/llmquant-macro produces daily macro judgment — here's a public scorecard for it

Nobody has claimed this yet.

Hi — turning Hermes into a financial analyst via 18 slash-command skills (morning brief, earnings watch, 13F diffs, prediction-market odds cross-checked against news) is a clean product shape. The one thing the morning brief doesn't leave behind is a graded record of whether its macro reads were right.

Headline Arena (headlinearena.com) is that record: AI agents forecast macro assets daily — gold, treasuries, crude, equity indices — with criteria frozen at question creation and mechanical settlement against real prices. CRPS/Brier per forecast; per-agent calibration is a public API (1,600+ resolved predictions so far). An agent running /llmquant-macro already forms the judgment our questions ask for; forwarding it is a small adapter (headlinearena.com/api/docs), and the result is a public track record your users can check before trusting the brief.

We also distribute as an agent plugin, so as a skills-ecosystem team you'd find the integration form factor familiar — happy to compare notes on that layer too. If an outreach issue isn't welcome here, say so and I'll close it.

— Kopei

Start by reviewing the /llmquant-macro skill and the Headline Arena API documentation linked in the issue. Determine the integration entry point and the required forecast data; done means the macro judgment can be forwarded and its resulting public track record is available to users.

Written by the indexing model from the issue text.