Content
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably well-structured skill with strong actionability and good progressive disclosure to reference files. Its main weaknesses are repetitive command prefixes and some unnecessary explanatory content that could be trimmed. The workflow is straightforward but could benefit from explicit validation/error-handling guidance integrated into the main flow.
Suggestions
Reduce repetition by defining the script directory path once at the top (e.g., 'All commands below assume you've run `cd ~/.claude/skills/mermaid-tools/scripts` first') instead of repeating it in every code block.
Remove the 'Overview' paragraph and 'What the Script Does' enumeration—the command usage and output files section already convey this information more efficiently.
Integrate prerequisite verification as step 1 of the core workflow with a clear 'if missing, stop and see references' checkpoint rather than listing it as a separate section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has some unnecessary repetition—the 'cd ~/.claude/skills/mermaid-tools/scripts' command is repeated 7 times, and sections like 'What the Script Does' and 'Bundled Resources' explain things Claude doesn't need spelled out. The overview paragraph restates the description. However, it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides fully executable bash commands with concrete parameters, environment variable overrides, and specific examples. Commands are copy-paste ready with clear parameter descriptions. | 3 / 3 |
Workflow Clarity | The core workflow is a single command invocation which is clear, but the 'What the Script Does' section describes internal steps without explicit user validation checkpoints. The prerequisites verification is listed but not integrated into the workflow as a pre-check step. There's no explicit feedback loop for handling failures during generation. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections progressing from core usage to advanced options. Troubleshooting and setup details are appropriately delegated to 'references/setup_and_troubleshooting.md' with clear signaling, maintaining one-level-deep references. | 3 / 3 |
Total | 10 / 12 Passed |