mermaid-diagrams
Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.
93
92%
Does it follow best practices?
Impact
92%
1.33xAverage score across 3 eval scenarios
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 hits all the key criteria. It provides comprehensive specificity by listing numerous diagram types with their use cases, includes natural trigger terms users would actually say, explicitly addresses both 'what' and 'when' with clear trigger guidance, and maintains a distinct focus on Mermaid-based diagramming that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and diagram types: class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, pie charts, gantt charts, with specific use cases like 'domain modeling', 'API interactions', 'database schemas'. | 3 / 3 |
Completeness | Clearly answers both what (creating software diagrams using Mermaid syntax with specific diagram types) AND when (explicit 'Use when' clause with detailed triggers and a 'Triggers include' section listing specific user phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'diagram', 'visualize', 'model', 'map out', 'show the flow', plus domain-specific terms like 'system architecture', 'database design', 'code structure', 'application flows'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on Mermaid syntax diagrams with distinct triggers. The combination of 'Mermaid syntax' plus specific diagram types and visualization-focused trigger terms makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability through concrete, executable Mermaid examples and strong progressive disclosure via clearly organized reference links. The main weakness is some verbosity in sections like 'When to Create Diagrams' and 'Best Practices' that explain concepts Claude already understands, though the core technical content is appropriately lean.
Suggestions
Remove or significantly condense the 'When to Create Diagrams' section - Claude knows when diagrams are useful
Trim the 'Best Practices' section to only non-obvious guidance specific to Mermaid syntax quirks
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary explanation like the 'When to Create Diagrams' section which explains obvious use cases Claude already knows. The diagram type selection guide could be more condensed. | 2 / 3 |
Actionability | Provides fully executable Mermaid code examples for each diagram type that are copy-paste ready. Includes concrete CLI commands for exporting and specific configuration syntax. | 3 / 3 |
Workflow Clarity | For a reference/syntax skill, the workflow is appropriately simple. The 'Start Simple' best practice and clear diagram type selection guide provide adequate sequencing for the non-destructive task of creating diagrams. | 3 / 3 |
Progressive Disclosure | Excellent structure with quick start examples in the main file and clear one-level-deep references to detailed guides for each diagram type. Navigation is well-signaled with descriptive links. | 3 / 3 |
Total | 11 / 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
- softaworks/agent-toolkit
- Commit
3027f20
- 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.