Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.

Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF

Claude Code skill for AI filmmaking — shot lists, keyframe & video prompts, with 10 director-style overlays (Spielberg, Kubrick, Wong Kar-wai, Nolan...).

One line of intent → a presentation-grade, dark-editorial HTML deck. A Claude Code skill.

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

Give your CLAUDE.md / AGENTS.md a checkup — audit size vitals, dead references, drifted claims, and backtest every rule against your own session history to see which rules get followed, ignored, or never used. A doctor-style report that cites its evidence.