azure-adr
**ANALYSIS SKILL** — Creates Azure Architecture Decision Records (ADRs) with WAF pillar mapping, alternatives, and consequences. WHEN: "create ADR", "document decision", "architecture decision record", "record why we chose", "WAF pillar justification", "trade-off analysis". DO NOT USE FOR: IaC code (06b/06t agents), architecture diagrams (drawio), cost estimates (cost-estimate-subagent).
75
92%
Does it follow best practices?
Impact
—
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 hits all the marks. It provides specific capabilities, natural trigger terms, explicit when/when-not guidance, and clear differentiation from related skills. The 'DO NOT USE FOR' clause is a particularly strong addition that reduces conflict risk in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating ADRs, WAF pillar mapping, alternatives analysis, and consequences documentation. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates Azure ADRs with WAF pillar mapping, alternatives, consequences) and 'when' (explicit WHEN clause with trigger phrases). Also includes a 'DO NOT USE FOR' clause that further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create ADR', 'document decision', 'architecture decision record', 'record why we chose', 'WAF pillar justification', 'trade-off analysis'. These are realistic phrases a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Azure ADRs with WAF pillars) and explicitly delineates boundaries by listing what NOT to use it for (IaC code, architecture diagrams, cost estimates), minimizing conflict risk with other skills. | 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 efficiently communicates the ADR creation workflow with good progressive disclosure to reference files. Its main weakness is that actionability depends heavily on the referenced template and checklist files — without them, Claude would lack the concrete structure needed to produce a correctly formatted ADR. The naming conventions, phase determination logic, and rules are all clearly specified and token-efficient.
Suggestions
Consider inlining a minimal ADR skeleton (just section headers) in the SKILL.md so Claude can produce a basic ADR even if reference files fail to load.
Add a brief concrete example of a WAF pillar mapping (e.g., a 2-3 line table showing one decision's impact across pillars) to make step 5 more actionable without requiring the template file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. Every section serves a purpose — naming conventions, rules, steps, and reference index. No unnecessary explanations of what ADRs are or how Azure WAF works; it assumes Claude already knows these concepts. | 3 / 3 |
Actionability | The skill provides clear rules and a step sequence, but the actual executable content is deferred to reference files (adr-template.md, quality-checklist.md). Without those files available, Claude lacks the concrete template structure and checklist to produce a complete ADR. The naming convention table is concrete and actionable, but the core authoring guidance is indirect. | 2 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with logical ordering: gather context → determine number → determine phase → generate → WAF analysis → alternatives → self-check. The final self-check step against a quality checklist serves as an explicit validation checkpoint before saving. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference index table that signals exactly when to load each supporting file. References are one level deep, clearly labeled with their purpose, and the main SKILL.md stays concise as an overview. The 'Load on demand' pattern is well-suited for token efficiency. | 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
a0098f9
- 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.