Content
85%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is highly actionable with a clear, validated workflow and executable contract details — its strongest dimensions. The main weakness is progressive disclosure: substantial reference-grade material is inlined rather than split into one-level-deep reference files.
Suggestions
Move the detailed config.json field reference and Review Criteria into separate files (e.g. CONFIG.md, REVIEW.md) with clearly signaled links, keeping SKILL.md an overview.
Surface the existing examples.md and cross-market-strategy reference earlier in the body where the relevant topics are introduced.
Consider extracting the Instrument Code Normalization and Market Detection tables into a reference file to reduce inline bulk.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is action-oriented and free of padded explanations of basic concepts; a few dense sections (position_adjustment, rebalance_tolerance) include extra measured detail that could be trimmed but mostly earns its place. | 4 / 5 |
Actionability | Provides an executable SignalEngine contract with exact signature and return semantics, a complete config.json schema, regex-based normalization rules, and a runnable syntax-check command — copy-paste ready guidance for common cases. | 5 / 5 |
Workflow Clarity | A clear 7-step numbered workflow includes an explicit syntax-check validation step and an iterative fix→backtest→re-evaluate feedback loop, plus hard gates and bug categories for evaluation. | 5 / 5 |
Progressive Disclosure | Structure and section headers are good, but nearly all reference-worthy detail (config.json field docs, review criteria, normalization rules) is inlined; only one local reference (examples.md) plus one cross-skill link exist, so the overview is not clearly separated from deeper material. | 3 / 5 |
Total | 17 / 20 Passed |