mermaid
Create diagrams and visualizations using Mermaid.js v11 syntax. Use when generating flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines, or any of 24+ diagram types. Supports CLI rendering to SVG/PNG/PDF, theming, and configuration. Essential for inline documentation diagrams that render natively on GitHub.
100
Quality
100%
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 hits all the key criteria. It provides specific capabilities (diagram types, output formats, theming), includes natural trigger terms users would actually say, explicitly states when to use it, and carves out a distinct niche around Mermaid.js diagramming. The description is concise yet comprehensive, using proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create diagrams and visualizations', 'CLI rendering to SVG/PNG/PDF', 'theming', 'configuration', and explicitly names 8+ diagram types (flowcharts, sequence diagrams, class diagrams, etc.). | 3 / 3 |
Completeness | Clearly answers both what ('Create diagrams and visualizations using Mermaid.js v11 syntax', 'CLI rendering', 'theming') AND when ('Use when generating flowcharts, sequence diagrams...', 'for inline documentation diagrams that render natively on GitHub'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'diagrams', 'visualizations', 'Mermaid', 'flowcharts', 'sequence diagrams', 'Gantt charts', 'timelines', 'GitHub', 'SVG', 'PNG', 'PDF'. These are terms users naturally use when requesting diagram creation. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche with distinct triggers: specifically targets Mermaid.js diagramming with explicit diagram types and output formats. The mention of 'Mermaid.js v11', specific diagram types, and GitHub rendering creates a unique fingerprint unlikely to conflict with other visualization or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill file that demonstrates excellent token efficiency while remaining highly actionable. It provides just enough context to get started with common diagram types, includes executable examples, and appropriately defers detailed syntax to reference files. The structure supports both quick usage and deep exploration.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what Mermaid is or how markdown works. Every section delivers actionable information without padding. The warning about loading reference files only when needed shows respect for token budget. | 3 / 3 |
Actionability | Provides fully executable code blocks for both inline markdown usage and CLI commands. The flowchart example is copy-paste ready, CLI commands include real flags and options, and syntax rules are specific and concrete. | 3 / 3 |
Workflow Clarity | For a skill focused on diagram creation (not a multi-step destructive operation), the workflow is clear: choose diagram type, use proper syntax, optionally configure theme, render via CLI if needed. The syntax rules section provides validation guidance to avoid parse errors. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview pointing to well-organized reference files. References are one level deep, clearly signaled with descriptive labels, and the Resources section provides easy navigation. The warning about loading references only when needed is a nice touch. | 3 / 3 |
Total | 12 / 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
- tslateman/duet
- Commit
96a72fa
- 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.