Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Create a complete YouTube video plan with title options, thumbnail concepts, hooks, and content outline. Use when planning a new video, creating title/thumbnail/hook options, or when the user says 'plan a video', 'video plan', 'plan my next YouTube video', or 'I want to make a video about'.
Control Unreal Engine 5 editor via HTTP commands. Spawn/delete/transform actors, manage blueprints, materials, animation blueprints, and any UObject property via reflection. Use when the user asks to create, modify, or query anything in UE5 editor, or mentions UE5, Unreal, actors, blueprints, levels, materials, animation, input, or characters.
World-class video production expertise combining the storytelling craft of documentary filmmakers, the efficiency of commercial production houses, and the engagement science of YouTube creators. Video production is where ideas become moving images that move people. Great video content doesn't just inform—it immerses, persuades, and converts. The best video producers understand that pre-production is where success is determined, that every shot must earn its place, that pacing controls attention, and that the story always comes first—before the technology, before the effects, before the polish. Use when "video, video production, film, shoot, footage, editing, product video, testimonial, talking head, brand video, social video, youtube, video content, b-roll, color grade, video, production, editing, filming, content, youtube, social, brand" mentioned.
Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops. Defaults to Seedance 2 but works the same with Kling 3 / 4, Veo 3 or Sora 2. Output is one MP4 saved to the project folder. When the workspace also ships an interactive-video / hyperframes skill, prefer composing several short shots into a single timeline rather than one long monolithic clip.
Use when someone outside the marketing team has to film — a customer for UGC, an employee for EGC, or a paid creator or KOC — and needs a brief: talking points, shooting guide, do and do-not list, usage rights, deliverables, and batch management. Trigger on 'UGC brief', 'creator brief', 'KOC brief', 'brief for employee videos', 'what do I tell the influencer', 'we hired a creator to film'. Also use when the user asks how to get customers to make videos for the brand. Not for — a script the team writes and shoots itself, see `04-script-video-global`; edit direction for footage already shot, see `44-video-editor-brief-global`; posting inside communities, see `38-community-seeding-global`.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Use when wiring `AnimationPlayer` + `AnimationGraphHandle`, building an `AnimationGraph` from glTF clips, blending state-driven animations with `AnimationTransitions::play`, isolating body parts with `AnimationMask`, firing gameplay sync via `#[derive(AnimationEvent)]` + `On<E>` observers, tweening with `AnimatableCurve` / `EaseFunction` / `CubicSegment::new_bezier_easing`, or applying the 12 Basic Principles of Animation to 3D characters in Bevy 0.19.
Benchmark Blender modeling agents, skills, prompts, scripts, or MCP tools with paired isolated runs. Use for baseline-versus-plugin comparisons, regression suites, skill forward-testing, MCP usefulness evaluation, score calibration, or claims that a Blender workflow improves mesh, visual, structural, animation, cost, or completion quality.
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.
Use when a user is installing DaVinci Resolve for the first time, switching machines, configuring a media drive for video editing, or asking about backup/proxy settings. Triggering symptoms include phrases like "just installed Resolve", "set up DaVinci Resolve", "drop frames during playback", "where should my media live", "how do I configure backups", or any DaVinci Resolve installation/preferences question.
Complete fal.ai image-to-video system. PROACTIVELY activate for: (1) Kling 2.5/2.6 Pro image animation, (2) MiniMax Hailuo with prompt optimizer, (3) LTX image-to-video, (4) Runway Gen-3 Turbo, (5) Luma Dream Machine with loop, (6) Stable Video Diffusion, (7) Motion description prompts, (8) Portrait/product animation workflows. Provides: Model endpoints, motion keywords, animation techniques, workflow examples. Ensures natural image animation with proper motion description.
Develop differentiated ideas for products, research, campaigns, names, or process changes. Use when the user asks to brainstorm, explore alternatives, escape generic concepts, or test a promising direction. Compare mechanisms and practical constraints; do not claim originality without an appropriately scoped search. Do not activate for proofreading, factual lookup, or implementing an exact spec.
Joel's writing voice and style guide for joelclaw.com content. Use when writing, editing, or reviewing any blog post, essay, book chapter, or prose content for joelclaw.com. Also use when asked to 'write like Joel,' 'match Joel's voice,' 'draft a post,' 'write content for the blog,' or 'review this for voice.' This skill captures Joel's specific writing patterns derived from ~90,000 words of published content spanning 2012–2026. Cross-reference with copy-editing and copywriting skills for marketing-specific copy.
Expert guide to end-to-end Python video pipelines combining FFmpeg, OpenCV, PyAV, ffmpegcv, Decord, VidGear, and Modal.com for scalable GPU-accelerated workflows. PROACTIVELY activate for: (1) FFmpeg+OpenCV in same pipeline (decode, process, re-encode); (2) color-format mismatches (BGR vs RGB across OpenCV, PIL, PyAV, FFmpeg); (3) frame dim ordering (HWC vs CHW) between OpenCV and ML frameworks; (4) audio stream loss in filter chains; (5) memory mgmt for long/large videos (streaming vs in-memory); (6) choosing ffmpegcv/Decord/VidGear/PyAV for performance; (7) GPU decode/encode on Modal.com; (8) parallel + chunk-based processing on Modal; (9) transcoding pipelines on serverless; (10) HLS generation on Modal; (11) upload -> process -> transcode -> HLS workflows; (12) batch sizing for GPU memory, pixel formats, large-video streaming. Provides: library selection matrix, integration recipes, Modal.com deployment examples, GPU pipeline tuning, production-ready workflow examples.
Turn a teardown (or a rough idea) into a finished, ready-to-shoot reel. Claude writes the beat-by-beat script in your voice and lays out the on-screen text, the scene for each beat, the pacing cues, and the caption — your words on a proven structure. Use when the user says "build the reel", "make the reel", "write the full reel", "turn this into a reel", "script and storyboard this", or hands over a breakdown/idea and wants the whole thing assembled.
Turn an idea or hook into a full 30-45 second reel script — hook, value beats, payoff, and CTA, with on-screen text. Use when the user says "reel script", "video script", "script this", "write a reel", "short-form script", or "turn this idea into a video".
This skill should be used to generate realistic, persona-consistent synthetic coaching and therapy session transcripts for evals, demos, and training data. It produces fictional but believable coach/client (or therapist/client) dialogue grounded in a chosen modality (ICF/GROW coaching, CBT, IFS parts work, ACT/motivational interviewing) and exports to Fathom/Granola transcript style, plain dialogue, structured JSON, or Obsidian markdown. Triggers on requests like "generate a synthetic coaching session", "make fake therapy transcripts for evals", "create demo session transcripts", "synthetic CBT dialogue", "persona-consistent coaching transcript", "test data for my session summarizer", or "mock coaching call".
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn a topic / product / person into a punchy narrated collage video — even if they don't say the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage ad workflows, or when the user asks for a motion collage or a scrapbook-style tribute. Triggers: "vox video", "collage video", "motion collage", "paper collage explainer", "make a collage ad", "turn this topic into a collage video".
Xiaohongshu note material creation skill. Use this skill when the user needs to create Xiaohongshu note materials. The skill covers: writing Xiaohongshu note content (title + body) based on the user's needs and provided materials, generating image cards (cover + body cards), and publishing Xiaohongshu notes.
Use this skill whenever the user wants detailed English prompts for AI image tools (NanoBanana / Gemini / DALL-E / Midjourney) to produce top-conference-quality academic figures — including framework diagrams, network architecture diagrams, pipeline flowcharts, module detail diagrams, comparison/ablation figures, and data pattern grids — especially when the user says "论文配图提示词", "生成论文配图", "学术论文生图", "架构图提示词", "框架图提示词", "顶会风格配图", "CVPR 风格图", "NeurIPS 风格图", "paper figure prompt", "academic diagram prompt", or provides a LaTeX/PDF/Word paper and asks for figure prompts. If the user has not specified a color scheme, present the 8 preset palette options and color tool links before generating any prompt.
Write marketing copy and App Store / Google Play listings (ASO keywords, titles, subtitles, short+long descriptions, feature bullets, release notes), plus screenshot caption sets and text-to-image prompt templates for generating store screenshot backgrounds/promo visuals. Use when asked to: write/refresh app marketing copy, craft app store metadata, brainstorm taglines/value props, produce ad/landing/email copy, or generate prompts for screenshot/creative generation.
Given a topic or workflow from the user, automatically generates a complete short-video piece (script, storyboard, digital-human voice-over, and mixed AI footage); calls the Chanjing Open API and sub-skill scripts in the same repository.
This skill should be used when the user asks to "edit an image", "modify a photo", "inpaint", "outpaint", "extend an image", "replace object in image", "add element to image", "resize image for social media", "crop image", "adapt image for Twitter", "convert image to OG format", or needs AI-powered image editing with masks.
FFmpeg CLI reference for video and audio processing, format conversion, filtering, and media automation. Use when converting video formats, resizing or cropping video, trimming by time, replacing or extracting audio, mixing audio tracks, overlaying text or images, burning subtitles, creating GIFs, generating thumbnails, building slideshows, changing playback speed, encoding with H264/H265/VP9, setting CRF/bitrate, using GPU acceleration, creating storyboards, or running ffprobe. Covers filter_complex, stream selectors, -map, -c copy, seeking, scale, pad, crop, concat, drawtext, zoompan, xfade. Do NOT use for image-only processing (use ImageMagick), live-streaming server setup (use OBS/nginx-rtmp), or NLE-style timeline editing (use a video editor).
Detects and eliminates 40 AI writing tells across vocabulary, structure, formatting, content inflation, and communication artifacts. Includes personality injection, 6-dimension scoring, and a self-audit loop. Use when editing or reviewing any text to make it sound unmistakably human.
Use for lateral thinking, or when ideas feel stuck or incremental: "we've tried everything", "need a surprising angle", "break the pattern", "give me a wild idea that could work". Uses provocations and reframes. Skip for rule lookups or strict logical proofs.
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.
Adapt a single master creator brief into platform-specific versions for TikTok, Instagram Reels, and YouTube Shorts with correct specs, safe zones, and platform-native guidance. This skill should be used when converting a brief for multiple platforms, adapting a campaign brief from TikTok to Reels, creating platform-specific content briefs from a master brief, adjusting video specs for different short-form platforms, building TikTok and Reels and Shorts versions of one brief, formatting creator deliverables by platform, splitting a campaign brief into platform versions, or generating platform-adapted briefs for a multi-platform creator campaign. For writing the master brief itself, see content-brief-builder. For generating content concepts before briefing, see creator-content-concept-generator. For checking submitted content against a brief, see content-to-brief-compliance-checker.
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.
Write and revise human-facing prose in a plain, professional register, stripping the tells that mark text as AI-generated. Works top down. First restructure the document (reorder, merge, split, delete, or replace sections and generated scaffold), then rebuild paragraphs and sentences with ASD-STE100 Simplified Technical English and the mechanics adopted from the Microsoft Writing Style Guide, then kill word-level tells and check with a bundled linter. Use when writing or editing a README, blog post, doc, PR or commit message, email, release note, changelog, error message, runbook, or any copy a person will read. Also use when asked to make text sound less like AI, remove AI slop, restructure or de-bloat a doc, cut the marketing voice, write plain or controlled technical English, fix over-structuring or list-itis, make wording inclusive or accessible, tighten or professionalize a draft, or to review prose you just generated. Extends to comments, commits, PRs, test names, error and log strings, and formatting.
Provides natural, readable, fluent and clear writing guidelines for Chinese or English copy. Use when drafting, rewriting or polishing articles, spoken scripts, speeches, PPT copy, website and product introductions, personal bios, WeChat official account and social posts; also use when the user explicitly specifies oil-tone. Applies to style editing, not to pure research or factual and technical edits that do not involve expression.
Export all layers of a Photoshop (.psd) file as separate PNG images. Useful for extracting layer images from PSD files, generating slices for web development, or preparing layer assets for other tools. Automatically handles layer naming, skips invisible layers, and recursively exports nested layer groups.
Turn talking-head footage into a finished reel, YouTube Short, or short advertisement with curiosity-led openings, earned payoffs, story-driven cuts, transcript-synced motion graphics, moving B-roll, captions, subtle music, and synchronized sound effects. Use for short-form editing; use edit-video for long-form videos and cut-silences for pause removal alone.
Generate professional shot lists from screenplays and scripts. Use when user uploads a screenplay (.fountain, .fdx, .txt, .pdf, .docx) or describes scenes for production planning. Parses scripts to extract scenes, helps determine camera setups, shot types, framing, and movement through collaborative discussion, then generates beautifully formatted PDF shot lists for production. Triggers include requests to create shot lists, plan shots, break down scripts for filming, or organize camera coverage.
WHAT: Transforms basic image prompts into model-optimized superprompts for AI image generation. WHEN: generating images, creating AI art, enhancing image prompts, working with Flux, Flux Kontext Max, Nano Banana, Midjourney, Ideogram, Recraft, Luma, Reve, Grok, GPT Image 1.5, or Seedream 4.5. KEYWORDS: superprompt, image prompt, generate image, AI art, enhance prompt, optimize prompt, photorealistic, portrait, product, selfie, photography, image generation.
Expert texture artist specializing in PBR workflows, Substance suite, Quixel Mixer, and hand-painted techniques for games and film productionUse when "texture artist, PBR textures, Substance Painter, Substance Designer, Quixel Mixer, normal map, roughness map, metallic map, albedo texture, base color map, texture baking, bake normal, texel density, trim sheet, texture atlas, channel packing, material layering, wear and tear, edge wear, hand painted texture, stylized texture, UDIM workflow, height map vs normal, color ID map, material ID, texture seams, tiling texture, seamless texture, texture, pbr, substance-painter, substance-designer, quixel, megascans, normal-map, roughness, metallic, albedo, uv-mapping, baking, trim-sheet, material, hand-painted, stylized, photorealistic, game-art, 3d-art" mentioned.
Integrate Three.js 3D scenes into Editframe compositions via addFrameTask. Scenes are pure functions of time, fully scrubable, and renderable to MP4. Use when creating 3D animations, WebGL content in compositions, or integrating Three.js with Editframe's timeline system.
Comprehensive Three.js and React Three Fiber skill for creating 3D scenes, characters, NPCs, procedural generation, animation retargeting, and interactive experiences. Use when user asks to "create Three.js scene", "setup React Three Fiber", "add 3D character", "create NPC AI", "procedural 3D generation", "retarget animation", "setup avatar system", or "create 3D game".
Remove the AI-script tells viewers hear in a TikTok spoken script and caption: 2026 vocabulary by density, reveal bridges, staccato stacks, stacked triads, performed sincerity, written-not-spoken phrasing, \"hey guys\" filler; caps em dashes. Includes --mode audit pre-film check (hook, completion design, caption fit) and --mode profile. Not for beating AI detectors (no edit reliably does). Not for writing from scratch (use tt-hook-scripter). Keywords: humanize script, de-AI, audit before filming.
Edit arbitrary supplied video, audio, images, screen recordings, and graphics into a polished deliverable. Use for cutting and restructuring footage, multi-track compositing, picture-in-picture, transitions, captions, sound work, color and framing changes, screen demos, presenter edits, social clips, and motion graphics made with FFmpeg, HTML, React, SVG, or Remotion. Includes source inspection, timeline design, reusable media tooling, transparent overlay generation, fast review artifacts, deterministic rendering, and technical validation.
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.