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.
93
92%
Does it follow best practices?
Impact
89%
3.17xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (generates draw.io diagrams using Python across multiple diagram types), when to use it (explicit trigger clause with natural user terms), and is distinctive enough to avoid conflicts with other skills. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate draw.io diagrams programmatically using Python', 'Creates flowcharts, architecture diagrams, tree structures, network diagrams'. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate draw.io diagrams programmatically using Python, creates flowcharts/architecture diagrams/tree structures/network diagrams) and 'when' (explicit 'Use when the user requests a .drawio file, diagram, flowchart, or visual documentation'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: '.drawio file', 'diagram', 'flowchart', 'visual documentation', 'architecture diagrams', 'network diagrams'. Good coverage of terms a user would naturally use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: draw.io format, Python-based generation, specific diagram types. The '.drawio file' trigger is very specific and unlikely to conflict with other skills. 'Diagram' and 'flowchart' could overlap slightly with other visualization tools, but the draw.io specificity anchors it well. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides clear, actionable guidance for generating draw.io diagrams. The decision tree is an excellent navigation aid, and the code examples are executable and complete. Minor verbosity in the overview and setup sections prevents a perfect conciseness score, but overall this is a strong skill body.
Suggestions
Trim the overview section — Claude doesn't need to know what apps can open .drawio files. Remove or condense the explanation of PEP 723 inline metadata and uv run behavior to a single line.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some unnecessary explanation (e.g., explaining what draw.io files can be opened in, the 'For custom code, you can also use uv run with inline dependencies' preamble). The PEP 723 mention and uv explanation could be tighter. The shape libraries section is borderline — useful reference but somewhat lengthy. | 2 / 3 |
Actionability | Provides fully executable Python code with copy-paste ready examples, concrete CLI commands for helper scripts, specific library/shape names, and clear parameter usage. The quick start example is immediately runnable. | 3 / 3 |
Workflow Clarity | The decision tree provides an excellent workflow for choosing the right approach. For a diagram generation skill, the workflow is clear: determine diagram type → use appropriate script/code → save to output path → present to user. No destructive operations requiring validation checkpoints. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, quick start, decision tree for navigation, key concepts inline, and clear one-level-deep references to REFERENCE.md, examples.md, and helper scripts. Content is appropriately split between the skill file and reference materials. | 3 / 3 |
Total | 11 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- fpl9000/ai-skills
- Commit
3d82fcd
- 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.