Multi-Agent LLM Orchestration for High-Quality Incident Response - 100% actionable recommendations vs 1.7% for single-agent
🦆 Socratic assistant operating system for developers who want better-quality decisions, not blind automation.
A skill that evaluates whether a suggested change is truly worth making before giving advice or editing.让你的agent三思而后行
Calibrated honesty and anti-sycophancy for Claude and Codex agent workflows.
A data-driven football scouting platform mitigating Team Bias. It leverages 360° spatial data, EPV grids to evaluate a player's true decision-making under pressure.
A curated map of judgment infrastructure for human-led AI.
Test an idea, claim, or decision before trusting it with Claude and Codex.
A five-member expert council that pressure-tests consequential decisions for Claude and Codex.
Judgment infrastructure for human-led AI: portable Claude and Codex skills.
Turn messy context into a brief you can think with for Claude and Codex.
Adaptation of the Contextual Football Scouting framework to Wyscout seasonal data. Features proxies for space control, decision quality (DQI), player similarity, and an in-memory FastAPI & React dashboard.
Custom GPT for recruiter-style coaching across media, technology, ad-tech, and AI business-side roles.
GitHub profile for Greg Lichtenthal: judgment infrastructure for human-led AI.
Freeze a decision, then score it against chance. No backfill.
To associate your repository with the decision-quality topic, visit your repo's landing page and select "manage topics."