Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill body is concise, clearly organized, and presents an unambiguous single-action workflow, but it lacks any executable code or usage example despite claiming a vectorized pandas implementation, which is the main gap.
Suggestions
Add a minimal copy-paste-ready code example showing the vectorized pattern scoring and composite signal generation in pandas.
Include a short worked example of calling the engine on a price DataFrame and interpreting the returned signal convention.
Document how the two parameters (body_pct, shadow_ratio) are applied in the implementation so users can tune them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean: compact pattern tables and a one-sentence Signal Logic rule with no padding explaining what candlesticks are, assuming Claude's competence so every token earns its place. | 3 / 3 |
Actionability | It gives the scoring rule and a parameters table, but provides no executable code despite the description promising a 'pure pandas vectorized implementation,' leaving it at 'some concrete guidance but incomplete / missing key details.' | 2 / 3 |
Workflow Clarity | The signal decision rule (score > 0 long, < 0 short, = 0 aside) plus the explicit signal convention table make the single action unambiguous, satisfying the simple-skill allowance for a clear single-purpose workflow. | 3 / 3 |
Progressive Disclosure | No bundle files exist and the body is under 50 lines with well-organized sections (Purpose, Signal Logic, Parameters, Dependencies), meeting the simple-skill allowance that progressive disclosure can score 3 from clean organization alone. | 3 / 3 |
Total | 11 / 12 Passed |