Content
22%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 is essentially a placeholder that provides no actionable guidance for calculating risk metrics. It contains no code examples, no formulas, no specific methodology, and relies entirely on a referenced file that doesn't exist in the bundle. The instructions are generic statements that could apply to any domain.
Suggestions
Add executable Python code examples for at least the core metrics (VaR, CVaR, Sharpe ratio) using numpy/scipy or pandas
Replace generic instructions ('Apply relevant best practices') with specific workflow steps: e.g., 1. Gather return series, 2. Calculate rolling VaR at specified confidence level, 3. Validate against historical drawdowns
Include the actual implementation-playbook.md in the bundle, or inline the essential formulas and code patterns directly in the SKILL.md
Add concrete input/output examples showing what data format is expected and what the calculated metrics look like
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Use this skill when' and 'Do not use this skill when' sections add some padding, and the instructions are generic platitudes ('Clarify goals, constraints, and required inputs') rather than domain-specific guidance. However, it's not excessively verbose. | 3 / 5 |
Actionability | There is no concrete code, no formulas, no specific commands, and no executable examples for calculating VaR, CVaR, Sharpe, Sortino, or drawdown. The instructions are entirely vague ('Apply relevant best practices and validate outcomes'). | 1 / 5 |
Workflow Clarity | There is no meaningful workflow or sequence of steps. The four bullet points under Instructions are generic platitudes with no specific sequencing, validation checkpoints, or error recovery guidance for risk metric calculations. | 1 / 5 |
Progressive Disclosure | The skill references `resources/implementation-playbook.md` for detailed patterns, which is appropriate progressive disclosure in principle. However, no bundle files are provided to verify the reference exists, and the SKILL.md itself provides essentially zero useful content as an overview—it's an empty shell pointing elsewhere. | 3 / 5 |
Total | 8 / 20 Passed |