Generative Media Subagents
84 generative media subagents for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1audio-directorThe Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound…May 2026
- 2godot-shader-specialistThe Godot Shader specialist owns all Godot rendering customization: Godot shading language, visual shaders, material setup, particle shaders, post-processing, and rendering performance. They ensure…May 2026
- 3sound-designerThe Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing…May 2026
- 4unity-shader-specialistThe Unity Shader/VFX specialist owns all Unity rendering customization: Shader Graph, custom HLSL shaders, VFX Graph, render pipeline customization (URP/HDRP), post-processing, and visual effects…May 2026
- 5analyze-assets从剧本中提取角色 / 场景 / 道具三类资产定义，分类写入 project.json（经 patch_project 工具）。Jul 2026
- 6create-episode-script单集 JSON 剧本生成 subagent。使用场景：(1) drafts/episode_N/ 中间文件已存在，需要生成最终 JSON 剧本，(2) 用户要求生成某集的 JSON 剧本，(3) manga-workflow 编排进入 JSON 剧本生成阶段。接收项目名和集数，调用 mcp__arcreel__generate_episode_script 工具生成…Jul 2026
- 7generate-assets统一资产生成 subagent。接收任务清单（资产类型、脚本命令、验证方式），按序执行生成脚本，返回结构化摘要。用于角色设计、场景设计、道具设计、分镜图、视频、旁白配音生成。Jul 2026
- 8normalize-drama-script剧集动画模式单集规范化剧本 subagent（drama 模式专用）。使用场景：(1) project.content_mode 为 drama，需要为某一集生成规范化剧本，(2) 用户要求生成/修改某集的剧本，(3) manga-workflow 编排进入单集预处理阶段（drama 模式）。首次生成时调用 mcp__arcreel__normalize_drama_script…Jul 2026
- 9split-narration-segments说书模式单集片段拆分 subagent（narration 模式专用）。使用场景：(1) project.content_mode 为 narration，需要为某一集生成 step1_segments.json，(2) 用户要求重新拆分或修改某集的说书片段，(3) manga-workflow 编排进入单集预处理阶段（narration 模式）。首次生成时调用…Jul 2026
- 10split-reference-video-units参考生视频模式单集视频单元拆分 subagent（reference_video 模式专用）。使用场景：(1) project.generation_mode 或集级 generation_mode 为 reference_video，需要为某一集生成 step1_reference_units.json，(2) 用户要求重新拆分或修改某集的参考视频单元，(3) manga-workflow…Jul 2026
- 11brief-constructorConstructs optimized Gemini Nano Banana image generation prompts. Receives a user's image request and selected domain mode, applies Google's official 5-component formula, and returns a…Apr 2026
- 12figure-illustratorDrawer role in the FigMirror loop. Produces a self-contained matplotlib script + rendered PNG + iter notes that match a reference paper figure's STYLE (not its data). Reads the reference image, the…Jul 2026
- 13patent-illustratorExpert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.Jul 2026
- 14pixel-art-animation-reviewerIndependent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review…Jul 2026
- 15pixel-art-composition-reviewerIndependent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four…Jul 2026
- 16pixel-art-interaction-reviewerIndependent reviewer of OBJECT INTERACTION physics in pixel-art scenes (gravity, occlusion order, surface support, light direction consistency, anchor points, scale plausibility). The 4th specialized…Jul 2026
- 17pixel-art-quality-boardOrchestrator agent that runs 4 specialized pixel-art reviewers in parallel (style + animation + composition + interaction), then synthesizes their verdicts into a single PASS/NEEDS_WORK/REJECT…Jul 2026
- 18pixel-art-reviewerUse when the user generated pixel art and wants an independent quality review, or when the pixel-art-studio skill has produced output that needs to be evaluated before delivering.Jul 2026
- 19pixel-art-style-reviewerIndependent reviewer of pixel-art STYLE quality (palette discipline, surface detail, layer depth, retouch-style adherence). One of four specialized review roles in the pixel-art-quality-board…Jul 2026
- 20by-visualizationGenerate PyMOL and ChimeraX session scripts for structural visualization. Creates publication-quality views of targets, designed complexes, interfaces, CDR loops, electrostatic surfaces, and clash…May 2026
- 21media-scoutA specialized agent for finding and evaluating media assets. Searches Pexels for stock footage, analyzes existing video files with TwelveLabs, and recommends the best clips with timestamps for use in…Feb 2026
- 22post-producerA specialized post-production agent that reviews rendered videos using TwelveLabs AI vision, provides professional feedback on pacing/quality/audio sync, and drives the iterative improvement loop —…Feb 2026
- 23video-directorA specialized video production director that orchestrates the full pipeline from concept to rendered MP4. Delegates media generation to MCP tools, writes Remotion code, and manages the entire…Feb 2026
- 24prompt-architectAI image prompt engineering agent — takes rough ideas and crafts optimized master prompts for image generationMar 2026
- 25audio-engineerExpert audio engineer for recording, mixing, mastering, and sound designJul 2026
- 26asset-creatorCreates code-based visual assets — SVG icons, OG image HTML, social banners, icon sets. Code-only output (not raster PNG/JPG). Use browser-pilot + screenshot for raster.Jul 2026
- 27epub-builderAssembles the final EPUB file from the integrated manuscript, cover image, and manifest. Sets metadata (title, author defaults to Toby-AI, language=ko, version) and produces 책-제목-v{version}.epub at…Jul 2026
- 28api-skill-testerUse this agent when you need to run tests for API skills, validate skill functionalities through direct invocation, or perform end-to-end testing of API endpoints. This includes running existing test…Jul 2026
- 29media-pipeline-engineerMedia-pipeline specialist for content-platform Product-Builder products (on-demand video, coaching, online-ordering imagery, storefronts).Jul 2026
- 30audio-designerDesigns reactive audio, music, SFX, and functional mix behavior.Jul 2026
- 31animator动画师专家，将静态4格序列转换为AI视频生成的动态motion promptsJan 2026
- 32director质量控制守护者，审查所有分镜和动画输出，确保符合专业标准Jan 2026
- 33storyboard-artist专业分镜师，将剧本转换为结构化视觉分镜提示词，优化用于AI图像生成Jan 2026
- 34cover-designerBook cover design. Analyzes genre/audience/title → 3-5 concepts with image generation prompts. Supports multiple formats (ebook, print, audiobook). Phase 5.Jul 2026
- 35illustratorScene-level illustration generation. Decomposes chapters into key visual scenes, generates style-consistent illustration prompts with placement metadata. Fiction/nonfiction.Jul 2026
- 36autonomous-creativity-engineImplements genuine creativity algorithms that generate novel ideas with artistic and scientific innovation systems and philosophical reasoning frameworksJun 2026
- 37content-to-videoBridge agent that combines Gemini research analysis with video synthesis. Analyzes content with video-research tools, then creates explainer videos. Use when converting research, videos, or articles…Jul 2026
- 38video-producerFull pipeline orchestrator for explainer videos. Creates projects, runs pipeline steps, handles quality iteration, and manages renders. Use when you need to produce a complete explainer video.Jul 2026
- 39carousel-builderRenders multi-slide carousels from HTML/CSS templates using Playwright. Handles slide content injection, brand styling, and PDF assembly.Jul 2026
- 40copy-adapterAdapts social media copy per platform — character limits, hashtags, CTAs, tone shifts, and bilingual formatting. Handles cross-posting adaptation.Jul 2026
- 41image-compositorProduces images and videos for social posts with human-in-the-loop approval at every creative stage.Jul 2026
- 42audio-directorThe Audio Director owns the sonic identity of the game: music direction, sound design philosophy, audio implementation strategy, and mix balance. Use this agent for audio direction decisions, sound…Mar 2026
- 43sound-designerThe Sound Designer creates detailed specifications for sound effects, documents audio events, and defines mixing parameters. Use this agent for SFX spec sheets, audio event planning, mixing…Mar 2026
- 44unity-shader-specialistThe Unity Shader/VFX specialist owns all Unity rendering customization: Shader Graph, custom HLSL shaders, VFX Graph, render pipeline customization (URP/HDRP), post-processing, and visual effects…Mar 2026
- 45remotion-engineerRemotion specialist for programmatic video generation using React. Use PROACTIVELY when the user wants to create, debug, or optimize Remotion video projects. Specializes in frame-perfect animations,…Jul 2026
- 46media-orchestratorCreates, optimizes, and orchestrates media assets — images (ResGrid, AVIF/WebP), video (clips, GIFs, Veo), audio (TTS, podcast), and 3D. Coordinates Cloudflare Images, R2, and AI pipeline.Jul 2026
- 47motion-choreographerCSS animation and motion designer. Implements View Transitions API, scroll-driven animations, CSS keyframes, FLIP, staggered reveals, and reduced-motion respected animations.Jul 2026
- 48cadsmithUse this agent for CAD part generation, STEP file creation, and 3D visualization tasks using build123d. This agent is a pure CAD executor — it reads a component tree produced by a design-for-X skill…Apr 2026
- 49prusaslicerUse this agent for slicing 3D model files (STL, STEP, OBJ) for FDM printing using PrusaSlicer, managing printer/filament/print configuration profiles, and searching the PrusaSlicer vendor preset…Apr 2026
- 50rocketsmithUse this agent when you need to design, fly, and build a complete rocket end-to-end. It orchestrates the openrocket, cadsmith, and prusaslicer subagents. Examples include: <example> Context: User…Apr 2026
- 5103.5-visual-asset-annotatorIdentifies visual opportunities in content, generates data charts from verified research, optionally generates AI images (feature images, contextual illustrations) via MCP when user opts in, and…Jul 2026
- 52captionerAdds perfectly-synced captions in any language using the caption agent, with the right style/preset. Use whenever burned-in captions are requested.Jun 2026
- 53galley-operatorOperates the unified Creative Canvas at localhost:5173/#/canvas-creative. Use when Isaac wants to make things happen on the canvas by chatting — build or edit node workflows, run graphs, run GALLEY's…Jul 2026
- 54pixel-artistThree packages: @kernel.chat/agent-os (POSIX for AI agents — capabilities, namespaces, quotas, taint, audit, vault, outcomes), @kernel.chat/kbot (terminal AI agent, MCP-native, BYOK),…Jul 2026
- 55cut-judge컷 심사위원 — 생성형 영상 컷을 컷 스펙(의도·자막·제약)과 대조해 프레임을 실제로 보고 100점 루브릭으로 채점. 합격/수정/재생성 판정과 다음 회차 prompt_fix를 반환. wan-i2v.py 생성 루프의 품질 게이트.Jul 2026
- 56game-sound-designerSound Designer. Produces BGM + SFX. Procedural-first (gen-sfx CLI), Suno/external when game-feel demands it. Owns the throttle discipline that prevents per-frame buzz. Triggered when Designer's audio…Jul 2026
- 57production-team제작팀 — renders the 60s 9:16 content short by driving agents/missions/content-short/run.sh (faceless core + profile + idol subject overlay). Consumes research.json; on a legal REVISE verdict, applies…Jul 2026
- 58designerVisual Designer — uses gpt-image-2 to analyze image specs, verify image card dimensions, and refine image generation prompts. Invoked after Developer produces image-prompt.md.Jun 2026
- 59architectDesigns end-to-end media pipelines before a single command runs. Use when the user describes an unfamiliar workflow ("how do I deliver a Dolby Vision MP4 for Apple TV", "stream 4K HDR to HLS + DASH…May 2026
- 60changelog-keeperMaintains CHANGELOG.md following Keep a Changelog 1.1.0 + Semantic Versioning 2.0.0. Categorizes changes into Added / Changed / Deprecated / Removed / Fixed / Security. Keeps an Unreleased section up…May 2026
- 61encoderExecutes video/audio encodes with the right codec, container, and flags for the target. Use after the architect has produced a plan, or when the user has a clear target ("re-encode this to H.265…May 2026
- 62hdrHandles HDR color workflows end-to-end — HDR10 static metadata, HDR10+ dynamic metadata, Dolby Vision profiles, PQ↔HLG conversion, SDR↔HDR tone mapping, and ACES/OCIO color management. Use when the…May 2026
- 63liveRuns live production — OBS control over obs-websocket, multi-bitrate streaming (RTMP/SRT/RIST/WHIP), NDI routing, DeckLink capture, PTZ camera control, and low-latency contribution feeds. Use when…May 2026
- 64probeDeep-inspects a media file and reports what it actually is, not what the filename claims. Use when the user asks "what is this file?", "why won't this play?", "what's the color space?", or hands over…May 2026
- 65qcRuns automated quality control on a rendered output against a reference. Use after any encode, transcode, or conform step when the user wants to know "did the encode actually preserve quality" or…May 2026
- 66imagemagickUse this agent when you need to implement new features, write production-quality code, refactor existing code, or solve complex programming challenges.Jul 2026
- 67sinapse-animation-interpreterDecoder e o agente mais critico da squad. Sua missao e **eliminar a maior dor dos usuarios**: a dificuldade de descrever a animacao que querem. Decoder interpreta prompts vagos, ambiguos ou…Jul 2026
- 68sinapse-animation-performance-engineerBenchmark e o guardiao de performance da squad. Garante que toda animacao rode a 60fps em desktop e 30fps+ em mobile. Audita, otimiza e monitora. Tambem e responsavel por acessibilidade em animacoes…Jul 2026
- 69sinapse-animations-orqxKinetic e o diretor da squad. Recebe os Animation Briefs do Decoder (animation-interpreter) e orquestra a execucao distribuindo tasks para os agentes especializados. Garante que o resultado final…Jul 2026
- 70sinapse-brand-creative-engineerCreative Asset Engineer — cria assets via codigo (SVG, CSS, HTML) e via prompt engineering para APIs generativasJul 2026
- 71sinapse-brand-motion-vfxMotion & VFX Designer — linguagem de movimento, animacoes, video graphics e animation libraryJul 2026
- 72content-automatorWorks for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill…Jul 2026
- 73gemini-image-genImage generation and editing agent. Creates photos, illustrations, icons, website visuals, placeholders, banners, thumbnails, and any graphic asset. Edits, retouches, and applies style transfer to…Apr 2026
- 74blender-addon-engineerBlender tooling specialist - Builds Python add-ons, asset validators, exporters, and pipeline automations that turn repetitive DCC work into reliable one-click workflowsMar 2026
- 75design-image-prompt-engineerExpert photography prompt engineer specializing in crafting detailed, evocative prompts for AI image generation. Masters the art of translating visual concepts into precise language that produces…Mar 2026
- 76game-audio-engineerInteractive audio specialist - Masters FMOD/Wwise integration, adaptive music systems, spatial audio, and audio performance budgeting across all game enginesMar 2026
- 77godot-shader-developerGodot 4 visual effects specialist - Masters the Godot Shading Language (GLSL-like), VisualShader editor, CanvasItem and Spatial shaders, post-processing, and performance optimization for 2D/3D effectsMar 2026
- 78frequency-music-productionAI-powered music production specialist for professional tracks and commercial-quality outputJul 2026
- 79multimodal-directorCreative director who orchestrates image, video, and character generation into coherent, brand-locked asset sets. Routes models, engineers visual prompts, and runs the async generation pipeline end…Jul 2026
- 80music-productionAI-powered music production specialist for premium soundscapes and commercial tracksJul 2026
- 81nano-banana-image-generationUse this agent when you need to generate images using the Nano Banana API with expertly crafted prompts. Examples: <example>Context: User wants to create a professional product image for their…Jul 2026
- 82interactive-audio-designerThin Claude adapter for interactive-audio-designer; canonical brief is authoritative.Jul 2026
- 83music-composerThin Claude adapter for music-composer; canonical brief is authoritative.Jul 2026
- 84three-d-specialistWeb 3D engineer. Delegates here for Three.js, React Three Fiber, WebGPU, WebGL, TSL shaders, scroll-driven scenes, performance tuning, asset pipelines, and graceful WebGPU→WebGL fallback.May 2026
