quant-statistics

Quantitative statistical methods: ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing.

Quality

68%

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/quant-statistics/SKILL.md

Quality

Content

71%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 examples and strong domain-specific decision guidance, but it is a long monolithic document that would benefit from progressive disclosure into reference files and trimming of basic explanations Claude already knows.

Suggestions

Split the per-method API detail (e.g. GARCH variants, regression diagnostics, bootstrap applications) into reference files under references/ and keep SKILL.md as an overview with one-level-deep pointers.

Trim explanations of concepts Claude already knows — the GARCH parameter-meanings block, the common-tests quick-reference table, and the multiple-testing primer — retaining only the non-obvious quant-specific gotchas.

Add a short top-of-file workflow that sequences the typical flow (test stationarity → check cointegration → fit volatility → diagnose regression → bootstrap inference) with explicit checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is dense with high-value, non-obvious domain gotchas (index-alignment ValueError, 13% false-positive rate at lags=10, the two bootstrap functions' ddof difference), but it also explains concepts Claude already knows — the GARCH "Parameter meanings" block, the basic "Quick Reference for Common Tests" table, and the multiple-testing primer — so it is mostly efficient with some trimmable explanation.	3 / 5
Actionability	Nearly every section gives copy-paste-ready imports and calls with expected output shown as comments and concrete decision tables (e.g. adf_test, cointegration_test, fit_garch, bootstrap_sharpe), fully covering the common cases.	5 / 5
Workflow Clarity	Each method follows a clear call → interpret-via-decision-table → act pattern and the Regression Diagnostics Checklist gives a sequenced validation workflow, but there is no overarching end-to-end sequence, leaving minor checkpoint gaps relative to the top anchor.	4 / 5
Progressive Disclosure	The body has good section structure with clear headers, but it is a single ~365-line monolithic reference with no bundle files (references/scripts/assets absent) and no one-level-deep pointers, so content that could be split into reference files is inlined.	3 / 5
	Total	15 / 20 Passed

Description

66%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 uses natural domain trigger terms, but it omits any explicit "Use when..." usage guidance, which caps its completeness. Adding a trigger clause would lift the weakest dimension.

Suggestions

Append a "Use when..." clause, e.g. "Use when running stationarity/cointegration tests, fitting GARCH volatility, diagnosing regression issues, or bootstrapping Sharpe/factor statistics."

Add a couple of common synonyms users might say (stationarity, unit root, volatility forecasting, Sharpe) to broaden trigger coverage.

Reframe the method list with verb phrases ("Test stationarity and cointegration, fit GARCH models, diagnose regressions, bootstrap statistics") to strengthen the action framing.

Dimension	Reasoning	Score
Specificity	The description enumerates several concrete method families — "ADF unit-root / cointegration tests, GARCH volatility modeling, regression diagnostics (heteroskedasticity / autocorrelation), Bootstrap, and hypothesis testing" — giving specific, named capabilities rather than vague language, though it stops just short of the comprehensive verb-action form of the top anchor.	4 / 5
Completeness	It clearly states "what" the skill does (the listed methods) but contains no "Use when..." clause or equivalent explicit trigger guidance, so per the rubric cap completeness cannot exceed 3.	3 / 5
Trigger Term Quality	It surfaces domain-natural terms a quant user would actually say ("ADF", "cointegration", "GARCH", "Bootstrap", "heteroskedasticity", "autocorrelation", "hypothesis testing") with good coverage, but lacks synonyms/common variants (e.g. stationarity, unit root, volatility, Sharpe) that would push it to the top anchor.	4 / 5
Distinctiveness Conflict Risk	The quant-statistics niche with triggers like ADF/cointegration/GARCH is mostly distinct from sibling skills, with only minor overlap risk against a broader statistics or econometrics skill, so it sits above the midpoint but not at the clearly-bounded-niche top anchor.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/quant-statistics/SKILL.md
Commit: e90b6c6

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.