python-diagrams
Python diagram generation: WAF/cost/compliance charts (matplotlib), architecture diagrams (diagrams library), ERDs, swimlanes, timelines, wireframes (graphviz). USE FOR: WAF bar charts, cost donut/projection charts, compliance gap charts, Python architecture diagrams, ERD diagrams, business process flows, timeline/Gantt charts, UI wireframes. DO NOT USE FOR: Draw.io architecture diagrams (use drawio), inline Mermaid (use mermaid).
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 an excellent skill description that covers all key dimensions well. It provides specific capabilities with library names, comprehensive trigger terms covering many diagram types users would request, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly delineate scope, and strong distinctiveness through negative triggers differentiating it from related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and diagram types: WAF/cost/compliance charts with matplotlib, architecture diagrams with diagrams library, ERDs, swimlanes, timelines, wireframes with graphviz. Very detailed about what it produces. | 3 / 3 |
Completeness | Clearly answers both 'what' (Python diagram generation with specific libraries and diagram types) and 'when' (explicit 'USE FOR' clause listing trigger scenarios). Additionally includes 'DO NOT USE FOR' negative triggers which further clarifies when to select this skill vs alternatives. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'WAF bar charts', 'cost donut charts', 'compliance gap charts', 'architecture diagrams', 'ERD', 'swimlanes', 'timeline', 'Gantt charts', 'wireframes', 'Python'. These are terms users would naturally use when requesting these outputs. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via 'DO NOT USE FOR' clauses that differentiate it from drawio and mermaid skills. The Python-specific framing and enumeration of specific chart types (WAF, cost donut, compliance gap) create a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%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 with strong actionability and excellent progressive disclosure through its reference index. The routing table is particularly effective for directing Claude to the right library. The main weaknesses are the lack of validation/verification steps in the workflow (e.g., checking PNG output exists, handling missing dependencies) and some content that could be tightened, such as the scope exclusions section which largely restates the routing guide.
Suggestions
Add a validation step after PNG generation (e.g., verify file exists and has non-zero size) to create a feedback loop for error recovery
Remove or consolidate the 'Scope Exclusions' section since the routing guide and guardrails already communicate boundaries
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables and compact formatting, but includes some unnecessary sections like 'Scope Exclusions' that restate routing information, and the 'Required Outputs (Workflow Integration)' table assumes a specific workflow context that may not always apply. The design tokens and conventions are well-compressed. | 2 / 3 |
Actionability | Provides executable code examples for architecture diagrams, concrete bash commands for installation and execution, specific color hex codes, exact graph_attr/node_attr configurations, and clear routing guidance. The code snippets are copy-paste ready and the design tokens are immediately usable. | 3 / 3 |
Workflow Clarity | The execution workflow (save .py, run to produce .png) is clear but lacks validation checkpoints — there's no step to verify the PNG was generated correctly, no error handling guidance if graphviz isn't installed properly, and no feedback loop for fixing rendering issues. For a skill involving file generation and external tool execution, validation steps would be important. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a concise overview in the main file and a well-organized reference index table pointing to 12 specific reference files covering different diagram types and patterns. References are one level deep and clearly signaled with descriptive content summaries. | 3 / 3 |
Total | 10 / 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.