correlation-analysis

Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/correlation-analysis/SKILL.md

Quality

Content

60%Weight 40%Scale 1-5

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

The content is highly actionable with complete executable code and a clear end-to-end workflow, but it is verbose and monolithic: substantial implementation detail that belongs in separate reference files is inlined in SKILL.md, hurting both conciseness and progressive disclosure.

Suggestions

Split the bulk of the function implementations (cointegration tests, Kalman, signal generation, plotting) into a references/ file and keep SKILL.md as an overview that links to them, reducing the body to a scannable quick-start.

Trim explanatory prose on well-known concepts (Pearson/Spearman assumptions, what ADF/cointegration mean) since Claude already knows these; keep only finance-specific heuristics and threshold tables.

Add an explicit validation/re-run checkpoint in the pair-selection workflow (e.g. 'after selection, re-run cointegration on out-of-sample data before generating signals') to lift workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is a ~1100-line monolith that embeds many full, lengthy code implementations and explanatory tables; while accurate, it spends significant tokens on material Claude largely already knows (Pearson/Spearman, ADF, Kalman) and could be substantially tightened.	2 / 5
Actionability	It provides numerous complete, copy-paste-ready functions with docstrings, args, and return values covering the common cases end-to-end, matching the score-5 anchor for fully executable guidance.	5 / 5
Workflow Clarity	The full pair-trading workflow (Steps 1-5) is clearly sequenced with concrete thresholds and monitoring checkpoints; it lacks an explicit validate/re-run feedback loop for a batch selection process, leaving it just below score 5.	4 / 5
Progressive Disclosure	No bundle files exist and almost all reference-grade content (multiple full function implementations, parameter tables, empirical patterns) is inlined into a single ~1100-line SKILL.md rather than split into one-level-deep reference files, matching the score-2 anchor.	2 / 5
	Total	13 / 20 Passed

Description

71%Weight 40%Scale 1-5

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 richly specific and covers its niche comprehensively, with low conflict risk. Its main weakness is the absence of any explicit 'Use when...' trigger guidance, which caps completeness at 3.

Suggestions

Add an explicit trigger clause, e.g. 'Use when analyzing asset co-movement, testing for cointegration, building pairs-trading signals, or doing portfolio diversification analysis.'

Include user-natural synonyms such as 'pairs trading', 'statistical arbitrage', and 'hedging' alongside the current technical terms.

Consider trimming the long method list slightly so the trigger context stays scannable.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete actions ('co-movement discovery', 'return-correlation analysis', 'sector clustering', 'Engle-Granger / Johansen cointegration', 'half-life', 'Kalman dynamic hedge ratio', 'pair-trading signal generation') with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	It clearly answers 'what' with a detailed capability list but contains no 'Use when...' clause or equivalent explicit trigger guidance, which the guidelines cap at 3.	3 / 5
Trigger Term Quality	It includes strong natural domain keywords ('correlation', 'cointegration', 'pair-trading signal', 'sector clustering') but lacks common synonyms/variations a user might naturally say (e.g. 'pairs trading', 'hedging', 'stat arb'), placing it just below comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The niche (correlation/cointegration analysis and pair-trading signals) is fairly distinct from most skills with only minor overlap risk against a generic statistical-analysis skill, but it is not a perfectly crisp niche.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1103 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: charliedream1/ai_quant_trade
Path: a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/correlation-analysis/SKILL.md
Commit: 6565e03

Reviewed: 8 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.