hoodini

Build a new AI agent on AWS and deploy it easily, OR wrap and deploy an agent you already have, using the Amazon Bedrock AgentCore harness. Explains what an "agent harness" is (the runtime scaffolding around a model - agent loop, tool execution, memory,…

Build AI agents with the Strands Agents SDK - the open-source framework (the agent "brain") for writing agent logic, tools, and multi-agent systems in Python. Model-agnostic, AWS Bedrock by default. Covers Agent, the @tool decorator, model providers…

Master prompt-engineer for photoreal, artifact-free AI still images on ANY tool (Reve, Midjourney, Flux, GPT-image, Imagen, Nano Banana, Stable Diffusion). Builds prompts that hit National-Geographic-grade realism — true skin/fur texture (no plastic), correct…

Award-winning director's brain for making films/videos with AI. Runs a gated, interrogation-first process: lock the IDEA and the SCRIPT (the story) in words before generating a single pixel, then plan shots/camera/light/sound, then generate and edit. Use…

Generate unified, on-brand Instagram Reel covers for Yuval (YUV.AI Neon Phoenix system) — the signature look is a giant Hebrew headline BEHIND the subject cutout + a punch line IN FRONT (depth effect), on rich black with a dim neural-net field, series-colored…

Yuval's all-in-one AI video pipeline. Turns an idea/script into a finished, on-brand MP4 by orchestrating HyperFrames (HTML→deterministic video render), Lottie (branded motion graphics), ManimCE (math / neural-network / concept animations), and a…

Build a premium cinematic landing page with mouse-scrub video hero and brand-driven narrative-arc sections. Use whenever the user provides a hero video plus a product / subject / brand and wants a landing page, promo site, product showcase, marketing page, or…

Edit any video into a captioned showcase — transcribe (any language, defaults to large-v3), present a transcript_review.txt for the user to fix mishears BEFORE rendering, then build a HyperFrames composition with liquid-glass caption pills, liquid blob…

Visibility into Logan self-healing and self-improving. Show what was analyzed, what improved, how, and why. Journal durable lessons. Trigger: /improve, /heal, /reflections, "what did you learn", "why did you decide that".

Yuval's design DNA - MANDATORY for any web/frontend deliverable: landing page, website, app UI, dashboard, React, HTML, CSS, portfolio, promo page. Signature moves (video-scrub heroes, parallax frame-scrub, HyperFrames motion), the YUV design system…

Yuval Avidani's learning-and-teaching method. Use WHENEVER Yuval wants to learn, understand, or be taught anything, AND when building educational/explanatory content (tutorial, course, interactive lesson, deep-dive explainer, walkthrough). Governs HOW to…

Ultra-compressed communication mode. Cuts output fluff so users save tokens. Intensity: lite | full (default) | ultra. Trigger: /caveman, "caveman mode", "be brief", "less tokens". Keep code/errors exact. User can disable anytime.

Default creative video stack for Logan: HyperFrames (HeyGen) HTML compositions to MP4. Use for any video, deck motion, captions, product launch, website-to-video, faceless explainer, PR-to-video, motion graphics. Routes to hyperframes skills. Trigger: video,…

Lazy senior mode - YAGNI, stdlib first, shortest working diff. Intensity: lite | full | ultra. Trigger: /ponytail, "be lazy", "yagni", "simplest", "do less", over-engineering complaints. Does NOT control speech style (use caveman for terse prose).

Profile interview and identity memory. Grill the user for who they are, social links, brand, tech stack, likes/dislikes. Persist to MEMORY.md / PROFILE.md. Trigger: /whoami, first-run onboarding, "update my profile", "remember who I am".

Recommend or switch to a token-saving model tier (fast / default / premium / local / gateway) based on task hardness. Triggers: "auto route", "save tokens", "use cheap model", "route this task", "which model should we use".