drawio
Use this skill to generate Azure architecture diagrams in .drawio format via the simonkurtz-MSFT MCP server (700+ Azure icons, batch creation, transactional mode). Covers architecture diagrams, dependency diagrams, runtime flow diagrams, and as-built diagrams. Do NOT use for WAF/cost charts (use python-diagrams), inline Mermaid (use mermaid), or Excalidraw diagrams (use excalidraw).
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 an excellent skill description that clearly defines its scope (Azure architecture diagrams in .drawio format), lists specific diagram types it covers, and explicitly delineates boundaries with competing skills through negative routing. The inclusion of both positive triggers and explicit 'Do NOT use' clauses makes it highly effective for skill selection among many options. Minor note: it uses second person 'Use this skill' but this is a common pattern in trigger guidance rather than capability description, so the impact is minimal.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate Azure architecture diagrams in .drawio format, mentions 700+ Azure icons, batch creation, transactional mode, and enumerates specific diagram types (architecture, dependency, runtime flow, as-built). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate Azure architecture diagrams in .drawio format with specific capabilities) and 'when' (explicit 'Use this skill to...' clause plus clear 'Do NOT use for...' negative boundaries directing to alternative skills). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'Azure architecture diagrams', '.drawio', 'dependency diagrams', 'runtime flow diagrams', 'as-built diagrams', and the MCP server name. Also includes negative triggers (WAF/cost charts, Mermaid, Excalidraw) which help with routing. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit negative routing ('Do NOT use for WAF/cost charts, inline Mermaid, or Excalidraw') that directly names competing skills, making it very unlikely to conflict. The Azure + .drawio niche is clearly carved out. | 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 strong, well-structured skill that provides highly actionable guidance for generating Azure architecture diagrams via the Draw.io MCP server. The workflows are clearly sequenced with validation checkpoints, and the reference index provides excellent progressive disclosure. The main weakness is some redundancy between the detailed sections and the Gotchas summary, which could be tightened to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is largely efficient and avoids explaining basic concepts Claude knows, but there is some repetition — the 'Gotchas' section restates rules already covered in earlier sections (batch-only, text:"", transactional finish-diagram, no anchors/waypoints). The layout conventions section is very detailed but most of it is project-specific knowledge Claude wouldn't have, so it earns its place. Overall mostly efficient with some tightening possible. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (bash scripts for saving/validating), specific tool call sequences, exact pixel values for layout, specific style strings, and clear examples of shape names and parameters. The workflows are copy-paste ready with specific tool names and parameter patterns. | 3 / 3 |
Workflow Clarity | Both transactional and non-transactional workflows are clearly sequenced with explicit steps. The batch-only workflow has numbered steps with validation (validate-group-containment, validate-drawio-files.mjs). Critical checkpoints are marked (MUST call finish-diagram, post-save cleanup). Error recovery is addressed (fix and re-validate pattern). | 3 / 3 |
Progressive Disclosure | The skill serves as a clear overview with well-organized sections and a reference index table pointing to one-level-deep files (style-reference.md, azure-patterns.md, validation-checklist.md, etc.). Quality reference examples are listed separately. The MCP server's own instructions are noted as automatically provided, avoiding duplication. | 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
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- 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.