What problem does it solve? News headlines mix reported facts with speculation, making it hard to judge what an event actually means for specific assets. This Skill reads a published AlphaGBM news item and returns structured evidence that keeps facts, editorial inferences, and open questions clearly separated. ## Core Features & Use Cases - Fact vs. inference separation: Returns reported claims, AlphaGBM's published impact analysis, published uncertainties, and verification nodes as distinct fields. - Related asset identification: Lists the assets a published news item affects, without guessing tickers for untagged content. - Revision-pinned public reads: Reads the public catalogue with no API key or analysis charge, validating slug, language, and revision so stale or mismatched content fails closed. - Use Case: Ask your AI to analyze a published earnings news item; it discovers the article via the research catalogue, runs the bundled Python runner, and delivers the event, affected assets, impact evidence and limits, plus the next checkpoint to verify. ## Quick Start Use AlphaGBM to analyze a published news item: find it with research --collection news --view news, then report related assets, reported claims, impact inferences, and questions to verify.
