mermaid-diagram

Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/mermaid-diagram/SKILL.md

Quality

Content

62%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 workflow itself is excellent — a clearly sequenced, validated, feedback-looped process with highly concrete commands and code. The weaknesses are verbosity (redundant Key Rules, duplicated output sections, an inline type table Claude doesn't need) and a monolithic structure that inlines three specialized guides and references nonexistent syntax documentation.

Suggestions

Delete the "Key Rules (MUST FOLLOW)" section and the "Output Structure" section — both restate the Step 0–6 workflow — and trim the type/use-case table to the non-obvious types.

Move the Math/KaTeX guide, the CVPR/ICLR/NeurIPS style guide, and the architecture junction techniques into references/ files (e.g. references/math.md, references/academic-style.md) and link to them from one line each.

Fix the dangling pointer in Step 1: either ship actual per-type syntax reference files in references/ and point to them, or drop the instruction to "read the corresponding syntax reference documentation" since it resolves to nothing.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose with several padded sections: "Key Rules (MUST FOLLOW)" restates the workflow in 11 rules, "Output Structure" duplicates Step 3's file list, the 22-row type/use-case table covers knowledge Claude already has, and decorative "═══" separators pad the review template. Not a 1 because no space is wasted explaining basic concepts, and the KaTeX gotchas and junction techniques are genuinely non-obvious.	2 / 5
Actionability	Concrete and executable throughout: the mmdc verification command with an npx fallback, exact .mmd/.md file formats with examples, a kebab-case naming convention, and copy-paste KaTeX and junction snippets. Not a 5 because Step 1 instructs "Read the corresponding syntax reference documentation (see Diagram Type Reference below)" but no such syntax documentation exists — the table below lists use cases, not syntax.	4 / 5
Workflow Clarity	Steps 0–6 are clearly sequenced with an explicit validation checkpoint (mandatory mmdc render), a bounded feedback loop (fix, re-render, re-verify up to MAX_ITERATIONS = 3), and a strict per-arrow/per-block review checklist. This matches the top anchor: sequence, validation, error-recovery loops, and checklists are all present.	5 / 5
Progressive Disclosure	The body is well-sectioned with headers, but it is a 420-line single file with no bundle files at all, and content that clearly belongs in separate references (per-type syntax guides, the KaTeX/math guide, the academic style guide, architecture junction techniques) is fully inlined. The instruction to read "syntax reference documentation" points at files that do not exist, leaving navigation dangling.	3 / 5
	Total	14 / 20 Passed

Description

66%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 specific, well-scoped description with strong natural trigger terms and a clear niche, undermined by the complete absence of a "Use when..." trigger clause. Adding when-to-use guidance and a few synonyms/file extensions would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for a Mermaid diagram, a flowchart, a sequence diagram, or diagram-as-code output (.mmd files)."

Mention the concrete outputs the skill produces (files in figures/: .mmd, .md, .png) to distinguish it from generic charting/dataviz skills.

Include common synonyms and the .mmd extension so natural variations of the request ("draw a diagram", "architecture diagram", "diagram as code") match.

Dimension	Reasoning	Score
Specificity	"Generate Mermaid diagrams from user requirements" is a concrete action, and the enumeration of 23 diagram types ("flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more") gives broad, concrete coverage. Not a 5 because it lists only one action verb — no mention of the save/verify/file-output behavior the skill actually performs.	4 / 5
Completeness	The "what" is clear and enumerated (generate Mermaid diagrams of 23 types), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which the rubric says caps completeness at 3. The only implicit trigger is naming the diagram types themselves.	3 / 5
Trigger Term Quality	Contains natural phrases users would actually say: "Mermaid diagrams", "flowcharts", "sequence diagrams", "ER diagrams", "Gantt charts". Not a 5 because it omits synonyms (draw, chart, diagram alone) and the .mmd file extension that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	"Mermaid" names a clear niche with distinct triggers, so it is unlikely to fire for the wrong skill. Minor overlap risk remains with general charting/dataviz skills for terms like "pie chart", "timeline", and "Gantt chart", which are not Mermaid-specific.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/mermaid-diagram/SKILL.md
Commit: 2132036

Reviewed: 11 minutes 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.