Content
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, concise reference skill with executable examples and clean progressive disclosure to real bundle files. The main gap is the absence of validation/error-handling guidance in the CLI rendering workflow.
Suggestions
Add a brief note on validating .mmd syntax or handling mmdc render failures (e.g., checking exit codes or error output before retrying), to strengthen workflow clarity.
Consider an explicit end-to-end sequence (write diagram → render via CLI → verify output file exists) with a checkpoint, rather than only listing example commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean body that assumes Claude's competence — no over-explanation of what a flowchart or library is, every section delivers syntax or commands directly. | 3 / 3 |
Actionability | Provides executable, copy-paste-ready guidance: 'npm install -g @mermaid-js/mermaid-cli', 'mmdc -i diagram.mmd -o diagram.svg', and a complete HTML embed with script tags. | 3 / 3 |
Workflow Clarity | Sections are organized but the CLI render path (write .mmd → convert) lacks validation or error-recovery checkpoints for when rendering fails, capping the score per the batch/destructive guidance even though operations are low-risk. | 2 / 3 |
Progressive Disclosure | Clear overview body with well-signaled one-level-deep references ('See references/cli-usage.md', 'See references/integration.md'); all five cited reference files exist and are organized in a Resources section. | 3 / 3 |
Total | 11 / 12 Passed |