一个问题，Claude、Gemini、ChatGPT 同时给你三个独立答案——然后展开结构化辩论，最终给出一个真正经得起推敲的建议。不是一家之言，而是三种视角的正面交锋。适合那些一个人说了不算的时刻：选技术架构、给策略挑毛病、听点大实话而不是场面话，或者拖了很久还没想通的决定。
Challenge your thinking before you commit. The riskiest decisions are the ones that feel obvious too early. Council runs your plan past independent advisers who surface objections and hidden risks — before you commit.
Track top public market voices on X and turn scattered stock opinions, news, fund flows, and disclosed trades into a daily market consensus dashboard. See who is bullish, bearish, or has no clear stance on the same stock, then compare their reasoning, disagreements, and evolving views. Supports multilingual reports and cross-account stock analysis. Public information only—not investment advice.
At McKinsey, a recommendation was only as good as the research under it. So I learned to do it right: scope the real question, pull from independent sources, triangulate what's actually true, and ground every claim in evidence. This Skill runs that discipline for you — breaking down a question, comparing sources, verifying claims, and writing a structured report with citations you can check. Decisions on evidence, not vibes.
No stock is only a buy or only a sell. Name any stock, sector, or theme and get a two-sided evidence read that argues the strongest bear case first, then weighs it against the bull evidence and reports where the public data leans: bull, balanced, or bear. Delivered as a self-contained HTML report — bull/bear force-field cards with intensity and horizon, net evidence pressure by week/month/quarter/year, and scenario drivers. Research, not advice: no buy/sell calls, no targets, no sizing.
Forces AI agents to identify independent judgment axes before answering any complex question — decomposing the problem into minimum separable sub-problems, solving each one independently, then integrating into a single conclusion so complex analysis is auditable, correctable, and never a blur of mixed reasoning.
Analyzes football forecasts provided by the user to identify consensus, agreement levels, prediction ranges, and key disagreements in one structured report.
Four independent AI reviewers — Security Skeptic, Reliability Realist, Maintainability Pragmatist, and Performance Pessimist — each review your diff blind to the others' verdicts, so real bugs don't get averaged away into one polite summary.
You ran a test and one variant looks better. Is that a finding or a coin flip? Paste trials and successes per variant. You get Wilson 95% intervals, a two-proportion test, and the check almost nobody runs: an overdispersion gate asking whether your grouping label explains anything. If the spread inside a group beats the spread between groups, no winner is declared. A p-value near zero has died on this gate before. Post-hoc axes get labelled. Underpowered tests get a sample size.