Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Must read before using the hosted ChatCut plugin in Codex, including creating projects, opening the editor, or editing/creating videos. Also use when ChatCut tools are missing or need authentication. For ChatCut Desktop, follow its own instructions unless the user explicitly chooses the hosted plugin/web surface.
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.
Use only when working on the docs site. Paint an editorial illustration for a docs page, used as a hero visual metaphor that captures the intent of the entire article. Every page opens with one, so use it whenever a page is being written or has none yet.
AI image generator for film scenes, concept art, storyboards, visual references. Use when: generating images, concept art, storyboards, visual references, scene visualization. Uses MiniMax for image generation. Keywords: image, art, concept, storyboard, visual, generate.
Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-reference brand styling, declarative subject-first prompts), the step-count strategy (4–8 for fast iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when to route to Flux 2 Pro / Seedream 5 / GPT Image 2 instead. Calls `runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image` (or `/4b/`) through the local RunComfy CLI. Triggers on "flux 2 klein", "flux-2-klein", "flux klein", "BFL flux 2", or any explicit ask to generate with this model
Extract the actual core loop from a game, feature set, or pitch based on repeated player actions, feedback, rewards, and renewed motivation. Use when a team can list mechanics but cannot clearly articulate the repeatable loop that drives engagement, when a pitch sounds like disconnected features, when a design document lacks loop clarity, or when you need to test whether the claimed loop is coherent, rewarding, and structurally complete.
Complete genviral Partner API automation. Create and schedule posts (video, slideshow, text-only) across TikTok, Instagram, YouTube, Pinterest, LinkedIn, Facebook, X, Bluesky, and other supported platforms. Includes slideshow generation, file uploads, template/pack management, analytics, and full content pipeline automation.
Production recipes for GSAP visual effects. Companion to official gsap-core and gsap-timeline skills (API reference). Triggers: glitch effect, cyberpunk glitch, RGB displacement, chromatic aberration, scramble text, jitter animation, noise bars, marquee, infinite scroll, directional marquee, rolling counter, animated number, count up, floating animation, yoyo, pulse ring, repeating timeline, GSAP VFX, visual effects, decorative animation, looping animation, footer bounce, morph bounce, elastic footer. Non-triggers: Not for scroll-driven reveals (use gsap-scroll), text-only animation (use gsap-text), SVG path/morph (use gsap-svg), or mouse-driven interaction (use gsap-interact). Outcome: Produces visual effects — glitch/chromatic aberration, infinite marquees, directional marquees, rolling counters, floating decorations, pulse rings, footer bounce reveals, and repeating timeline patterns.
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Upscale image resolution with AI using each::sense. Enhance low-resolution images to high resolution while preserving detail, sharpness, and texture. Recover detail from compressed or small images. Powered by topaz-upscale-image for studio-quality results. Use for: print preparation, restoring old photos, enhancing thumbnails, improving AI-generated images, social media quality, e-commerce. Triggers: upscale image, image upscaling, enhance resolution, increase resolution, super resolution, upscale photo, enlarge image, hd image, enhance image, sharpen image, improve quality, hi-res
Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes.
A line editor that reads prose sentence by sentence and shows which lines are weak — filtering, overwriting, flat rhythm, blurred clarity, voice slips — naming the craft principle behind each and pointing at the fix, without ever writing the replacement. It works pattern-first: it surfaces the writer's recurring line-level habits and flags the clearest instances, so they fix the class in their own voice. Use it after the story works, when the prose needs to earn its place line by line. It marks and explains; it never rewrites the author's sentences.
Insert AI illustrations into documents in place. After reading the document, plan insertion points globally, generate all images in parallel, and insert them back into the original text asynchronously. Supports cover images, custom aspect ratios, and three styles. Use when: the user asks to generate illustrations or images for a document/article/note. Also trigger when the user mentions: 配图, 插图, illustration, generate images, document images, 为文章加图.
Viral memecoin content creation and distribution engineering. Use when creating memes, launching viral campaigns, coordinating raids, or building narrative momentum. Covers: meme format selection, viral hooks, platform-specific distribution, community activation, engagement farming.
Mimeng-style viral article writing techniques. Use when creating articles aiming for 100,000+ reads, emotionally resonant content, storytelling, or commentary on social issues. Covers core techniques such as headline crafting, opening design, emotional engagement, punchline distillation, and storytelling.
Generate, monitor, and download MiniMax-H3 videos through the mmx CLI. Use for H3 text-to-video, first/last-frame video, multimodal reference image/video/audio generation, H3 prompt improvement, media preflight, Pay-as-you-go API key selection, task waiting, downloads, and H3 failure handling.
Turn newly recorded talking-head footage into review-ready vertical video drafts with an explicit edit plan, deterministic FFmpeg rendering, captions, hook cards, audio normalization, and visual QA. Use for original Instagram Reels, TikTok videos, YouTube Shorts, LinkedIn videos, founder-led recordings, multiple takes of a new script or idea card, or requests to automate the first video-editing pass. Do not use to mine clips from long-form source videos.
AI companion-style long-form novel writing assistant, combining WPS notes for continuous, memory-aware, context-aware creation without continuity errors. Triggers: help me write a novel, I want to write a novel, continue the novel, write the next chapter, I have a story idea, help me create. Core capabilities: cold-start profiling (worldbuilding + character settings + AI image generation), chapter-by-chapter writing, automatic review of prior text each time to prevent continuity errors, archiving in WPS notes throughout. Not applicable to: short stories, essays, poetry and other non-long-form-novel creation.
Run the PAIDF Orchestration Event Video Generation DAG on Kubernetes - image-to-video anomaly generation, auto-labeling, and anomaly dataset generation. Select for requests about event video generation, anomaly video generation, image-to-video synthesis, Cosmos3 image2video, anomaly dataset creation, safety/surveillance SDG, or generating person-falling, person-climbing, person-running, fighting, smoking/vaping, fire/smoke, or shoplifting video clips from a seed image. Runs environment setup first when controller readiness is unknown. Not for person-crop clothing/attribute augmentation (that is image-attribute-augmentation-workflow) and not for video style transfer.
A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this draft for style", or wants a rigorous line-edit focused on cutting flab, killing dead metaphors, fixing passive voice, and correcting typographic errors like straight quotes, wrong dashes, and double spaces. Also use when the user asks you to be a "tough editor", "strict editor", or "copy editor", or wants feedback on prose quality rather than content or structure.
Converts the user's natural-language video request into prompts that follow the advanced Doubao Seedance 2.0 formula (8 elements: precise subject + action details + scene and environment + lighting and color tone + camera movement + visual style + image quality + constraints). Use for requests such as "write me a Seedance prompt," "generate a video prompt," "make a product ad video," or "generate XX with Seedance." If the user does not explicitly mention Seedance but describes a complex, cinematic single-shot video with multiple subjects, this skill is also preferred.
Create social media graphics and visual assets for any platform. Use when asked to create a social media image, newsletter header, blog feature image, OG image, profile banner, or when the user mentions 'social graphic', 'header image', 'banner', or needs a platform-specific visual asset (not thumbnails — use creator-stack:thumbnail for those).
This skill should be used when the user asks to "build a Three.js scene", "set up React Three Fiber", "animate a mesh with useFrame", "load a GLTF or GLB model", or "add physics with react-three/rapier". Covers scene setup, Drei helpers, the asset pipeline, responsive canvas, and performance budgets for Three.js and React Three Fiber projects.
Transform raw podcast transcripts into polished, readable documents. This skill removes filler words, fixes grammar, adds structure, and preserves authentic voice. Use when processing podcast transcripts, interview recordings, video captions, or any spoken content that needs cleanup while maintaining 100% fidelity to meaning.
VHS terminal recording best practices from Charmbracelet (formerly charmbracelet-vhs). This skill should be used when writing, reviewing, or editing VHS tape files to create professional terminal GIFs and videos. Triggers on tasks involving .tape files, VHS configuration, terminal recording, demo creation, or CLI documentation
Orchestrates end-to-end video generation through sequential workflow steps (audio, direction, assets, design, coding). Activates when user requests video creation from a script, wants to resume video generation, mentions "create video", "generate video", or "video workflow", requests running a specific step (audio, direction, assets, design, coding), asks to "create audio", "generate direction", "create assets", "generate design", or "code video components", or wants to resume a video. Manages workflow state tracking and parallel scene generation.
Records and assembles documentation videos for web apps using Playwright browser automation, TTS narration, and FFmpeg. Generates a React docs site with embedded videos. Use when asked to document an app, record user flows, create tutorial videos, walkthroughs, onboarding videos, step-by-step guides, how-to videos, "make docs", "document my app", "show how to use", or "create a video guide".
Advanced video analysis and selection skill with AI-powered automatic scoring. Integrates Walter Murch's rules and dynamic weighting for professional-grade curation. Supports Bilibili, YouTube, Douyin (抖音), and Xiaohongshu (小红书). Use this skill whenever the user wants to analyze videos, score or rate scenes, extract best shots/highlights, evaluate video quality, curate clips, do competitor video analysis, or mentions terms like "视频分析", "镜头筛选", "场景评分", "视频拆解", "精选片段", "视频质量", "镜头打分", "素材挑选" — even if they don't explicitly ask for "expert analysis".
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.