azure-diagrams
ROUTING SKILL — delegates to specialized diagram skills. USE FOR: any diagram request when the caller does not know which tool to use. Routes to drawio, python-diagrams, or mermaid based on diagram type.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
75%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 effectively communicates its role as a routing skill for diagram requests and clearly states when it should be used. Its main weakness is the lack of natural trigger terms that users would actually say (e.g., 'flowchart', 'UML', 'architecture diagram') and limited specificity about what types of diagrams map to which tools.
Suggestions
Add natural user-facing trigger terms like 'flowchart', 'sequence diagram', 'architecture diagram', 'UML', 'network diagram', 'chart', 'visualization' to improve matching on real user requests.
Briefly describe what types of diagrams route to which tool (e.g., 'Routes network/infrastructure diagrams to python-diagrams, flowcharts to mermaid, complex visual diagrams to drawio') to increase specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (diagrams) and the routing action, and lists the three target tools (drawio, python-diagrams, mermaid), but does not describe concrete actions beyond routing/delegating. | 2 / 3 |
Completeness | Clearly answers both what ('delegates to specialized diagram skills, routes to drawio/python-diagrams/mermaid') and when ('any diagram request when the caller does not know which tool to use'), with an explicit 'USE FOR' clause. | 3 / 3 |
Trigger Term Quality | Includes 'diagram request' and the tool names (drawio, python-diagrams, mermaid), but misses common natural user terms like 'flowchart', 'sequence diagram', 'architecture diagram', 'UML', 'chart', or 'visualization'. | 2 / 3 |
Distinctiveness Conflict Risk | The description clearly positions this as a routing/meta skill for diagrams, distinct from the individual diagram tools it delegates to, making it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent routing skill that is lean, well-structured, and highly actionable. The routing table is comprehensive and clearly maps diagram types to target skills with expected output formats. The 3-step workflow is appropriately simple for a delegation skill, and the progressive disclosure pattern of pointing to specialized skills is exactly right.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. The routing table is compact and informative, with no unnecessary explanation of what diagrams are or how routing works. The instruction to not load references directly is a useful, non-obvious constraint. | 3 / 3 |
Actionability | The routing table provides concrete, unambiguous mappings from diagram type to target skill and output format. The 3-step process is specific and tells Claude exactly what to do: identify type, read the target skill file at a specific path, follow that skill's workflow. | 3 / 3 |
Workflow Clarity | For a simple routing/delegation skill, the workflow is clear and unambiguous: identify → load target skill → follow its workflow. There are no destructive or batch operations requiring validation checkpoints, so the simple 3-step sequence is appropriate and complete. | 3 / 3 |
Progressive Disclosure | This is a textbook example of progressive disclosure for a routing skill. It provides a concise overview and explicitly delegates to one-level-deep specialized skill files via a clear path pattern. It even warns against loading its own references directly. | 3 / 3 |
Total | 12 / 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.