microsoft-docs
**ANALYSIS SKILL** — Query official Microsoft documentation to understand concepts, find tutorials, and learn how services work. WHEN: "Microsoft Learn", "Azure docs", "quickstart guide", "limits and quotas", "WAF reference", "architecture pattern docs". DO NOT USE FOR: Azure pricing (use azure-pricing MCP).
74
91%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-structured skill description with strong trigger terms, clear scope boundaries, and an explicit 'DO NOT USE FOR' clause that helps disambiguate from related skills. The main weakness is that the capability actions are somewhat generic ('understand concepts', 'find tutorials') rather than listing highly specific concrete operations. Overall, it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions such as 'retrieve API references', 'find service limits tables', 'locate architecture diagrams', or 'extract code samples from quickstarts' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Microsoft documentation) and some actions ('query official Microsoft documentation', 'understand concepts', 'find tutorials', 'learn how services work'), but the actions are somewhat generic and not highly concrete — e.g., it doesn't specify extracting code samples, comparing service features, or summarizing architecture patterns. | 2 / 3 |
Completeness | Clearly answers both 'what' (query official Microsoft documentation to understand concepts, find tutorials, learn how services work) and 'when' (explicit WHEN clause with trigger terms), plus includes a helpful 'DO NOT USE FOR' exclusion clause that further clarifies scope. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'Microsoft Learn', 'Azure docs', 'quickstart guide', 'limits and quotas', 'WAF reference', 'architecture pattern docs'. These are specific phrases a user would naturally use when seeking documentation help. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Microsoft/Azure documentation queries with distinct triggers like 'Microsoft Learn', 'Azure docs', 'WAF reference'. The explicit exclusion of Azure pricing with a redirect to another skill further reduces conflict risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
92%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-crafted skill that efficiently teaches Claude how to query Microsoft documentation through the Azure MCP server. It excels in conciseness, actionability, and workflow clarity with clear decision points and concrete tool invocations. The only minor weakness is that all content is inline with no progressive disclosure to supporting files, though for a skill of this size it's a minor concern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Microsoft Learn is or how MCP servers work conceptually. Every section delivers actionable information without padding. The table format for commands and CLI equivalents is token-efficient. | 3 / 3 |
Actionability | Provides concrete tool invocations with exact command values, a JSONC example showing the MCP call structure, CLI fallback commands, and a clear mapping table between MCP and CLI equivalents. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The Steps section provides a clear 6-step sequence with explicit decision points (step 3: 'if they cover the question, stop'; step 4: 'only when the excerpt is cut off'). The 'search first, fetch second' rule reinforces the workflow. For a non-destructive read-only documentation query skill, this level of validation is appropriate. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections (Tools, Rules, Steps, CLI Alternative), but everything is inline in a single file. For a skill of this complexity (~70 lines), this is borderline acceptable, but the CLI fallback section and mapping table could potentially be split out. No bundle files are provided, and no external references are made. | 2 / 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
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.