open a local image gallery, inspect ~/.codex/generated_images, view a Codex image output folder, or browse image files produced by Codex.
Edit videos in Pireel Studio through the `pireel` MCP server — first-run setup, local and stock media import, transcript editing, multi-source montage, multiple editable outputs, storyboarding, designed graphics, captions, themes, and export. Read this whenever the user wants to install or connect Pireel or edit, cut, remix, storyboard, illustrate, caption, theme, or export a Pireel video, and before the first Pireel MCP call or after a tool failure. Routes to the matching bundled playbook
Edit images with Alibaba Cloud Model Studio Qwen Image Edit models (qwen-image-edit, qwen-image-edit-plus, qwen-image-edit-max, qwen-image-2.0 series and snapshots). Use when modifying existing images (inpaint, replace, style transfer, local edits), preserving subject consistency, or documenting image edit request/response mappings.
Picks the form that explains best and applies the house explanation style: plain prose, controlled English modelled on ASD-STE100, a diagram, an interactive HTML page, or a narrated explainer video. Use when asked for “ELI5”, “plain English”, “re-pitch that”, “stop using jargon”, “explain it in STE100”, “draw me a diagram of how this works”, “make an interactive explainer”, or “make a 3b1b style video on X”.
Generates 150–750+ ad variations using Alex Hormozi's combinatorial Hook x Meat x CTA framework. Triggers on requests to create ads, ad copy, ad scripts, marketing creatives, video ad scripts, ad hooks, CTAs, ad testing, ad scaling, or ad factories. Also triggers on mentions of Hormozi's ad method or combinatorial ad creation. Does not trigger for general copywriting, email marketing, landing pages, or non-advertising content
Scene and sequence craft (场景/段落/细节/道具/悬念/情趣) — merged from Robert McKee's scene design and five-step scene analysis (value turn, beats, text/subtext, turning points, pacing, image systems), McKee's Dialogue scene types (balanced, comic, asymmetric, indirect, reflexive, minimal), Syd Field's sequence and scene elements, Neill Hicks (less is more, enter late leave early, energy), Richard Walter (action over talk, small gestures, avoid phones/cars/restaurants, list twelve alternative locations), Wendy Henson (action paragraphs, transitions, story-doing), Julian Hoxter (scene beats, objectives and tactics), Mei Feng's value test, and Lu Jun's chapters 意趣要足 (suspense, delay, wit), 细节要妙, 道具要精, 场景要当. Use when writing or fixing a single scene, choosing a location, building a sequence, planting a prop or detail, designing suspense and delay, cutting a scene that "nothing happens" in, or turning talk into action.
Download, export, save, or package images from a Google Gemini conversation/chat/app page, especially uploaded images or generated image previews visible in a Gemini thread. Use when the task needs logged-in Chrome/Gemini state, opening Gemini image lightboxes, downloading the larger displayed image files, renaming them in order, and producing a ZIP archive.
Generate images, short videos, enhance/upscale, train LoRAs, and run campaign workflows through Krea. Intent-first workflow prefabs route common asks to hard recipes for social video, key visuals, image generation, product photography, archviz, enhancement, LoRA training, and ad campaigns. For professional animation, anime series, storyboard-to-video, asset bibles, or shotlist-to-sequence production, use the sibling krea-animation skill.
Story structure for screenplays and stage plays (故事结构) — merged from Syd Field's paradigm and plot points, Blake Snyder's Save the Cat beat sheet and board, Robert McKee's Story (event/scene/sequence/act, inciting incident, progressive complications, crisis-climax-resolution, subplots, story triangle), Julian Hoxter's nine-beat model, Neill Hicks' three acts as attraction/anticipation/satisfaction, and Lu Jun's Chinese short-play structure (凤头猪肚豹尾, 起承转合, eight openings, eight endings, 入戏要快/脉络要清/高潮要高/转变要顺/变化要多). Use when outlining a script, placing plot points and midpoint, fixing a saggy second act, designing an opening or ending, diagnosing "nothing happens", choosing between linear and non-linear designs, or converting a premise into beats and cards.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Edward de Bono's Random Stimulus technique — force-fit a random unrelated object, place, or phenomenon onto a creative target to break familiar association patterns. Use for product ideation, feature naming, brand direction, copywriting, architecture and design choices when ideas from outside the problem space would help. Triggers include "random stimulus", "random word", "force-fit", "de Bono", "inject a random object", "stare out the window", "see the tree and squeeze an idea". Do NOT use for analytical work like debugging, code review, or implementation tasks.
Professional video ad creation with Remotion — Instagram Reels (9:16), website explainers (16:9), and carousels (4:5). Use when creating video ads, animated social content, or educational explainer videos. Includes ElevenLabs voiceover with word-level captions, AI icon generation, background music, ad copywriting frameworks, and Meta campaign management. Also use when the user provides a URL and wants to create a video for that page
Generate AI videos from text prompts or reference materials. Supports HappyHorse, SeeDance, and PixVerse models. Triggers on: "生成视频", "做视频", "video generation", "text to video", "create video", "视频生成", "视频编辑", "video edit", "pixverse", "口型", "lipsync", "对口型".
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
Make a polished video of an app or a feature with OpenScreen's MCP tools, from storyboard to recording, editing and export, then either attach it to a pull request or draft a post on X. Use when the user asks for a demo, a demo video, a screen recording, a product video, a launch clip, a video for X/Twitter, LinkedIn or a README, or to show a change in a pull request (“add a video to the PR”, “show the feature to reviewers”). Also use to set OpenScreen up for an agent, and to continue an OpenScreen demo in a new session.
Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".
SCAMPER (Bob Eberle) — run one existing idea, product, or process through seven systematic transformations: Substitute, Combine, Adapt, Modify/Magnify, Put to other use, Eliminate, Reverse/Rearrange. Use when there is already one working idea and the need is disciplined variations of it, e.g. "give me variations", "riff on this", "scamper", "what can we substitute or combine", "remix this feature". Do NOT use for analytical work like debugging, code review, or implementation tasks, and not for blank-page ideation (needs an existing idea as input).
Generate short-form video content for platforms such as Xiaohongshu, Douyin, X/Twitter, and WeChat Channels. Analyze user input, automatically adapt to platform specifications, generate video scripts, and call a video-generation backend. Use when the user asks to “generate a short video,” “make a video,” or mentions “short video,” or wants to create video content for social platforms.
Add volumetric underwater god rays to a Three.js scene, marching one drifting swell field along every view ray at half resolution so the light shafts converge on the sun, parallax with the camera and carry rippling caustic streaks, with a shimmering surface underside, a sun that wobbles through the ripples, and the same light dappling fish as they swim through the beams. Use for underwater scenes, oceans seen from below, aquariums, reefs, kelp forests, diving and shipwreck scenes, schools of fish, sunbeams or light shafts through water, caustics, "rays of light shining through the ocean", or watery ripples on a background. Includes a reusable module and the Blue Hour sardine-school demo.
Use when the user runs /add-read-aloud or wants the app to speak text with Grok text-to-speech: read-aloud button on assistant replies, auto-speak, TTS, voice output, narration, IVR prompts, speech tags, voice_id. For a two-way voice agent use /add-voice. For speech-to-text use /add-dictation.
Edit, transform, extend, upscale, and enhance videos using EachLabs AI models. Supports lip sync, video translation, subtitle generation, audio merging, style transfer, and video extension. Use when the user wants to edit or transform existing video content.
Diagnose and guide revisions in non-fiction books. Use for non-fiction book revision, when arguments feel weak, evidence is outdated, readers report confusion, thesis is unclear, or book structure has problems. Keywords: non-fiction, revision, thesis, argument, evidence, structure
Turn AI-generated or existing videos and image sequences into web animations driven by scrolling, pointers, dragging, touch, device orientation, audio, data, or state changes: design motion direction, generate keyframes and video, organize them into a spritesheet or video, compile the timeline, and connect it to the runtime. Use when users need character turnarounds, product breakdowns, camera fly-throughs, one-shot transitions, or need to clean up, chroma-key, add frames to, or compress green-screen videos and spritesheets. Not for interface transitions and microinteractions achievable with CSS, JS, SVG, Lottie, or real-time 3D alone (leave those to regular frontend implementation), nor for standalone film editing, single illustrations, or static pages.
Lead workflow for developing vgpu features and Blender assets with the repository's subharness specialists. Use for agent-based research, API design, implementation, shaders, materials, simulations, or ImageGen-guided asset iteration, and when the human mentions the agent flow or subharness team.
Remove signs of AI-generated writing from prose, and keep it out of a repo. Use when drafting, editing, or reviewing text to make it sound natural and human, or when auditing a whole docs folder for AI slop. Detects 41 patterns across content, language, style, communication, filler, and rhetoric, including: significance inflation, promotional language, -ing tails, vague attributions, AI vocabulary, copula avoidance, negative parallelisms, false agency, em dash overuse, chatbot artifacts, hedging stacks, staccato drama, and aphorism formulas. Includes voice calibration, a no-fabrication rule, statistical tells, and a draft -> audit -> final rewrite loop.
Assumption Inversion — list the assumptions behind the current approach and flip each one, then ask where the flipped version could actually be true. Use when requirements encode beliefs nobody has questioned, when a design feels inevitable, or when incumbents all share one blind spot. Triggers include "invert", "flip it", "flip the assumption", "reverse the premise", "what if the opposite were true", "challenge the assumption". Do NOT use for analytical work like debugging, code review, or implementation 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.