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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

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

A well-structured, token-efficient skill body with executable examples and clean progressive disclosure to verified reference files. The main gap is the absence of an explicit error-recovery loop for parse/render failures in the CLI workflow.

Suggestions

Add a short validate→fix→retry checkpoint to the CLI Usage section (e.g., 'If mmdc reports a parse error, fix the flagged line and re-run') to support the common render-failure path.

Replace the abstract '{diagram-type} / {diagram-content}' Quick Start template with a concrete minimal example, since the inline flowchart example already shows the real structure.

Dimension	Reasoning	Score
Conciseness	The body is lean: it avoids explaining what diagrams or Mermaid are, jumps to executable code and tight bullet rules, and every section earns its tokens — matching the 'lean and efficient' anchor.	3 / 3
Actionability	Provides copy-paste-ready executable examples — a full 'flowchart TD' block, frontmatter config, and concrete 'mmdc -i diagram.mmd -o diagram.svg' CLI commands with install and theming flags.	3 / 3
Workflow Clarity	The CLI section sequences install→convert and the Syntax Rules list preventive guidance, but there is no explicit validate→fix→retry feedback loop for the common parse/render failure mode, leaving a validation gap.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing one level deep to real, clearly-signaled reference files (diagram-types.md, cli-usage.md, integration.md, configuration.md, examples.md), each gated with 'Load only when...' guidance.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong, third-person description that states concrete capabilities, includes an explicit 'Use when' trigger with many natural diagram-type keywords, and occupies a clear niche. It does not over-claim or pad.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create diagrams and visualizations', 'CLI rendering to SVG/PNG/PDF', 'theming, and configuration' — matching the anchor for enumerating several specific capabilities.	3 / 3
Completeness	Explicitly answers both what ('Create diagrams and visualizations using Mermaid.js v11 syntax') and when ('Use when generating flowcharts...'), satisfying the explicit-trigger requirement for the top anchor.	3 / 3
Trigger Term Quality	Covers the natural terms users say when requesting diagrams — 'flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, Gantt charts, user journeys, timelines' — giving broad keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The Mermaid.js v11 niche with diagram-type triggers is clearly distinguishable from other skills and unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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: tslateman/duet
Commit: 436824a

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.