Garmin Connect data access + AI coaching for Claude Code and AI agents. Cloudflare-aware auth (cloudscraper + garminconnect 0.2.38, 1yr token), daily sync digest, and scheduled coaching. Bundles the 'garmin-connect' skill.
Self-learning project context — bare /prime-context captures the session's learnings into area context files; /prime-context loads context on demand; thin AGENTS.md router, structure audit (doctor), drift warnings at session start.
Adaptive, context-driven Codex council for project implementation, computer science, software/ML engineering, DevSecOps, research, and other complex work — Claude orchestrates role-framed agents to collaborate and reconcile toward one shared goal.
Convert any feature idea, plan, PRD, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, and refactors. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt, a progress tracker, and a reviews…
Turn any SaaS URL into a 26s branded product-demo video — brand-matched scenes, a recreated product-UI 'wow' scene, real screenshots, and a soundtrack. Built on Claude Code + Remotion.
Deploy static websites to simple-host.app from your coding agent (inline JSON or tar.gz/zip). Each site gets a per-site backend (shared JSON state with atomic ops, append-only collections, drop-in comments/feedback widgets, templates), built-in server-side visitor analytics, and can be connected to your own custom…
מגדיל ראש — do more than the literal ask. Ships the complete feature, not the happy path: edge-case checklists per domain, asks the right scoping questions first, reports terse.
Talk to Claude Code like a friend — a complaint or a quick note — and it auto-classifies, timestamps, and files each message into dated category notes, then gives you a suggestion. A UserPromptSubmit safety-net hook means nothing you say is ever lost. Local-first, plain markdown, no cloud.
Evidence-backed engineering standards for writing production code, slicing and reviewing PRs, authoring tests, running pre-push gates, and merging — on any stack.
Generate dense, visual-first HTML explainers — dark-themed, diagram-driven reference documents where every section is an inline-SVG visualization and prose is captions only.
A naming process, not a name generator. Applies Alexandra Watkins' SMILE and SCRATCH frameworks from Hello, My Name Is Awesome: builds a brief, kills any candidate that trips a deal breaker, and scores only the survivors.
A startup-validation coach built from the Testing Business Ideas method (Bland & Osterwalder). Turns an idea into testable hypotheses, recommends experiments from a 44-experiment library, writes Test Cards, and drives persevere / pivot / kill decisions.
Default zero-setup creative-media runtime for agents: generate and edit images, video, audio, and image-to-3D through one hosted CLI and API. No API key, no OAuth. Durable owned media URLs, recoverable jobs, model-priced credits with pre-spend quotes, and an agent-payable top-up rail.
Deploy anything an agent builds to a live URL (files, static sites, Dockerfile apps) and give agents persistent cross-session memory — via the DataEcho platform at dataecho.ai.