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

76%

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 ./agent/src/skills/correlation-analysis/SKILL.md

Quality

Content

77%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 executable code and a well-sequenced, validation-backed workflow. It loses points on conciseness (verbose docstrings/tables) and progressive disclosure (everything inlined into one long file with no external references).

Suggestions

Move the empirical-pattern tables (China A-share sector patterns, cross-market linkage, regime behavior) and the visualization templates into reference files and link to them from SKILL.md to reduce inline bulk.

Trim routine docstring prose (e.g. restating the OLS/Kalman state equations already shown in code) and keep only the non-obvious finance rationale.

Add a short 'Quick start' or single-mode quickstart at the top so the overview loads before the full per-mode reference material.

Dimension	Reasoning	Score
Conciseness	The ~1100-line body is mostly efficient and the domain content (cointegration rules, regime tables, A-share patterns) earns its place, but verbose docstrings and large empirical-pattern/reference tables could be tightened, matching the score-3 anchor rather than the lean score-4.	3 / 5
Actionability	Fully executable, copy-paste-ready functions with imports, complete signatures, and concrete examples covering the common cases (scan, cointegration tests, signals, monitoring), matching the score-5 anchor.	5 / 5
Workflow Clarity	The 'Full Workflow From Correlation to Signal' gives an explicit 5-step sequence with validation checkpoints (p<0.05, ADF, half-life bands) and feedback loops via monitor_spread_health (health score -> reduce/exit), matching the score-5 anchor.	5 / 5
Progressive Disclosure	Section headers are clear, but with no bundle files present the entire reference library, empirical tables, and visualization templates are inlined into one ~1100-line SKILL.md rather than split into one-level-deep reference files, matching the score-3 anchor; the under-50-line simple-skill exception does not apply.	3 / 5
	Total	16 / 20 Passed

Description

75%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 specific and distinctive, clearly carving out a quant-finance correlation/cointegration niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Append an explicit trigger clause, e.g. 'Use when analyzing asset co-movement, testing for cointegration, building pairs-trading signals, or clustering assets by correlation.'

Soften the technical-jargon density by adding a couple of natural user-facing phrases (e.g. 'pairs trading', 'stat-arb', 'spread mean-reversion') alongside the method names.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'co-movement discovery', 'Engle-Granger / Johansen cointegration', 'half-life', 'Kalman dynamic hedge ratio', 'pair-trading signal generation' — giving comprehensive coverage of the skill's actions, matching the score-5 anchor.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Strong domain keywords ('correlation', 'cointegration', 'pair-trading', 'hedge ratio', 'half-life') that a quant user would naturally say, but coverage leans on technical jargon and omits common lay synonyms/variations, placing it just below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	A clear niche (correlation/cointegration/pairs-trading analytics) with distinct, specialized triggers and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	17 / 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 (1124 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: HKUDS/Vibe-Trading
Path: agent/src/skills/correlation-analysis/SKILL.md
Commit: f9cb061

Reviewed: 3 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.