Content
36%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a role description or persona prompt than an actionable skill. It lists many quantitative finance topics (VaR, Sharpe ratio, Black-Litterman, etc.) but provides zero executable code, no concrete examples, and no real workflow with validation steps. The content tells Claude what to be rather than what to do, making it largely ineffective as a skill document.
Suggestions
Add concrete, executable code examples for at least the core tasks (e.g., a backtesting template with pandas, a VaR calculation, a portfolio optimization snippet using scipy.optimize).
Replace the abstract 'Approach' section with a concrete numbered workflow including validation checkpoints, e.g., 'Run backtest → verify Sharpe > threshold → check for overfitting via walk-forward analysis → if metrics degrade, adjust parameters and re-run'.
Remove the generic 'Use this skill when / Do not use this skill when' boilerplate and the persona statement ('You are a quantitative analyst...') to save tokens for actual actionable content.
Either provide the referenced 'resources/implementation-playbook.md' bundle file with real implementation details, or inline the most critical examples directly in the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary padding ('You are a quantitative analyst specializing in...') and the 'Use this skill when / Do not use this skill when' sections are generic boilerplate that add little value. The focus areas and output sections are essentially lists of topics rather than actionable content, but they aren't excessively verbose. | 3 / 5 |
Actionability | The skill provides no concrete code, commands, or executable examples. It lists focus areas and outputs at a high level ('Use pandas, numpy, and scipy') but never shows how to actually implement anything—no code snippets for backtesting, risk metrics, portfolio optimization, or any of the claimed capabilities. | 2 / 5 |
Workflow Clarity | The 'Approach' section lists a rough sequence (data quality → backtesting → risk-adjusted returns → out-of-sample testing → separation of code) but these are abstract principles, not actionable workflow steps. There are no validation checkpoints, no feedback loops, and no concrete commands. For a skill involving financial modeling and backtesting (where validation is critical), this is insufficient. | 2 / 5 |
Progressive Disclosure | There is a reference to 'resources/implementation-playbook.md' for detailed examples, which is appropriate progressive disclosure. However, no bundle files are provided to verify this reference exists, and the main content itself could benefit from better structuring—the focus areas and output lists could be in a reference file while the main skill focuses on actionable workflow. | 3 / 5 |
Total | 10 / 20 Passed |