Tessl • The management layer for AI agent skills

SkillPublic

mermaid-expert

Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/mermaid-expert/SKILL.md

The canonical home for this skill is mermaid-expert in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

42%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 well-organized and brief, but it reads as a template skeleton rather than expert guidance: no actual Mermaid syntax examples, generic instruction filler, and a dangling reference to a nonexistent playbook file. Claude would learn almost nothing domain-specific from loading it.

Suggestions

Add one or two complete, copy-paste-ready Mermaid examples (e.g. a styled flowchart and a sequenceDiagram) so the skill delivers actual syntax expertise.

Fix or remove the broken `resources/implementation-playbook.md` reference — either create the file or drop the pointer.

Replace the generic "Clarify goals / Apply best practices" filler with domain-specific guidance such as common Mermaid syntax pitfalls and a concrete validation step (render with `mmdc` or the Mermaid Live Editor before delivering).

Cut the circular "Use this skill when / Do not use" boilerplate that restates the skill name without adding trigger information.

Dimension	Reasoning	Score
Conciseness	The body is short and sectioned, but the circular boilerplate ("Working on mermaid expert tasks or workflows", "The task is unrelated to mermaid expert") and generic filler ("Clarify goals, constraints, and required inputs", "Apply relevant best practices") are unnecessary padding that could be trimmed.	3 / 5
Actionability	No executable Mermaid syntax appears anywhere — the "Diagram Types Expertise" block is just a keyword list and the Approach steps are high-level hints ("Choose the right diagram type", "Use consistent styling and colors") without the specific steps or code a Mermaid skill needs.	2 / 5
Workflow Clarity	The Approach section lists a rough five-step sequence (choose type → readability → styling → labels → "Test rendering before delivery"), but validation is only a single vague mention with no concrete checkpoint (e.g. render via mermaid CLI or live editor) or error-recovery guidance.	3 / 5
Progressive Disclosure	Sections are clearly headed and the skill is short, but the sole external pointer — "If detailed examples are required, open `resources/implementation-playbook.md`" — targets a file that does not exist in the bundle, leaving the reference broken rather than well-signaled.	3 / 5
	Total	11 / 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 solid, specific description that names the domain and concrete diagram types, but it only answers "what" — it never says when Claude should reach for it. The trailing "Masters syntax for all diagram types" reads as a mild over-claim and could be replaced with a trigger clause.

Suggestions

Add an explicit 'Use when...' clause, e.g. "Use when the user mentions Mermaid, .mmd files, or needs flowcharts, sequence diagrams, ERDs, or architecture diagrams."

Replace the capability claim "Masters syntax for all diagram types and styling" with concrete actions (e.g. "write and debug Mermaid syntax, apply themes and class styles").

Include natural trigger synonyms and file extensions users actually say: "sequence diagram", "chart", "diagram", ".mmd", "mermaid.js".

Dimension	Reasoning	Score
Specificity	"Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures" names several concrete diagram categories, but "Masters syntax for all diagram types and styling" is a capability claim rather than an action, leaving minor coverage gaps.	4 / 5
Completeness	The "what" is clear (create Mermaid diagrams of listed types), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes good natural keywords users would say — "Mermaid diagrams", "flowcharts", "sequences", "ERDs", "architectures", "styling" — but misses common variations like "sequence diagram", "chart", "diagramming", or the ".mmd" file extension.	4 / 5
Distinctiveness Conflict Risk	Mermaid is a named tool with a clear niche and distinct triggers, but the broad "diagrams"/"architectures" framing has minor overlap risk with general charting or visualization skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/mermaid-expert/SKILL.md
Revision: 64adc55

Reviewed: 5 hours ago

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.

mermaid-expert

Table of Contents

Is this your skill?