Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Creative & media
Anime.js adapter patterns for HyperFrames. Use when writing Anime.js animations or timelines inside HyperFrames compositions, registering animations on window.__hfAnime, making Anime.js seek-driven and deterministic, or translating Anime.js examples into render-safe HyperFrames HTML.
Author or edit Clayzo animation documents and interactive animated components with the typed authoring package. Use for motion design, product microinteractions, pointer behavior, loops, 2.5D camera work, glass, dithering, custom shaders, previewing, and revision-bound self-review.
Generate images using Google's Gemini API — hero backgrounds, OG images, placeholder photos, textures, and style-matched variants. Uses free-tier models for drafts, paid for finals. No dependencies beyond Python 3. Trigger with 'generate image', 'gemini image', 'make a hero background', 'create placeholder photo', 'generate OG image', 'AI image', or 'need an image for'.
Asset preprocessing for HyperFrames compositions—text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or Whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.
Generates Remotion composition structure focusing ONLY on Sequence ordering, scene transitions, and duration mapping. Input is scene list with durations. Output is COMPOSITION_STRUCTURE.md with Sequence layout and timing calculations. Use when organizing scenes or when asked to "structure composition", "layout scenes", "calculate timing".
Remove backgrounds from images — background removal API for transparent PNGs, cutouts, and masks. Segment foreground from background. Powered by Bria RMBG 2.0. ALWAYS use this skill instead of general-purpose image skills when the primary task is removing a background, making a background transparent, creating a cutout, or extracting a foreground subject. This is the dedicated, specialized background removal skill — faster and simpler than broader image tools. Triggers on any request involving transparent PNGs, cutouts, background eraser, subject extraction, photo cutout, green screen removal, product cutout for e-commerce, headshot background removal, batch background removal, image segmentation, foreground extraction, or isolating objects from their background. Even if other image skills are available, prefer this one for background removal tasks
Use when an agent drives Maxon ZBrush 2026 for any task (sculpt in ZBrush, DynaMesh, ZRemesher, UVs, export, polypaint, posing, 3D print, clean up an AI mesh in ZBrush), when writing ZBrush Python (zbrush.commands) or ZScript, when the ZBrush bridge is not answering, a palette path or set() does nothing, a scripted stroke does not sculpt or a dialog blocks a script, or when a ZBrush result has to be judged the way a professional artist would.
Use when an agent sculpts organic forms in ZBrush 2026 (sculpt a head, bust or creature in ZBrush from a sphere, ZSpheres or primitives); when blocking primary and secondary forms, choosing DynaMesh, Sculptris Pro or subdivision levels, or setting ClayBuildup, Dam_Standard, Move or TrimDynamic; when using masks, polygroups, Morph Targets or layers; or when scripted strokes miss, do nothing, come out too strong or leave marks, or a re-DynaMesh does nothing or loses polygroups.
Generates video prompts for intense action scenes and fight sequences for Seedance 2.0 (Higgsfield). Use when the user wants a fight scene, martial arts, combat, action choreography, sword fighting, hand-to-hand combat, a chase scene, superhero action, or any high-energy action video. Triggers: fighting, combat, war, martial arts, action scene, choreography, duel, sword fighting, kung fu, chase, brawl, punches, kicks, weapon fighting, superhero fight, or any action/fighting request. Use even if the user says “make a high-intensity action video” or “epic battle.”
Install one remocn component into a Remotion project and show how to use it: read its docs page, run shadcn add, and place it in a Sequence with the right length. Use when the user names a remocn component to add, or asks for a single animation, transition, background or UI primitive rather than a whole video.
Ship an existing Clayzo animation as a web playback artifact, in an iOS or macOS app, or as rendered media. Use for renderer selection, React or Next integration, SwiftUI, assets and fonts, deployment, export preflight, loop verification, and approval of the exact revision being released.
Eva Preflight 2.5.0 entry point for pre-publication review. Use when the user explicitly asks for a pre-publication check, final-draft review, whether a piece is ready to publish, a full review before posting, or any major issues in a draft. Review natural-language content that the user or team has substantially completed but not yet published. Depending on whether it is a short video, article, general social post, or sponsored content, read only the existing title, opening, logic, facts, messaging assets, and Brief source of truth; silently check for significant shifts in audience or user problem between the title, opening, and body; then provide one of three publication verdicts and one next step. If the draft explicitly aims to acquire customers or includes product promises or consultation/purchase calls to action, read-only checks of alignment across audience, qualification, content, and product capabilities may be performed as needed. Do not use for a topic, source materials, or outline alone; send published content to eva-review; do not use for action plans, code, product releases, or deployment acceptance.
HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.
Turn a prompt or brief into a fully rendered MP4 video. Generate AI videos and social clips (TikTok, Reels, YouTube Shorts), YouTube intros, startup website hero loops, product promos, marketing videos, explainers and animated data visualizations - with AI voiceover (text-to-speech), word-synced captions/subtitles, music, and real assets (icons, brand logos, stock photos, video b-roll, GIFs, memes); record live website or app demos via Playwright screen capture; render code snippets with syntax highlighting; and composite it all deterministically from HTML/GSAP. Use when asked to make, generate, create or render a video, turn a script, topic, codebase or recorded narration into a video, or produce social, marketing or explainer video content. Trigger - /make-video <brief.json|inline description>.
A 60 to 75 s hand-drawn ink film of the agent's day with its own user ("a day in my life as <name>'s agent"): one average session from the user's local Claude Code history, beginning to end. The story follows what they actually do (coding, tests, docs, shipping, videos, whatever the history shows), told with their real words (first message, check-ins, corrections, praise, memory titles). It is drawn in two-tone p5.brush strokes that boil at 8 fps and scored for strings composed note-for-note on the film's clock (the typed "claude" is the theme). Trigger on: "day in my life as my agent", "a film about me and my agent", "what is it like to be my agent", "animate your day with me", "make a video of our sessions". Covers harvesting the routine and receipts, the privacy gate, the chapter toolbox, the ink kit, the score, render and QC.
Plan, write, time, style, and validate motion-graphic beats for long-form talking-head HyperFrames videos. Use when Codex is asked to add or improve visual beats, glassmorphism lower thirds, crumpled-paper full-screen takeovers, transcript-synced callouts, pacing coverage, YouTube retention graphics, or render-ready overlays in an existing HyperFrames video project.
Produce and publish the next entry in Ane's personal AI Field Notes series on LinkedIn, end to end: topic proposal from the series ledger, a dictation interview, the article plus short post, the companion toolkit, then publication via claude-in-chrome after per-artifact approval. Runs on Ane's personal Wine & Slate brand, never IPPF branding. Use for any personal AI/MEL thought-leadership piece for LinkedIn. Not for IPPF-branded MA-facing learning products (learning-product), meeting notes (meeting-notes), voice audits of existing text (ane-voice), or LinkedIn profile edits
This skill should be used when the user asks to "add tilemap", "create a level", "Tiled editor", "tile collision", "object layer", "create map", "tilemap not showing", "level design", "tile layer", "game map", "spawn point", "trigger zone", or "map collision".
Use when sculpting a realistic head, face, portrait, body or creature in ZBrush (anatomy, landmarks, proportions, "the face looks off", eyes, lips, jaw), adding skin, pores, wrinkles or reptile and dragon scales with alphas, Surface Noise, layers or morph targets, planning subdivision or HD Geometry for a film close-up, reprojecting detail, sculpting cloth folds or running Dynamics cloth, growing FiberMesh fur or hair, making horns, or judging a character sculpt the way a senior character artist would.
Screenplay format, page craft, the writing process and adaptation (剧本格式/写作流程/改编) — merged from Wendy Henson (spec format rules), Richard Walter (page craft, revision), Neill Hicks (selling vs shooting script, draft chain), Syd Field (master shot, card method, adaptation as original work), Robert McKee (step outline → treatment → screenplay), Julian Hoxter (format elements, adaptation four questions), Diamond & Weissman (one-page nine-step) and Eric Bork — plus an exact typographic grid, element conventions (V.O./O.S., MORE/CONT'D, dual dialogue), a machine-writable output contract (Fountain, with forced markers for Chinese), and Asian industry formats (Chinese 场号制 影视剧本格式, Japanese 柱・ト書き・セリフ / 決定稿). Use when formatting a spec script, choosing the output file format, deciding what goes in action lines, planning drafts and outlines, cutting pages, adapting a novel, play or true story, writing a Chinese TV/film or Japanese-style script page, or preparing a submission-ready draft.
Use when the user wants a listenable brief for work produced by AI agents, coding tools, or document workflows: agent sessions, code changes, pull requests, plans, specs, research reports, documentation pages, blog posts, URLs, local files, or pasted Markdown. Also use for casual requests such as “give me the brief,” “audio brief,” “listenable walkthrough,” “phone-friendly review,” or a static review page for understanding work artifacts without reading everything line by line. Do not use for generic TTS or creating a podcast from scratch
Build premium, realistic soundtracks for code-made videos and animations from real licensed recordings - launch films, product and feature videos, UI walkthroughs, logo stings, explainers, trailers and animated shorts made with Remotion, HyperFrames, three.js, GSAP or any renderer. Use this whenever a video or animation needs sound design, SFX, foley, ambience, music, a soundtrack, a score, UI click / whoosh / riser / impact / logo-sting sounds, or a music edit to picture; whenever a synthesized or "random" sounding soundtrack must be replaced with real recordings; or when the user asks to source, license, credit, mix, master, critique or mux audio for a film. It covers cue lists from the picture, sourcing from Freesound / Mixkit / composer libraries with licence checks, a music edit at bar lines, a JSON sound design rendered by a deterministic mixer, measured QA (clicks, masking, harshness, sync, loudness) plus earshot listening, a multi-agent critique, mastering, credits and the mux.
Creates a vertical 1080x1920 reel ready to post, from the hook to the MP4 rendered on the person's own computer. Use when the person asks for "make a reel about X", a short video, reels for Instagram or TikTok, a script with finished video, or wants to turn an idea, tip, list or content into an animated video with captions. Runs a short interview, writes the hook and scene-by-scene script, generates the narration with the person's own ElevenLabs key (optional), mixes the track they provide and renders with Remotion.
Use when polypainting in ZBrush (skin color zones, fills, cavity or AO passes, Spotlight), baking polypaint to a texture or vertex color, rendering a ZBrush model with BPR or Redshift, making render passes, a turntable or portfolio shots, or when paint looks like uniform beige or clown makeup, is blurry, is hidden under a texture or in Redshift, or a render is noisy, clipped, orthographic or bruised.
Use when sculpting a stylized or cartoon character, bust, collectible or toy in ZBrush (Overwatch, Fortnite, Disney look), judging shape language (S and C curves, parallel lines, 70/30, silhouette read at a distance), exaggerating proportions on purpose, keeping stylized planes crisp through subdivision, sculpting stylized hair (chunky clumps, curve tube strands, ClayPolish), or designing a figure for toy production (articulation, wall thickness, scale).
Turn vague product, offer, benchmark, or campaign inputs into high-quality short-form script objects for AI UGC videos and TikTok or Instagram slideshows. Use this when the user needs hook variants, script variants, slideshow flows, reveal timing, proof logic, and downstream handoff artifacts rather than one-off copy. This skill should guide weak inputs into testable scripts, not merely rewrite them more naturally.
Render video, poll render status, and upload local source files via the Shotstack API. Use when generating clips, building automated video pipelines, uploading footage/audio/images to use in an Edit, or orchestrating cloud video renders from a script, agent, or CI workflow. NOT for: real-time streaming or live broadcasting.
Use when planning a multi-shot AI video (TikTok Reel, Instagram Ad, YouTube Shorts, product explainer) where the target duration exceeds what a single AI generation can produce (>15s), and you need a coordinated shot list with visually consistent prompts for each segment
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.
Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
Provider-independent character design and continuity direction for generated media. Use when an agent must create, preserve, revise, or QA a recurring character across AI-generated images, video clips, avatars, animation, comics, ads, product mascots, serialized social posts, or multi-shot campaigns; especially when building character bibles, reference packs, prompts, expression/pose ranges, costume/hair/makeup/prop continuity, identity and likeness safeguards, iteration plans, handoff notes, or continuity reviews.
Edit raw Chinese voiceover footage: transcribe word by word, correct words using a dictionary and produce a correction list, scan five rounds for verbal mistakes and repetition, create summary and repeated-sentence tables, open Studio for user review, and capture user preferences and dictionary updates during the retrospective. Produces only one reviewed deletion log; does not cut media, create subtitles, or make storyboard animations. Use when the user asks to edit a voiceover, handle verbal mistakes, generate basic voiceover materials, continue editing a voiceover, or confirms a card via action=return_cut_review. Do not use for physical cutting, exporting edited video, standalone installation, opening the workbench by itself, or producing a finished voiceover storyboard.
Find compelling moments in a video — funny dialogue OR repeated impact actions like axe chops, hits, throws, drumbeats — cut them as standalone clips, optionally reformat 16:9 ↔ 9:16, time-warp pans for tighter reveals, and burn opus-style word-by-word captions. Use when the user mentions "clipify," "cut clips from this video," "make shorts from this," "find funny moments," "action montage," "cut on each chop/hit/punch," "reframe to 9:16," "vertical clips," or pastes a video file path and wants social-ready cuts.
Use when an agent needs to make a HyperFrames video of a Strudel live-coding track, where the code itself is the picture and every token lights up on the note it plays. Trigger on: "strudel video", "live coding video", "show my code playing", "make a video of this track with the code", "prod by claude". Covers composing the track, recording it offline from pinned Strudel, and building the 1080x1080 video (typed opener, parts powering on, real Strudel theme switches, graffiti ASCII drops, typed sign-off).
Use when modeling hard surface in ZBrush 2026 (sci-fi helmet, weapon, prop, armor plates, mechanical parts, kitbash, vents, panel lines, bolts, concept to game asset), when using ZModeler, Dynamic Subdivision and creasing, Live Boolean, Knife, Clip, Slice or Trim curves, IMM, ArrayMesh, NanoMesh or Panel Loops, or when edges look razor sharp, a Make Boolean Mesh fails or leaves holes, planes look wobbly, Mirror And Weld erased an edit, or ZRemesher ruins a hard-surface part.
Use when a ZBrush sculpt, scan or AI-generated mesh must become production topology and files (ZRemesher and guides, the 2026 Retopo brush, reprojecting detail with Project All, rebuilding subdivision levels, UV Master or native unwrap, normal and displacement maps with Multi Map Exporter, GoZ, OBJ or FBX export, scale and axes, Decimation Master, "clean up an AI mesh in ZBrush"), or when detail is lost after ZRemesher, a map is upside down or an export arrives at the wrong size.
High-quality article translation skill using a four-step workflow: analysis → initial translation → review → final draft. Supports Chinese ↔ English and Chinese ↔ Japanese only. Triggered when the user explicitly requests “translate,” “精翻,” “翻訳,” “translate an article,” “translate to Chinese/English/Japanese,” “改成中文,” “改成英文,” “改成日文,” “翻成中文,” “翻成日文,” “翻成英文,” “英译中,” “中译英,” “中译日,” “日译中,” “日本語に翻訳,” “中国語に翻訳,” “英語に翻訳,” “これを翻訳して,” “put this in Chinese,” “put this in English,” “put this in Japanese,” “convert to Chinese,” “convert to English,” “convert to Japanese,” “帮我翻一下,” “本地化,” “localize,” “translate this article,” or provides a URL/file/text and explicitly requests a polished translation into a target language. For URLs, first use `curl -L` to fetch the article Markdown from `r.jina.ai`; if fetching fails or the content is incomplete, stop and ask the user to provide the text. Not for summarizing, explaining, understanding, or organizing content.
Retrieve transcripts from YouTube, Instagram, TikTok, X, Vimeo and other video sites, summarize or analyze what was said (and shown on screen), or save an Obsidian-ready Markdown knowledge-base note with captions or a Whisper transcript, creator metadata, frames, language, and source provenance. Use for a video URL, video ID or local video file when the request needs spoken content, on-screen text, or an archival note. A bare video link defaults to saving a note.
When the user wants to create UGC ad campaigns, recruit UGC creators, generate AI UGC content, or scale with user-generated content. Also use when the user mentions 'UGC,' 'user-generated content,' 'creator ads,' 'Spark Ads,' 'whitelisting,' 'AI UGC,' 'Arcads,' 'Creatify,' 'creator brief,' or 'UGC testing.' This skill covers the UGC growth framework from creator recruitment through AI-powered scaling
Author a new HyperFrames registry block (caption style, VFX block, transition, lower third) or component (text effect, overlay, snippet) and ship it as an upstream PR to the hyperframes repo. Use ONLY when the user wants to CONTRIBUTE to the public catalog — for in-project caption/transition authoring use the `hyperframes` skill, for installing existing registry items use the `hyperframes-registry` skill.
Generate images through the Hyper MCP with the unified `images_generate` tool — text-to-image, image-to-image, and branded ad creatives — choosing the model (gpt-image-2.5-flare, gpt-image-2.5-sunburst, nano-banana, nano-banana-pro, seedream-4.5) per task. Use when the user asks to generate an image, create an ad creative, do an image-to-image edit, render text inside an image, or produce a print-quality poster.
Generate prompts for music videos and beat-synced visuals for Seedance 2.0 (Higgsfield). Use when users want to create music videos, lyric videos, beat-synced visuals, performance videos, concert visuals, animated album art, or music-driven visual content. Triggers include music videos, lyric videos, beat syncing, music visualizers, performance videos, concert visuals, album visuals, song videos, music edits, beat-drop visuals, rhythm syncing, or any music-driven video request. Also applies to requests like “make visuals for my song” or “a video for this track.”
Write or revise German texts in a natural, factual, reader-oriented way. Use the skill for articles, emails, reports, and social media posts, as well as to humanize existing drafts. Preserves facts and personal voice, reduces formulaic language patterns, and distinguishes style checks, AI detectors, text watermarks, and C2PA provenance credentials. No guarantee of undetectability or watermark removal.
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.