residual-edge-analyzer

Separate a strategy return series into declared baseline exposure and residual edge with returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns. Use when evaluating whether backtest, out-of-sample, or live returns contain independent alpha beyond market, equal-weight, momentum, sector, or user-supplied factor returns; when explaining whether a drawdown came from baseline exposure or strategy-specific behavior; or when a strategy needs an attribution quality gate after backtesting. Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics without a dated return series.

Quality

95%

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

Quality

Content

96%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.

A dense, well-structured instruction file: exact commands and config keys, an explicit validate-then-interpret workflow with hard stops, deferral of contract and methodology details to real reference files, and a concrete boundaries section. The only blemish is the absolute GitHub URL in Prerequisites where a local relative path would be more robust.

Suggestions

In Prerequisites, link the input contract via the local relative path (references/input-contract.md) instead of the absolute GitHub URL, matching the path style used in the Resources section.

Optionally add one explicit error-recovery note in step 2 (e.g. 'if validation fails, report the specific failed check and the minimal fix; do not silently repair the data'), making the feedback loop explicit rather than implied by 'Stop'.

Dimension	Reasoning	Score
Conciseness	Lean, imperative prose throughout with zero concept tutorials; even explanatory lines like 'do not calculate a Sharpe ratio from raw OLS residual mean because an intercept makes that mean zero' convey non-obvious domain knowledge rather than padding. Every section earns its tokens.	5 / 5
Actionability	Fully executable guidance: a copy-paste bash invocation with all four flags ('--input', '--config', '--output-json', '--output-markdown'), enumerated config keys ('baseline_selection', 'analysis_scope', etc.), and concrete validation requirements ('unique ISO dates; finite numeric returns greater than -100%').	5 / 5
Workflow Clarity	A clearly sequenced 5-step workflow with an explicit validation checkpoint and hard stop ('Stop if the input lacks a dated strategy return series'), four diagnostic statuses for interpreting failure modes, and structured handoff rules in step 5. Validation-before-verdict is enforced via the mandatory-declaration rule.	5 / 5
Progressive Disclosure	The body stays an overview and correctly splits the CSV/config contract and statistical methodology into real one-level-deep reference files, each with a one-line description in Resources. The minor gap is mixed reference signaling: Prerequisites links the input contract via an absolute GitHub URL instead of the local 'references/input-contract.md' path used in Resources, which fits anchor 4's 'minor organization gaps' rather than 5's fully clear navigation.	4 / 5
	Total	19 / 20 Passed

Description

92%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.

An exemplary description: concrete capabilities, explicit 'Use when' triggers covering backtest evaluation, drawdown explanation, and quality gating, plus clear do-not-use boundaries that disambiguate it from Brinson and Shapley-style analyses. Only minor room to broaden natural phrasing synonyms.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete, specific actions — 'returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns' — giving comprehensive coverage of the skill's capabilities with no generic filler.	5 / 5
Completeness	Clearly answers both what ('Separate a strategy return series into declared baseline exposure and residual edge...') and when ('Use when evaluating whether... when explaining whether... or when...'), with concrete trigger phrases plus an explicit do-not-use clause.	5 / 5
Trigger Term Quality	Good keyword coverage with natural domain phrases users would say — 'independent alpha', 'backtest', 'out-of-sample', 'drawdown', 'attribution quality gate'. A few natural variations are still missing (e.g. 'is my strategy just market beta?', 'does my strategy beat the benchmark'), which fits the anchor-4 example better than 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	Clear niche (residual alpha attribution on dated return series) with an explicit boundary — 'Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics' — minimizing conflict risk with adjacent analysis skills.	5 / 5
	Total	19 / 20 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/residual-edge-analyzer/SKILL.md
Commit: eab8d5c

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.