Content
28%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 as a high-level topic outline rather than actionable guidance. It lists many risk management concepts (VaR, Kelly criterion, R-multiples, hedging) but provides no concrete implementations, formulas, code, or executable examples for any of them. The output section is a wish list of deliverables without templates or examples showing what they should look like.
Suggestions
Add executable code examples for core calculations: Kelly criterion formula, VaR calculation, R-multiple tracking, and expectancy computation with sample data.
Replace the generic 'Output' bullet list with concrete templates or example outputs (e.g., a sample risk dashboard in markdown, a position sizing calculation with specific numbers).
Add validation checkpoints to the workflow, such as verifying position sizes don't exceed account limits, checking correlation matrix validity, and confirming stop-loss levels are within acceptable ranges.
Remove boilerplate sections ('Use this skill when' / 'Do not use this skill when') and generic instructions ('Clarify goals, constraints, and required inputs') that waste tokens without adding actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant padding: generic 'Use this skill when' / 'Do not use this skill when' sections that add no value, vague boilerplate instructions ('Clarify goals, constraints, and required inputs'), and a long bullet list of outputs that are merely labels without substance. It explains concepts Claude already knows at a surface level without adding novel information. | 2 / 5 |
Actionability | The content is almost entirely abstract and descriptive. There are no concrete code examples, no executable commands, no formulas beyond a single inline expectancy formula, and no specific implementation details. The 'Approach' section lists high-level steps but lacks the specifics needed to actually execute any of them (e.g., no Kelly criterion formula, no VaR calculation code, no example of R-multiple tracking). | 2 / 5 |
Workflow Clarity | The 'Approach' section provides a rough sequence of 7 steps, but they are high-level descriptions without validation checkpoints, error handling, or feedback loops. For a skill involving financial risk calculations (which are consequential), there are no verification steps to confirm calculations are correct, no bounds checking, and no explicit validation of outputs. | 2 / 5 |
Progressive Disclosure | There is a reference to 'resources/implementation-playbook.md' for detailed examples, which suggests some progressive disclosure intent. However, no bundle files exist to support this reference, the reference is vaguely signaled ('If detailed examples are required'), and the bulk of the content that should be in supporting files (like formulas, code examples, templates) is neither inline nor properly referenced elsewhere. | 3 / 5 |
Total | 9 / 20 Passed |