python-diagrams
**UTILITY SKILL** — Python diagram generation: WAF/cost/compliance charts (matplotlib), architecture diagrams (diagrams lib), ERDs, swimlanes, timelines, wireframes (graphviz). WHEN: 'WAF bar chart', 'cost donut chart', 'compliance gap chart', 'Python architecture diagram', 'ERD diagram', 'swimlane', 'UI wireframe'. DO NOT USE FOR: Draw.io architecture diagrams (drawio), inline Mermaid (mermaid).
66
78%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/python-diagrams/SKILL.mdQuality
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 hits all the marks. It provides specific capabilities with named libraries, includes natural trigger terms users would actually say, explicitly defines both when to use and when NOT to use the skill, and clearly distinguishes itself from related diagram skills (drawio, mermaid). The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and outputs: WAF/cost/compliance charts with matplotlib, architecture diagrams with diagrams lib, ERDs, swimlanes, timelines, wireframes with graphviz. Very detailed about both the diagram types and the libraries used. | 3 / 3 |
Completeness | Clearly answers both 'what' (Python diagram generation with specific chart types and libraries) and 'when' (explicit WHEN clause with trigger phrases). Also includes a 'DO NOT USE FOR' clause that further clarifies boundaries, which is excellent for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'WAF bar chart', 'cost donut chart', 'compliance gap chart', 'Python architecture diagram', 'ERD diagram', 'swimlane', 'UI wireframe'. These are specific phrases a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via the 'DO NOT USE FOR' clause distinguishing it from drawio and mermaid skills. The focus on Python-based diagram generation with specific libraries (matplotlib, diagrams, graphviz) creates a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%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 progressive disclosure and clear routing/scoping guidance. Its main weaknesses are the lack of inline executable code examples (always deferring to reference files) and the absence of validation/verification steps in the workflow. The content is moderately concise but has some redundancy across sections.
Suggestions
Add at least one minimal executable code example showing how to import and use save_figure from diagram_io.py to produce a PNG+SVG pair — this would significantly improve actionability.
Add a validation step after running the .py generator, e.g., 'Verify both .png and .svg files exist and are non-empty; if generation fails, check graphviz installation and font availability.'
Consolidate the repeated mentions of diagram_io.py requirements — it's stated in Execution & Output Standards, the Rules DO section, and implicitly in the routing table. One authoritative statement with a clear import template would be more token-efficient.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables, but some redundancy exists — the routing guide table and required outputs table overlap conceptually, and the DO/DON'T rules section repeats information already conveyed (e.g., the diagram_io requirement is stated three times). Some sections like 'Scope Exclusions' restate what's in the description. | 2 / 3 |
Actionability | Provides concrete library choices, file naming conventions, and clear DO/DON'T rules, but lacks any executable code examples. There's no sample Python script showing how to use save_figure or diagram_kwargs from diagram_io.py — the user is always redirected to reference files for actual implementation patterns. | 2 / 3 |
Workflow Clarity | The step numbering table (Steps 2, 3, 4, 7) implies a workflow sequence and the 'save .py then run python3' instruction is clear, but there are no explicit validation checkpoints — no step to verify the PNG/SVG were generated correctly, no error recovery guidance if diagram generation fails, and no feedback loop for checking output quality. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in SKILL.md and well-organized one-level-deep references via the Reference Index table. Each reference file is clearly labeled with its content scope, scripts are listed with purpose descriptions, and navigation is straightforward. | 3 / 3 |
Total | 9 / 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
05d7617
- 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.