performance-attribution

Performance attribution analysis — Brinson sector/stock-selection attribution, factor alpha/beta decomposition, market-timing evaluation, and benchmark comparison framework.

Quality

58%

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/performance-attribution/SKILL.md

Quality

Content

50%

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

The content is well-structured and information-dense with concrete formulas, thresholds, and templates, but it is a long monolithic single-file skill dominated by pseudocode-style formulas with no executable code and no explicit validation checkpoints in its workflow.

Suggestions

Tighten redundancy — consolidate the duplicate risk-adjusted-metric tables and trim the Notes section to non-obvious caveats only — to reduce length and improve token efficiency.

Add at least one minimal executable snippet (e.g., a statsmodels OLS/regression example or a Brinson computation snippet) to lift actionability from formula-only to copy-paste ready.

Add explicit validation checkpoints to the Analysis Framework (e.g., 'verify Allocation+Selection+Interaction+residual equals total excess return before reporting', 'confirm factor-return data is loaded before running regression').

Dimension	Reasoning	Score
Conciseness	The body is mostly high-value formulas, tables, and templates that assume Claude's competence, but at ~248 lines it carries redundancy (repeated metric tables and a Notes section restating fairly obvious caveats) and could be tightened; not 3 due to length and redundancy, not 1 because it avoids padded concept explanation.	2 / 3
Actionability	Provides concrete formulas, specific thresholds ('Sharpe >1.5', 'gamma > 0 and significant'), and reusable templates, but guidance is largely mathematical/pseudocode notation rather than executable code, so it is actionable but incomplete; not 3 because nothing is copy-paste runnable, not 1 because concrete specifics are present.	2 / 3
Workflow Clarity	The 'Analysis Framework' section lays out a clear 4-step sequence (Aggregate, Attribution Decomposition, Style Analysis, Conclusions), but it lacks explicit validation checkpoints or error-recovery feedback such as verifying residuals sum or confirming factor data loaded; not 3 due to missing checkpoints, not 1 because the sequence is clear.	2 / 3
Progressive Disclosure	Sections are well-organized, but all content is inline in a single ~248-line SKILL.md with no bundle files; reference-heavy material (metric tables, factor-proxy mappings, output templates) that could be split remains inline, matching the 'content that should be separate is inline' anchor; not 3 because it is monolithic, not 1 because organization is clean.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 naming four concrete attribution capabilities, but it lacks any explicit 'Use when...' trigger guidance and offers only partial coverage of natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when explaining why a portfolio outperformed or underperformed a benchmark, decomposing excess returns, or evaluating manager skill/alpha').

Include more natural user-facing trigger terms such as 'return decomposition', 'explain my returns', or 'why did my strategy outperform' alongside the technical labels.

Dimension	Reasoning	Score
Specificity	Enumerates four concrete analysis capabilities — 'Brinson sector/stock-selection attribution', 'factor alpha/beta decomposition', 'market-timing evaluation', and 'benchmark comparison framework' — matching the multiple-specific-actions anchor; not 2 because it lists more than 'some actions'.	3 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger for when to use it, which per the guidelines caps completeness at 2; not 1 because the 'what' is well covered.	2 / 3
Trigger Term Quality	Contains relevant domain keywords ('performance attribution', 'Brinson', 'benchmark comparison') but lacks common natural phrasings a user would say and leans technical; missing common variations keeps it at 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The performance-attribution niche with specialized terms ('Brinson', 'factor alpha/beta decomposition') is distinct and unlikely to trigger other skills; not 2 because it is more specific than a generic domain reference.	3 / 3
	Total	10 / 12 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/performance-attribution/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.