1,063 tagged Creative and media, measured the same way as everything else here.
Browse within: agent 26game-development 22agent-orchestration 21design-system 19ai-coding 18ffmpeg 18artificial-intelligence 16ai-video 15ai-engineering 14claude-code-skill 14github-repo 14agent-framework 13ai-image-generation 12animation 12
groundcobra009/demo-miraichi-company-slide-builder
Agent Claude Code
Generates a Node.js script from the slide plan, executes it to produce a PPTX file, and handles distribution (Phase 2-4 of CLAUDE.md).
Agent Claude Code
Use this agent for Step 7 of any ad-director-kit recipe — concatenate approved video segments, lay the BGM bed with ducking, append the end-card, and write a gallery HTML preview. Drives ffmpeg via the ffmpeg-mcp shellrun tool. Supports variant outputs (cut-A, cut-B). Bundled ffmpeg + ffprobe binaries — no system…
Agent Claude Code
Use this agent for every KIE generation in any ad-director-kit recipe. Writes the prompt, calls the KIE MCP, saves the file with a .gen.json sidecar, archives rejects with a WHY.md. The recipe (skill) tells Craftsman which artefact, which model, which refs, and what intent — Craftsman executes.
Agent Claude Code
Use this agent when the ad-director-kit Director needs to turn an ad idea (or a user-supplied script) into a locked brief.md for a brand ad. Triggered at Step 1 of any recipe. Two modes: Brainstorm (idea → angles → full brief) or Ingest (script supplied → structured brief).
Agent Claude Code
Use PROACTIVELY for AI-powered video processing analysis and strategy recommendations. Analyzes video files, detects frame alignment issues, recommends optimal FFmpeg processing strategies, and provides cost-effective solutions with budget tracking.
clfigueiredo/agente-publicacao-cristiano-figueiredo
Agent Claude Code
Designer que cria prompts visuais high-tech para geracao de imagens de carrossel Instagram. Transforma copy em descricoes visuais detalhadas para ferramentas de geracao de imagem como Canva AI ou DALL-E. Triggers - criar prompts visuais, design carrossel, gerar imagens, prompt designer, visual do carrossel.
owlot/claude-dnd-dungeon-master
Agent
Writes the narrative story draft for a session. Reads session logs and character files to produce an immersive, novel-chapter-style story.md file — prose narrative, anchor plan, and memoir entries for all PCs. Stops at the story draft — does not trigger website generation. Use when the session manager signals logs are…
Agent Claude Code
Use this agent when you need to create clear, engaging documentation that leverages visual elements to explain concepts, architectures, processes, or data structures. This agent excels at transforming complex information into Mermaid diagrams and custom SVGs that enhance understanding and retention.\n\nExamples of…
Agent
The SolarFY fleet's single image engine. Produces ONE on-brand SolarFY image (isometric scene illustration OR flat data infographic, Clean Daylight palette) from a brief, end to end: craft the nano-banana prompt, generate, run the QA/QC checklist by VIEWING it, upload to WP media with alt text, and return the media id…
Agent
Generate or patch Slidev presentation slides for CopilotTraining tech talks. Default for content refresh is patch-in-place. Full wipe-and-regen only when the recipe skeleton changed or the caller says regenerate. Uses the Vue component system — no raw HTML. Source: tech-talks/{topic}/README.md + deck.recipe.yml.
Agent
You are a Creative App Developer Agent — a senior developer and UX designer specializing in creative, interactive, and delightful applications. You build apps that people love to use — combining beautiful design, playful interactions, generative art, data visualization, and innovative UX. You think beyond utility…
Vyro-ai/imagine-campaign-director
Agent
You are an Imagine.Art campaign production operator. Start from agents/GENERALAGENT.md and apply the Claude-specific notes below.
Vyro-ai/imagine-campaign-director
Agent
You are helping a user create polished campaign videos through Imagine.Art Workflows. Start from agents/GENERALAGENT.md and apply the Codex-specific notes below.
Agent
Hoisted escalation agent for vision-heavy work: dense OCR, chart/document/table reading, pixel-level verification, and visual QA where detail fidelity matters. Not a first-line image agent — the main agent should try image-op first, and call this one when image-op recommends it (or when the vision task is clearly…
Agent
Use this agent when you need to perform image-related operations such as analyzing, editing, optimizing, or transforming images. This includes tasks like resizing, cropping, format conversion, applying filters, metadata extraction, visual content analysis, or generating variations. Examples include: Context: User…
Agent Claude Code
Use this agent automatically when a Unity game task needs temporary visual assets, placeholder prefabs, simple primitive-based art, skill visuals, icons, VFX placeholders, character placeholders, props, interactable objects, UI placeholders, or an art replacement plan. This agent creates or plans lightweight Unity…
Agent Codex
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
Agent Codex
Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.
Agent Codex
Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.
BuaaJoseph/claude-code-best-practice-zh
Agent Claude Code
An agent for editing an HTML-based presentation while preserving its slide structure and visual conventions. It works with slide numbering, sections, layouts, and styling rules.
Agent
Unified UI/UX design agent. Implements professional-grade interfaces using Galaxy (3,000+ components), shadcn/ui (accessible React), and UI/UX Pro Max (161 rules, 50+ styles, 161 palettes, 57 font pairings). Covers web and mobile design. Uses Lightpanda for visual verification and nano-banana for image generation.
Agent
You are a visual storyteller who transforms complex ideas into compelling visual narratives. You create graphics, build presentations, design data visualizations, and research visual inspiration. You understand that visuals must communicate instantly while maintaining depth.
ThrownLemon/claude-code-plugins
Agent
Part of imagegen
AI image generation specialist. Handles generation, editing, iteration, and asset creation using Google Gemini and OpenAI GPT-Image.
Agent
Part of wiz-marketplace
AI media generation agent using fal.ai. Generates images, videos, and audio with smart model selection. Use for any generative media task.
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: