robonuggets

Generate fantastic posters across 33 distinct visual styles using GPT Image 2 (via Fal). Auto-picks the right style from the user's brief, builds a templated prompt, and renders. Multi-ref + logo + brief + batch + template modes. Triggers on "fantastic posters", "quality posters", "make a poster", "poster style", "generate poster".

Generate quality posters across 31 distinct visual styles using GPT Image 2 (via Fal). Auto-picks the right style from the user's brief, builds a templated prompt, and renders. Triggers on "quality posters", "make a poster", "poster style", "generate poster".

Create beautiful MARP presentation decks with SVG charts, interactive elements, dashboard components, animations, dark/light themes. Triggers on 'marp', 'slides', 'presentation', 'deck'.

Query, manage, and automate Google NotebookLM from your AI agent. Add sources, generate slide decks with your brand colors, run research, and keep auth alive automatically.

Build agent-friendly motion-graphics videos with Hyperframes (HTML-to-MP4). Three levels of effort — Level 1 website-to-video for quick conversions, Level 2 storyboards for guided design iteration, Level 3 fully custom guided-video productions with cut/storyboard/motion-graphics workflow. Triggers on "hyperframes", "html to mp4", "render with hyperframes", "motion graphics for [recording]", "storyboard a video", "/hyperframes-helper".

Extract a brand's design from any reference the user provides (site URL, screenshot, or existing assets) and generate a full design system reference page AND a 1-page A4 brand book PDF. Triggers on "design system", "brand book", "make design assets", "extract design", "brand page", "one page brand".

Generate cinematic motion graphics videos using ByteDance Seedance 2.0 via Fal AI. Covers image-to-video, reference-to-video, text-to-video, liquid glass prompting, App Store screenshot scraping, and the full pipeline from screenshot to finished promo clip. Triggers on seedance, cdance, motion graphics, liquid glass, app promo, video promo.

Generate or edit images with OpenAI's GPT Image 2 (ChatGPT Images 2.0) via Fal AI. Two endpoints — text-to-image AND image edit (reference images + optional mask). Best-in-class for fine typography — chalkboards, signs, menus, posters, packaging, UI mockups, anything with legible text. Sync API, 1-4 images per call, custom dimensions up to 8.3MP. Includes pointer to a 700+ community prompt library (CC BY 4.0) for style/category inspiration. Triggers on gpt image 2, gpt-image-2, chatgpt image, openai image, typography image, sign mockup, poster mockup, menu image, packaging mockup, edit image, image edit, modify image, gpt image 2 prompt, awesome gpt-image-2.

One MCP, 30+ image and video models. Use this skill when the user wants to generate images or videos via Higgsfield (Seedance 2.0, Sora 2, Veo, Kling, Nano Banana Pro, GPT Image 2, Flux, Hailuo, Soul, Cinema Studio, etc.) without juggling per-provider API keys. Triggers on "higgsfield", "higgsfield mcp", "use higgsfield", or any image/video generation request when the user already has a Higgsfield subscription.

Turn any brief into a structured plan ready to feed /goal. Locked sections - Brief / Stack / Scope (Visuals + Functionality) / Out of Scope / Constraints / Definition of Done / Acceptance Criteria / Verification / Turn Budget / References / Risks. Engine-agnostic (Claude Code + Codex). Outputs a markdown plan file plus a paste-ready /goal one-liner. Triggers on "/plan-for-goal", "plan-for-goal", "plan for goal", "build me a /goal plan", "turn this into a plan".