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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The skill body is highly actionable with a well-structured, validated workflow, but it is a monolithic single file that bundles several large reference-style sections inline and carries some generally-known guidance that inflates its length.

Suggestions

Move the CVPR/ICLR academic style guide, color palette, and Architecture Diagram Best Practices into separate reference files referenced from the main body to reduce inline bulk and enable progressive disclosure.

Trim generally-known guidance (e.g., the full hex color palette and generic "What to AVOID" list) and the decorative banner dividers to tighten token efficiency.

Cut the first-person/second-person flavored filler and keep only Mermaid-specific syntax the model would not already reliably know.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete syntax guidance, but it includes content Claude largely already knows (academic color palettes with hex codes, generic "What to AVOID" lists, decorative banner dividers) that could be tightened, so it sits at 'mostly efficient but could be tightened' rather than fully lean.	2 / 3
Actionability	Provides fully executable commands (mkdir -p figures, mmdc -i ... -o ..., npx -y @mermaid-js/mermaid-cli@latest) and complete copy-paste-ready code examples for math and junction layouts, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Presents a clear six-step sequence with MANDATORY verification, an explicit fix->re-run feedback loop bounded by MAX_ITERATIONS, and a strict review checklist with pass/fail thresholds, matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	No bundle/reference files exist, so all content (math guide, academic style guide, architecture best practices) lives inline in a single monolithic file rather than being split into well-signaled one-level-deep references, sitting at 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

67%

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

The description is specific and clearly distinguishes the skill, but it omits an explicit "Use when..." trigger clause, leaving the activation context only implied and capping both completeness and trigger-term quality.

Suggestions

Add an explicit "Use when..." clause listing the natural request phrasings (e.g., "Use when the user asks for a Mermaid diagram, flowchart, sequence diagram, or wants to visualize a process or architecture").

Round out trigger-term coverage with common user phrasings like "diagram", "visualize", "flowchart", and "draw" so the skill matches natural requests.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions and outputs — "Generate Mermaid diagrams", "Save .mmd and .md files", "syntax verification" — and enumerates specific diagram types, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." or equivalent trigger guidance, so the "when" is only implied and completeness is capped at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Includes relevant natural terms users would say ("flowcharts", "sequence diagrams", "ER diagrams", "Gantt charts") but lacks the common request phrasings and has no explicit trigger clause, so coverage is incomplete rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	Targets a clear, distinct niche (Mermaid diagram generation with file output and verification) that is unlikely to overlap with or wrongly trigger other skills.	3 / 3
	Total	10 / 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: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: fe5963c

Reviewed: about 18 hours 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.