CtrlK
BlogDocsLog inGet started
Tessl Logo

drawio

Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

76%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 content is highly actionable with executable commands and a clear pipeline, and it uses remote references well to keep bulk syntax offloaded. Its weaknesses are mild command redundancy and an XML well-formedness validation step that is caution-based rather than an explicit validate-retry checkpoint.

Suggestions

Add an explicit XML validation checkpoint to the pipeline (e.g., a one-line 'Validate the .drawio XML is well-formed before exporting; if it errors, fix the XML and re-validate') to convert the caution into a real validate → fix → retry feedback loop and lift workflow clarity.

De-duplicate the convert/export commands that recur across the pipeline, CLI, and troubleshooting sections by defining each command once and cross-referencing it, trimming token cost.

Consider moving the detailed custom-layout JSON options and the WSL2 path-alternative lists into the remote XML reference to tighten the core body.

DimensionReasoningScore

Conciseness

The body is dense and operational — full of concrete draw.io CLI commands, flag tables, and OS-specific gotchas Claude would not already know — with only minor redundancy (the convert/export commands recur across the pipeline, CLI, and troubleshooting sections) and a few trimmable path-alternative lists, placing it just below the lean 5 anchor.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout (e.g. 'drawio -x -f xml -o diagram.drawio diagram.mmd', the node URL-generation one-liner, WSL2 .url workaround) with concrete worked examples covering the common cases (flowchart, ER, AWS architecture, url), matching the 5 anchor.

5 / 5

Workflow Clarity

The pipeline is clearly numbered (Author → .drawio → Deliver → Open) with a thorough troubleshooting error-recovery table, but the rubric caps XML/document-manipulation workflows at 3 when an explicit validate → fix → retry feedback loop is missing; XML well-formedness is only a caution ('Validate XML well-formedness before writing') with no concrete validation checkpoint or retry loop embedded in the workflow.

3 / 5

Progressive Disclosure

Good structure with clear section headers, internal anchor links, and two well-signaled one-level-deep remote references (mermaid-reference.md, xml-reference.md) that offload bulk syntax; the body stays fairly long because operational details (CLI flags, OS-specific commands, URL generation) are appropriately inline, so it sits just below the 5 anchor.

4 / 5

Total

16

/

20

Passed

Description

86%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.

The description is trigger-rich and highly distinct, with comprehensive natural keywords and an explicit 'use when' clause. Its main weakness is that the skill's actual capabilities are implied through trigger verbs rather than stated as explicit actions.

Suggestions

Lead with a short explicit capability statement (e.g., 'Generates draw.io diagrams as native .drawio files from Mermaid or XML, with optional ELK layout, PNG/SVG/PDF export, and browser-URL output.') before the 'Use when...' trigger clause to make the 'what' as explicit as the 'when'.

DimensionReasoningScore

Specificity

Lists several concrete trigger verbs ('create, generate, draw, or design') plus a comprehensive set of diagram types and 'diagram export to PNG/SVG/PDF', but the skill's actual capabilities (generate .drawio files, convert Mermaid, build browser URLs) are implied through triggers rather than stated as explicit capability actions, leaving a minor coverage gap below the 5 anchor.

4 / 5

Completeness

An explicit and thorough 'Always use when...' clause answers 'when' with concrete trigger phrases, and 'what' is present but only implied via the create/generate/draw/design verbs and the export-to-PNG/SVG/PDF mention rather than as a standalone capability statement, so it falls short of the 5 anchor's 'clearly and explicitly answers both'.

4 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms ('drawio', 'drawoi'), the file extension ('.drawio files'), many concrete diagram types (flowchart, ER, sequence, class, network, mockup, wireframe, UI sketch), and export formats (PNG/SVG/PDF) — matching the 5 anchor that asks for synonyms and file extensions.

5 / 5

Distinctiveness Conflict Risk

A clear niche tied to the specific draw.io tool name, the 'drawoi' misspelling, and the '.drawio' file extension, with distinct diagram-type triggers, gives minimal overlap risk with other skills — matching the 5 anchor.

5 / 5

Total

18

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jgraph/drawio-mcp
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.