mermaid-diagram
Generate Mermaid diagrams from user requirements. Save .mmd and .md files to figures/ with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and many more diagram types.
69
61%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex/mermaid-diagram/SKILL.mdQuality
Discovery
82%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 a strong description with excellent specificity and trigger term coverage, clearly enumerating supported diagram types and concrete actions like file saving and syntax verification. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill over others.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks to create diagrams, visualize workflows, generate Mermaid syntax, or needs flowcharts, sequence diagrams, or other visual representations.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate Mermaid diagrams', 'Save .mmd and .md files to figures/', 'syntax verification', and enumerates specific diagram types (flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts). | 3 / 3 |
Completeness | Clearly answers 'what does this do' (generate Mermaid diagrams, save files, verify syntax, supports multiple diagram types), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Mermaid', 'diagrams', 'flowcharts', 'sequence diagrams', 'class diagrams', 'ER diagrams', 'Gantt charts', '.mmd'. These cover the main terms a user would naturally use when requesting diagram generation. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: Mermaid diagram generation with specific file formats (.mmd, .md) and output directory (figures/). The mention of Mermaid specifically and the enumerated diagram types make it unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent workflow clarity with well-defined steps, validation checkpoints, and feedback loops for error recovery. However, it is severely bloated — inlining extensive reference material (KaTeX syntax tables, academic color palettes, diagram type catalogs, architecture layout tips) that should be in separate files or omitted entirely since Claude already knows most of this. The lack of progressive disclosure and excessive verbosity significantly undermine its effectiveness as a skill file.
Suggestions
Extract the KaTeX math reference, academic style guide, architecture best practices, and diagram type table into separate reference files (e.g., MATH.md, ACADEMIC-STYLE.md, ARCHITECTURE.md) and link to them from the main skill.
Remove or drastically condense the diagram type table — Claude already knows Mermaid diagram types. A single sentence like 'Select the most appropriate Mermaid diagram type for the request' suffices.
Add a complete end-to-end example showing the actual content of a generated .mmd file and .md file for a simple diagram, rather than just describing the format.
Simplify the visual review section — the elaborate scoring rubric with ASCII borders and detailed score breakdown could be reduced to a concise checklist of 5-6 critical verification items.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It includes extensive sections Claude already knows (diagram type tables, KaTeX syntax references, academic style guides with hex color codes, common math patterns). The visual review scoring rubric with ASCII art borders and detailed score breakdown is unnecessarily elaborate. Much of this could be condensed or moved to reference files. | 1 / 3 |
Actionability | The workflow steps are concrete with bash commands for directory creation and mmdc verification, and file naming conventions are clear. However, the actual Mermaid code generation step lacks executable templates — it says 'generate the Mermaid code' without showing a complete end-to-end example of what the .mmd and .md files should look like. The verification script uses placeholder `<diagram-name>` rather than showing variable substitution. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 0-6) with explicit validation checkpoints: Step 4 mandates mmdc verification with a retry loop up to MAX_ITERATIONS, and Step 5 provides a detailed review checklist with pass/fail criteria and a fix-then-re-review feedback loop. Error recovery is well-defined. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The KaTeX math reference table, academic style guide with color palettes, architecture diagram best practices, and the full diagram type table are all inlined when they should be split into separate reference files. The skill would benefit enormously from a concise overview pointing to detailed docs. | 1 / 3 |
Total | 7 / 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.
- Commit
700fbe2
- 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.