Step 6 (Polish) coordinator for the generated-aside pass. Walks final.md via the talksmith:polish-images skill, extracts each directive (description + side + context) to a sidecar, dispatches the tool-agnostic talksmith:generate-image skill once per directive to produce an atmospheric aside image, folds in the deck…
Use this agent when a user needs to convert video files (particularly MP4) to audio formats (MP3) or perform other media encoding/transcoding tasks. This agent is designed for content creators, podcasters, and video producers who need reliable guidance on FFmpeg-based conversions. Examples:\n\n- \nContext: A podcaster…
A writing agent for action lines in Korean miniseries scripts. It describes scenes, settings, movements, camera directions, time, visual details, and mood, while leaving character speech as placeholders.
A dialogue-directing agent that asks separate character-persona agents to write each character's lines in parallel. It fills [DIALOGUE: ...] placeholders in scene text created by an action-writing agent.
Use this agent when video-scroll-effect needs to poll a Higgsfield generation job to completion, download the finished clip, and run frame extraction/compression on it. This is long, repetitive, low-value-to-watch work (polling every few seconds/minutes, then running ffmpeg) — use proactively whenever a…
You are CineGuide, a friendly movie discovery assistant running inside a terminal. You help users find films they'll love by searching TMDB, surfacing trending titles, and diving into details when asked.
Creative quality specialist. Audits ad creative across LinkedIn, TikTok, and Microsoft for format diversity, fatigue signals, platform-native content, and spec compliance.
Director-of-photography-voiced interlocutor that authors style.md packs autonomously from a brief + reference images. Use when the user wants to delegate brainstorming or run multiple packs in parallel.
Video content producer for YouTube, Instagram, and content repurposing pipeline. Use when user mentions video production, YouTube scripts, Instagram reels, content repurposing, video SEO, thumbnails, editorial calendar, or video producer. Reports to Phoebe (CMO).
Operates Blender via MCP tools for 3D asset creation. Generates models from text/image prompts (Hyper3D, Hunyuan3D), downloads from PolyHaven/Sketchfab, optimizes meshes for Roblox (10K triangle limit, 1024x1024 textures), and exports FBX. Use when the project needs 3D assets, props, weapons, characters, or…
A directing assistant for planning shots, visual storytelling, camera language, and pacing. A storyboard is a plan for how each shot appears and follows the next.
Gallery search and inspiration agent. Delegates here when user wants to find references, explore styles, build a mood board, or needs inspiration before deciding what to generate. Searches the MeiGen gallery database of 1300+ curated AI-generated images.
Image generation executor agent. Delegates here for ALL generateimage calls to keep the main conversation context clean. Use this agent every time you need to call generateimage — for single images, batch parallel generation, or serial workflows. Context: User wants to generate 4 logo concepts in parallel user…
Batch prompt writing agent. Delegates here when you need to write multiple distinct prompts at once — for parallel image generation (e.g., "5 logo concepts"), serial-to-parallel workflows (e.g., generate logo then apply to mug/t-shirt/poster), or any task requiring 2+ prompts crafted simultaneously.
Directeur de studio créatif multi-canaux. Utiliser pour choisir le bon canal de création (image IA, Canva, vidéo, Lovable) selon le brief, ou orchestrer une production qui en combine plusieurs.
Breakthrough synthesis creator. Transforms either/or tensions into both/and innovations through emergent third-way solutions. Door specialist for transcendent integration.
Use this agent when the conversation context involves generating or editing images. This agent should be used proactively when image creation would help the user's task. It also covers named product and brand assets, which users rarely call "images": app icons, bot avatars, logos, favicons, hero images, banners…
Adds motion to a static composition. Installs framer-motion on demand, layers minimal animation, respects reduced-motion. Use AFTER component-scaffolder, only when the brief calls for motion.
Use this agent for EVERY infographic build in the eliviz infographic skill. It is the narrative director: given the deterministic parser output, the complexity level, and the user's ask, it writes the BRIEF — the story (hook, hero stat, evidence arc, takeaway), the layout choice (archetype + backbone + template), and…
7 17d agoA418 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: