news-reaction-failure-analyzer

1# News Reaction Failure Analyzer
2 
3## Overview
4 
5Implements step 2 of Jason Shapiro's COT contrarian process: once a market
6is flagged as crowded (`cot-contrarian-detector`, step 1), check whether it
7FAILED to react to news that should have rewarded the crowd. A crowded-long
8market that doesn't rally on genuinely bullish news, or a crowded-short
9market that doesn't sell off on genuinely bearish news, is the core
10behavioral tell that the crowd has run out of buying/selling power — this
11is the confirmation step that turns "crowded" into a contrarian setup
12candidate (steps 3-5, still manual: price-action confirmation, entry, exit).
13 
14**Why this isn't a naive failure-ratio check:** an earlier design flagged
15"news failure" whenever fewer than half the relevant events "responded" —
16but under pure noise, roughly 69% of individual events fail to respond by
17chance, so that rule would CONFIRM on random noise 48-83% of the time
18depending on sample size. This skill instead requires the market to have
19moved *significantly against* the crowd's favorable news (a drift-
20significance test with a Monte-Carlo-verified null false-positive bound),
21never merely "didn't respond enough." See
22`references/news-failure-patterns.md` for the full statistical rationale.
23 
24## When to Use This Skill
25 
26**English:**
27- "Did the market shrug off [event] even though [asset] is crowded long/short?"
28- "Run a news-failure check on [symbol]"
29- "Is [symbol] confirmed for a Shapiro-style contrarian setup?"
30…