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…

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".

Turns any goal into one short, paste-ready "gauntlet loop" prompt - a prompt that makes an agent set a concrete quality bar, split the work into small judgeable pieces, run a builder and a separate harsh critic on each, compare blind against the bar, and loop…

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.

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…

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.…

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…

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,…

Runs Claude Code's built-in /doctor health check, then audits the workspace against the 6 then-and-now context-engineering shifts Anthropic shipped with the Claude 5 models (rules to judgement, examples to interfaces, upfront to progressive disclosure,…

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…

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.…