Content
78%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 body is commendably lean and well-structured with a clear workflow and validation checkpoint, but the guidance stays abstract — it tells Claude what to do without concrete examples of encodings or charts. Adding a few concrete encoding/chart examples would meaningfully raise actionability.
Suggestions
Add one or two concrete examples mapping comparison types to encodings (e.g. 'change over time → line chart; part-of-whole → stacked bar') to make step 2 actionable.
Add a brief feedback loop after the sanity-check, e.g. 'If axes are misleading or values are missing, adjust encodings and re-check.'
Optionally note a default tool or library (e.g. matplotlib/plotly) so the produce step is executable rather than abstract.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is extremely lean (~12 lines) with no padding and no explanation of concepts Claude already knows; every token earns its place, matching anchor 5. | 5 / 5 |
Actionability | A structured 4-step workflow with a concrete sanity-check ('axes, units, and missing values') and clear non-goals, but 'Choose encodings for the comparison at hand' and 'Produce the visual' are high-level hints with no concrete examples or specifics. | 3 / 5 |
Workflow Clarity | Clear numbered sequence with an explicit validation checkpoint (step 4 sanity-check), but there is no error-recovery feedback loop describing what to do when the check fails; not a destructive/batch operation so no cap applies. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references and well-organized sections (When to use, Non-goals, Workflow), meeting the simple-skill exception for a top score. | 5 / 5 |
Total | 17 / 20 Passed |