JeremyGracey-AI

Prime Radiant — AI skill for Claude Code

AI community

Calibrated forecasting: CDC FluSight quantile forecaster (LightGBM + baseline replica, WIS-scored, vintage-honest) with a live dashboard; Metaculus LLM thread parked.

How to install Prime Radiant

This entry records only its repository, not the path inside it, so there is no exact command to give. Open JeremyGracey-AI/prime-radiant and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Prime Radiant does

Calibrated forecasting: CDC FluSight quantile forecaster (LightGBM + baseline replica, WIS-scored, vintage-honest) with a live dashboard; Metaculus LLM thread parked.

Alternatives in AI

Om Humanize — Voice-calibrated editing — makes Claude-drafted text sound like you wrote it, not like AI wrote it 4.6k ★
Tokentap — Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard 763 ★
Openclaw Dashboard — 🔐 Secure, real-time monitoring dashboard for OpenClaw AI agents 654 ★

README

Prime Radiant

[![ci](https://github.com/JeremyGracey-AI/prime-radiant/actions/workflows/ci.yml/badge.svg)](https://github.com/JeremyGracey-AI/prime-radiant/actions/workflows/ci.yml) [![AI-USE: declared](https://img.shields.io/badge/AI--USE-declared-2ea44f)](./AI-USE.md) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE) [![Dashboard](https://img.shields.io/badge/%F0%9F%A4%97%20Space-live-blue)](https://huggingface.co/spaces/jeremygracey-ai/prime-radiant) [![docs](https://img.shields.io/badge/docs-live-2ea44f)](https://jeremygracey-ai.github.io/prime-radiant/) [![PyPI](https://img.shields.io/pypi/v/prime-radiant)](https://pypi.org/project/prime-radiant/) [![codecov](https://codecov.io/gh/JeremyGracey-AI/prime-radiant/branch/master/graph/badge.svg)](https://app.codecov.io/github/JeremyGracey-AI/prime-radiant)

Calibrated forecasting, measured honestly. Two threads share this repo:

FluSight epi forecaster (prime_radiant.epi) — CDC FluSight-format quantile forecasts of weekly US influenza hospital admissions: LightGBM quantile regression in the shape of the FluSight-2023/24-winning flusion model, ensembled with a validated replica of CDC's own baseline. Pure statistical pipeline; no LLM calls.
Metaculus bot (prime_radiant.metaculus) — LLM forecasting on binary questions (parked at its retrieval phase; client + tests remain green).

Backtest results (three seasons, vintage-honest)

Rolling-origin backtests over 85 weekly origins across the 2023-24, 2024-25 and 2025-26 seasons. Every forecast is trained only on the data snapshot a live forecaster would have held on the Wednesday submission evening (the hub's git history is the vintage store); scored against final truth as of 2026-07-09, horizons 0-3, all 53 jurisdictions. `wis_rel` = mean WIS relative to the official FluSight-baseline on the common task set across all six models (lower is better; the official "scaled relative skill" collapses to this ratio on i