mermaid
Mermaid diagram generation for inline markdown documentation: flowcharts, sequence diagrams, Gantt charts, class diagrams, state diagrams, ER diagrams, and architecture visualizations. USE FOR: inline markdown diagrams, flowcharts, sequence diagrams, Gantt charts, state diagrams, ER diagrams, Azure resource visualization. DO NOT USE FOR: architecture diagrams with Azure icons (use drawio), WAF/cost charts (use python-diagrams), Draw.io diagrams (use drawio).
86
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that covers all key dimensions well. It lists specific diagram types, includes natural trigger terms, explicitly states both when to use and when not to use the skill, and clearly distinguishes itself from related skills (drawio, python-diagrams). The 'DO NOT USE FOR' section is a particularly strong feature for reducing conflict risk in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and diagram types: flowcharts, sequence diagrams, Gantt charts, class diagrams, state diagrams, ER diagrams, and architecture visualizations. Very detailed about what it produces. | 3 / 3 |
Completeness | Clearly answers both 'what' (Mermaid diagram generation for various diagram types) and 'when' (explicit 'USE FOR' and 'DO NOT USE FOR' clauses with specific triggers). The negative triggers further strengthen the 'when' guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'flowcharts', 'sequence diagrams', 'Gantt charts', 'ER diagrams', 'state diagrams', 'mermaid', 'inline markdown diagrams', 'Azure resource visualization'. These are all terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via 'DO NOT USE FOR' clauses that differentiate it from drawio and python-diagrams skills. The 'inline markdown' and 'Mermaid' framing clearly carves out a unique niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid reference skill with excellent actionability — every diagram type has a complete, executable example. The main weaknesses are moderate verbosity (some redundant scope/boundary statements across multiple sections) and a missing validation workflow for checking diagram syntax before committing. The structure is good but could benefit from splitting detailed theming/styling into a separate reference file.
Suggestions
Add a concrete validation step or command for checking Mermaid syntax (e.g., using mmdc CLI or a preview method) to replace the vague 'validate syntax before committing' guideline.
Consolidate the scope boundaries — the 'When to Use', 'Guardrails DON'T', and 'Scope Exclusions' sections overlap significantly and could be merged into a single concise section.
Consider moving the theming and node styling sections into a separate MERMAID-STYLING.md reference file to keep the main skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of code examples, but includes some unnecessary content like the 'When to Use Mermaid' bullet list that largely restates what Claude already knows, and the scope exclusions section repeats boundaries already stated in the guardrails. The Azure resource visualization section could be trimmed since it mostly defers to another skill. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready Mermaid code blocks for every diagram type (flowcharts, sequence, Gantt, state, ER). Includes concrete theming configuration, classDef styling syntax, and specific directives like `graph TB` vs `graph LR`. Every section has working examples. | 3 / 3 |
Workflow Clarity | This is primarily a reference/syntax skill rather than a multi-step workflow, but the guardrails mention 'validate syntax before committing' without providing any concrete validation step or command. For a skill that involves generating diagrams that could fail to render, a validation checkpoint (e.g., how to test rendering) would improve this. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and sections, and references other skills (drawio, azure-resource-visualizer, python-diagrams) appropriately. However, the theming and node styling sections add significant inline content that could be split into a reference file, and the document is fairly long for a SKILL.md overview. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.