news-reaction-failure-analyzer

Judge whether a market FAILED to react to news favorable to a crowded speculative position — step 2 of Jason Shapiro's COT contrarian process. Consumes a cot-contrarian-detector report (or an explicit direction) plus a Claude-curated events JSON, fetches the underlying price series with a documented fallback chain, and produces a fail-closed CONFIRMED / NOT_CONFIRMED / INSUFFICIENT_EVIDENCE verdict using a statistically validated drift-significance test (not a naive failure-ratio, which false-confirms on pure noise). Generic beyond COT — reusable for PEAD and macro-crowding news-failure checks. Use when the user asks to check news-failure confirmation, whether a crowded market "shrugged off" good/bad news, or wants to run Shapiro step 2 on a CROWDED_LONG/CROWDED_SHORT market.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear phased workflow and well-structured one-level references, but leans verbose in its statistical-rationale prose that overlaps content already delegated to reference files.

Suggestions

Trim the 'Why this isn't a naive failure-ratio check' paragraph in Overview to a single sentence and defer the 69%-noise math to references/news-failure-patterns.md, which already covers it.

Condense the 'Residual statistical risk under extreme correlation' Guardrail to the limitation + the --drift-z 1.75 knob, moving the full AR(1) numbers to the reference.

Consider moving the per-field Output enumeration into references/news-failure-patterns.md (or a schema reference) to keep the main body focused on the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly substantive and avoids generic explanations Claude already knows, but it carries padding that could be tightened — e.g. the 'Why this isn't a naive failure-ratio check' paragraph in Overview and the lengthy 'Residual statistical risk under extreme correlation' Guardrail repeat statistical rationale already detailed in references/news-failure-patterns.md.	2 / 3
Actionability	Provides a fully executable CLI invocation with real flags and arguments, a concrete JSON handoff block, and an enumerated output-field schema — copy-paste ready guidance rather than abstract direction.	3 / 3
Workflow Clarity	A clear four-phase sequence with explicit fail-closed validation checkpoints (NEUTRAL refusal, stale/missing detector vintage, --min-events threshold, dropped_events never hidden) and error-recovery feedback to INSUFFICIENT_EVIDENCE instead of crashing.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to two one-level-deep references (news-failure-patterns.md, price-source-map.md), both of which exist as real files, with a dedicated 'When to Load References' section signaling navigation.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, well-triggered, complete, and distinctive, naming concrete pipeline actions alongside natural user phrasings and an explicit 'Use when' clause. No meaningful weaknesses against the rubric anchors.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Consumes a cot-contrarian-detector report', 'curates ... events JSON', 'fetches the underlying price series with a documented fallback chain', and 'produces a fail-closed CONFIRMED / NOT_CONFIRMED / INSUFFICIENT_EVIDENCE verdict using a ... drift-significance test' — far beyond a single named domain action.	3 / 3
Completeness	Explicitly answers both what it does (the verdict pipeline) and when to use it via a clear 'Use when the user asks to ...' clause, satisfying the what-AND-when anchor.	3 / 3
Trigger Term Quality	Includes natural user phrasings such as 'check news-failure confirmation', 'whether a crowded market "shrugged off" good/bad news', and 'run Shapiro step 2 on a CROWDED_LONG/CROWDED_SHORT market', covering how users would actually phrase the request.	3 / 3
Distinctiveness Conflict Risk	A clear niche — Shapiro COT contrarian step 2 with CROWDED_LONG/CROWDED_SHORT triggers — is distinct from generic analysis skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/news-reaction-failure-analyzer/SKILL.md
Commit: 62a1635

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.