Content
67%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 an actionable, well-structured matplotlib reference with strong code examples and a real bundle, but it is verbose in its explanatory prose and inlines content that overlaps with the reference files.
Suggestions
Trim overview and concept paragraphs (Figure/Axes hierarchy, interface rationale) that restate what Claude already knows about matplotlib.
Move the inlined styling and plot-type catalogs into references/ and leave brief pointers, reducing duplication with styling_guide.md and plot_types.md.
Make code examples self-contained so variables like x, y1, matrix, X/Y/Z are defined or noted as assumed inputs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly code-driven and useful, but several prose sections explain concepts Claude already knows (the Figure/Axes/Artist hierarchy, interface rationale, overview paragraphs) and could be tightened. | 3 / 5 |
Actionability | Abundant concrete, executable code across plot types, styling, saving, and 3D with real parameters; minor gaps where examples reference undefined variables (x, y1). | 4 / 5 |
Workflow Clarity | Well-organized into numbered workflows (1-6) with clear sequencing; no validation checkpoints, but plotting is non-destructive so they are not critical, fitting the simple-skill allowance. | 4 / 5 |
Progressive Disclosure | Real references/ (4 files) and scripts/ (2 files) are clearly signaled one level deep, but a fair amount of styling/plot-type content that duplicates the reference files is inlined in the body. | 4 / 5 |
Total | 15 / 20 Passed |