draw-mermaid-diagrams

Draw and edit Mermaid diagrams in Markdown. Use when the user wants to visualize processes, flows or sequences, or asks for a diagram. Load it before writing any Mermaid block, even when you know the syntax — that is why it gets skipped.

Quality

80%

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 ./plugins/flowai-engineering/skills/draw-mermaid-diagrams/SKILL.md

Quality

Content

77%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.

A well-structured, action-oriented body with an excellent validation workflow and clean progressive disclosure. The main weakness is the measurement justification prose carrying date-sensitive detail that does not earn its tokens.

Suggestions

Move the dated measurement narrative ('Measured on 2026-08-30/31...', probe counts) into references/SPEC.md or trim it to a single clause, so SKILL.md stays lean and date-free.

Add one short 'good vs. broken' Mermaid example pair (e.g. a label with unquoted parentheses) so the hazard list and the validate loop have a concrete anchor.

Tighten the Overview from two paragraphs to one sentence stating the goal, since the rules and steps already convey the motivation.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and purposeful, but the measurement narrative ('Measured on 2026-08-30/31 over twelve agent-written diagrams', '43 synthetic probes') is time-sensitive justification prose that could be trimmed and is not placed in a deprecated section.	3 / 5
Actionability	Provides a concrete, copy-paste-ready command ('python3 scripts/validate.py path/to/diagram.md') with exit-code semantics and diagram-type selection, but includes no example Mermaid block showing correct vs. fixed output.	4 / 5
Workflow Clarity	A clear numbered sequence (pick type → read SPEC → write → run check → repair and re-check until clean) with an explicit validation checkpoint and a fix→re-run feedback loop, matching the anchor pattern exactly.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview that points one level deep to real, verified files (references/SPEC.md, scripts/validate.py), with both inline and Resources-section signaling for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

82%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 strong description that clearly states both capability and trigger conditions in concise third-person voice. The only real gap is action coverage beyond draw/edit.

Dimension	Reasoning	Score
Specificity	Names the domain ('Mermaid diagrams in Markdown') and two concrete actions ('Draw and edit'), but the action list is not comprehensive — only draw/edit, no layout, styling, or export actions.	3 / 5
Completeness	Explicitly answers both what ('Draw and edit Mermaid diagrams in Markdown') and when ('Use when the user wants to visualize processes, flows or sequences, or asks for a diagram') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-keyword coverage with 'visualize processes, flows or sequences', 'diagram', and 'Mermaid', but a few common terms users would say ('flowchart', 'chart') are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Mermaid diagrams) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	17 / 20 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: korchasa/flowai-plugins
Path: plugins/flowai-engineering/skills/draw-mermaid-diagrams/SKILL.md
Commit: ad81ae6

Reviewed: 7 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.