drawio

Generate draw.io diagrams programmatically using Python. Creates flowcharts, architecture diagrams, tree structures, network diagrams, and more. Use when the user requests a .drawio file, diagram, flowchart, or visual documentation.

3.17x

Quality

86%

Does it follow best practices?

Impact

89%

3.17x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

85%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.

Well-structured, executable content with strong progressive disclosure and a useful decision tree. Workflow clarity could improve with explicit validation steps for generated output.

Suggestions

Add a verification checkpoint after generation (e.g., confirm the .drawio is valid XML or can be reopened) to strengthen workflow_clarity.

Trim the duplicated inline-metadata explanation between the Quick Start prose and the second Python example to improve conciseness.

Document the expected input JSON schema for each helper script so the table entries are fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and a tight decision tree, but the Quick Start repeats the inline-metadata concept across prose and a second example, adding minor padding.	4 / 5
Actionability	Fully executable copy-paste code and concrete uv run commands cover the common cases (flowcharts, trees, from-data, custom drawpyo code).	5 / 5
Workflow Clarity	The decision tree gives a clear routing sequence to helper scripts or custom code, but generation workflows lack explicit validation/verification checkpoints (e.g., confirming the .drawio opens or output is well-formed).	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled one-level-deep references (references/REFERENCE.md, references/examples.md, scripts/) all verified present and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

88%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, specific description with explicit 'what' and 'when' clauses and concrete actions. Minor trigger-term synonym gaps prevent a perfect trigger_term_quality score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (generate flowcharts, architecture diagrams, tree structures, network diagrams) with comprehensive coverage of the diagram-generation domain.	5 / 5
Completeness	Explicitly answers both 'what' (generate draw.io diagrams programmatically using Python) and 'when' ('Use when the user requests a .drawio file, diagram, flowchart, or visual documentation').	5 / 5
Trigger Term Quality	Covers natural user terms (diagram, flowchart, visual documentation, .drawio file) but misses common synonyms like 'org chart' or 'architecture diagram' as standalone triggers.	4 / 5
Distinctiveness Conflict Risk	A clear niche (draw.io file generation via Python/drawpyo) with distinct trigger phrases unlikely to conflict with other skills.	5 / 5
	Total	19 / 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: fpl9000/ai-skills
Path: drawio/SKILL.md
Commit: 46b1ac6

Reviewed: 10 days 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.