mermaid-studio
Expert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document system flows, model databases, draw AWS infrastructure, analyze code structure, or anything involving "mermaid", "diagram", "flowchart", "architecture diagram", "sequence diagram", "ERD", "C4", "ASCII diagram". Do NOT use for non-Mermaid image generation, data plotting with chart libraries, or general documentation writing.
94
92%
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 marks. It provides comprehensive specificity with concrete actions and diagram types, includes abundant natural trigger terms, explicitly addresses both what and when, and clearly delineates its boundaries with a 'Do NOT use' clause. The only minor concern is that it's quite verbose, but the density of useful information justifies the length.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creation, validation, rendering, dual-engine output (SVG/PNG/ASCII), code-to-diagram analysis, batch rendering, syntax validation. Also enumerates 12+ specific diagram types by name. | 3 / 3 |
Completeness | Clearly answers both 'what' (Mermaid diagram creation, validation, rendering with specific capabilities) and 'when' (explicit 'Use when...' clause with detailed trigger scenarios). Also includes a 'Do NOT use' clause which further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'mermaid', 'diagram', 'flowchart', 'architecture diagram', 'sequence diagram', 'ERD', 'C4', 'ASCII diagram', 'render mermaid files', 'visualize architecture', 'AWS infrastructure'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around Mermaid diagrams specifically. The 'Do NOT use' clause explicitly excludes non-Mermaid image generation, chart libraries, and general documentation, reducing conflict risk with adjacent 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 high-quality, comprehensive skill with excellent actionability and workflow structure. It provides concrete, executable examples, clear multi-step workflows with validation checkpoints, and well-organized progressive disclosure to reference files. The main weakness is verbosity — the inline content is substantial and some sections (Golden Rules explanations, C4 color tables) could be tightened or moved to reference files to reduce token consumption.
Suggestions
Move the C4 Mandatory Styling Guide section (color values table, layout tips) to the existing references/c4-architecture.md to reduce main file length and improve conciseness.
Tighten the Golden Rules section by removing explanatory phrases like 'The single biggest visual improvement is...' and 'They are not optional — they define the difference between...' — Claude doesn't need motivational framing.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300+ lines) with substantial inline content that could be offloaded to reference files. The color tables, theme lists, and extensive C4 styling section add bulk. However, most content is genuinely instructional rather than explaining things Claude already knows. The Golden Rules section, while useful, is verbose with explanations like 'The single biggest visual improvement is...' that could be tightened. | 2 / 3 |
Actionability | Excellent actionability throughout — concrete executable commands for validation, rendering, and batch processing. Complete Mermaid code examples with copy-paste ready init directives, specific color hex values, exact CLI flags, and real script paths using $SKILL_DIR. The decision matrix maps user intent directly to diagram syntax keywords. | 3 / 3 |
Workflow Clarity | Clear 5-step workflow (Understand → Create → Validate → Render → Code-to-Diagram) with explicit validation checkpoint in Step 3 before rendering. Includes a feedback loop (validate → read error → consult troubleshooting → fix → re-validate, max 3 attempts). Setup is clearly marked as first-run-only. The modes of operation table cleanly separates different execution paths. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to 6 specific reference files (c4-architecture.md, aws-architecture.md, code-to-diagram.md, themes.md, troubleshooting.md, diagram-types.md). Each reference is mentioned at the exact point where it's needed with clear 'Read X BEFORE doing Y' instructions. | 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
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.