Content
100%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.
An exemplary compact skill body: an executable command with fully documented arguments, a precise output contract, and only high-value non-obvious details. It fits the simple-skill exception cleanly, with clear sections and a real, one-level-deep script reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~25-line body is lean and assumes competence, never explaining what EMA or RSI are; every sentence adds non-obvious information (e.g., "Extra history is downloaded before the window, so the lines are settled from the first plotted bar"). | 5 / 5 |
Actionability | "uv run python scripts/chart.py SYMBOL [--period 6mo] [--fast 9] [--slow 20] [--rsi 14] [--output PATH]" is copy-paste ready, with every flag documented, defaults and output-path convention stated, and the JSON output contract specified field by field. | 5 / 5 |
Workflow Clarity | This is a simple single-purpose skill where the single action (run the command, then "Show the user the image after it's written") is unambiguous; it involves no destructive or batch operations, so no validation cap applies. | 5 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references: well-organized Instructions/Arguments/Output sections, and the single referenced path (scripts/chart.py) exists in the bundle and is one level deep. | 5 / 5 |
Total | 20 / 20 Passed |