CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/mermaid-diagrams/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured overview: a diagram-type selection guide, four executable quick-start examples, verified one-level-deep references, and useful pitfalls. It is held back by generic best-practices padding, missing examples or references for several advertised diagram types, and a duplicated configuration section.

Suggestions

Trim or move the "Best Practices" and "When to Create Diagrams" sections, which restate generic guidance Claude already knows, to improve token efficiency.

Add inline mini-examples or dedicated reference files for state diagrams, git graphs, gantt, and pie/bar charts, which are listed in the selection guide but never demonstrated.

Move the "Configuration and Theming" details fully into references/advanced-features.md to remove duplication with the advertised reference, keeping only a one-line pointer.

DimensionReasoningScore

Conciseness

Core sections (type selection guide, quick-start examples, pitfalls like "Unknown words break diagrams; parameters fail silently") earn their tokens, but "Best Practices" ("Use Meaningful Names - Clear labels make diagrams self-documenting"), "When to Create Diagrams" ("Always diagram when starting new projects"), and "Core Syntax Structure" restate generic guidance Claude already knows, fitting 'mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

Complete, executable mermaid examples for class, sequence, flowchart, and ERD diagrams plus concrete export commands ("mmdc -i input.mmd -o output.png", the docker invocation) make the guidance mostly copy-paste ready; however state diagrams, git graphs, gantt, and pie charts appear in the selection guide with neither an inline example nor a referenced deep-dive file, leaving minor gaps.

4 / 5

Workflow Clarity

The path (type selection guide -> quick-start example -> per-type reference -> pitfalls) is a clear sequence, and validation is mentioned ("validate syntax in Mermaid Live"), but validation appears only as pitfall advice rather than an explicit step in the creation workflow, fitting 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

"Detailed References" cleanly signals seven one-level-deep, annotated reference files that all exist in the bundle, but the inline "Configuration and Theming" section duplicates what references/advanced-features.md is advertised to cover ("Themes, styling, configuration, layout options"), and the Best Practices / When to Create Diagrams sections add bulk that belongs deeper or nowhere, fitting 'good structure; minor organization gaps'.

4 / 5

Total

15

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities with comprehensive diagram-type coverage and provides explicit, double-stated trigger guidance. Its only weaknesses are slightly broad trigger words ("visualize", "model") that overlap charting/visualization skills and a few missing natural synonyms.

Suggestions

Add commonly used synonyms and file extensions as triggers (e.g., "draw", "architecture diagram", ".mmd", "mermaid") to strengthen trigger term coverage.

Narrow broad triggers like "visualize" and "model" to diagram-specific contexts to reduce overlap with charting/data-visualization skills.

DimensionReasoningScore

Specificity

"creating software diagrams using Mermaid syntax" plus an enumerated list covering class, sequence, flowchart, ERD, C4, state, git graph, pie, and gantt diagrams gives multiple concrete actions with comprehensive coverage of the domain, matching the top anchor rather than the 'minor gaps' anchor below it.

5 / 5

Completeness

It explicitly answers what ("creating software diagrams using Mermaid syntax" with concrete diagram types and use-case parentheticals) and when ("Use when users need to create, visualize, or document software through diagrams" plus a second explicit "Triggers include..." clause), matching the anchor for clear what AND when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("diagram", "visualize", "model", "map out", "show the flow") plus contextual keywords like "system architecture, database design, code structure", but a few natural variations users would say ("draw", "chart", ".mmd", "mermaid" itself) are missing, which fits the 'good coverage, a few natural terms missing' anchor rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The diagramming niche is mostly distinct ("diagram" is the core trigger), but broad triggers like "visualize" and "model" plus pie/gantt charts create minor overlap risk with charting/data-visualization skills, fitting 'mostly distinct; minor overlap risk' rather than 'clear niche with minimal conflict risk'.

4 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
shep-ai/shep
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.