Content
65%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.
A dense, actionable reference skill with executable code and useful lookup tables, but it is monolithic (no progressive disclosure into bundle files) and lacks an explicit sequenced workflow with validation checkpoints.
Suggestions
Split the large ETF ticker/categorization tables and the data-source table into reference files (e.g. references/etf_catalog.md) and link to them from SKILL.md to improve progressive disclosure.
Add an explicit numbered analysis workflow (pull data → compute breadth & C/D ratio → classify signals → assemble output) with a validation/sanity-check step before producing the report.
Tighten concept explanations (e.g. creation/redemption mechanics) to assume more domain competence and reduce token cost.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean reference material (ticker tables, AUM figures, cycle-phase mappings, data-source latency) that earns its tokens; only minor stretches of concept explanation could be trimmed, so it sits just below the top anchor. | 4 / 5 |
Actionability | Provides executable Python (yfinance download, sector breadth, cyclical/defensive ratio, an etf_flow_signal function) plus a concrete output template and data-source table, with only minor gaps (e.g. undefined daily_flows/aum variables in the signal snippet). | 4 / 5 |
Workflow Clarity | The body is organized as concepts plus an output template rather than an explicit step sequence, and there are no validation/checkpoint steps; the implicit workflow is present but checkpoints are missing. | 3 / 5 |
Progressive Disclosure | Well-sectioned single file with no bundle files or external references; sizable reference tables (tickers, flow sources) that could live in separate files are inlined, leaving structure good but separation incomplete. | 3 / 5 |
Total | 14 / 20 Passed |