Content
92%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.
A well-structured, dense workflow skill: lean body, explicit validation checkpoints and a feedback loop, and clean one-level-deep progressive disclosure. The only minor gap is reliance on MCP-loaded guidance rather than an inline copy-paste Mermaid example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes Claude's competence — no padding about what UML/ERD/flowchart are; rules are referenced by ID with only the essentials inline and the full ruleset deferred to a reference file. | 5 / 5 |
Actionability | Concrete, executable authoring guidance — exact node syntax, banned shapes, edge-label verb lists, layout coordinate math, widget attributes, and XML-escaping rules — but relies on MCP-loaded guidance for full Mermaid mechanics rather than providing a complete inline worked example. | 4 / 5 |
Workflow Clarity | Clearly sequenced seven-step workflow with explicit mandatory pre-compilation checks, a final shape audit, and a reflow feedback loop that iterates from the latest result_svg. | 5 / 5 |
Progressive Disclosure | SKILL.md is an overview pointing to one real, well-signaled reference file (references/diagramming-principles.md) one level deep, with the full R/H ruleset appropriately split out and external format guidance loaded on demand. | 5 / 5 |
Total | 19 / 20 Passed |