microsoft-code-reference
Look up Microsoft API references, find working code samples, and verify SDK code is correct. USE FOR: Azure SDK method verification, .NET/Python package lookups, code sample discovery, error troubleshooting, catching hallucinated methods and deprecated patterns. DO NOT USE FOR: conceptual documentation (use microsoft-docs), skill creation (use microsoft-skill-creator), Bicep/Terraform module lookups (use azure-bicep-patterns or terraform-patterns).
97
96%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 concrete actions, rich natural trigger terms covering multiple technologies and use cases, explicit 'USE FOR' and 'DO NOT USE FOR' clauses that clearly delineate scope, and strong distinctiveness through named alternative skills for boundary cases.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Look up Microsoft API references', 'find working code samples', 'verify SDK code is correct', plus specific use cases like 'Azure SDK method verification', '.NET/Python package lookups', 'code sample discovery', 'error troubleshooting', 'catching hallucinated methods and deprecated patterns'. | 3 / 3 |
Completeness | Clearly answers both 'what' (look up API references, find code samples, verify SDK code) and 'when' (explicit 'USE FOR' clause with trigger scenarios, plus a 'DO NOT USE FOR' clause that further clarifies boundaries and redirects to alternative skills). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Azure SDK', '.NET', 'Python', 'package lookups', 'code sample', 'error troubleshooting', 'hallucinated methods', 'deprecated patterns', 'Microsoft API'. These are terms developers would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive with explicit boundary-setting via the 'DO NOT USE FOR' clause, which names specific alternative skills (microsoft-docs, microsoft-skill-creator, azure-bicep-patterns, terraform-patterns). This makes it very unlikely to conflict with related skills. | 3 / 3 |
Total | 12 / 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 high-quality skill that provides concrete, actionable guidance for verifying Microsoft SDK code against official documentation. It excels at conciseness and actionability with specific query patterns, tool mappings, and a clear validation workflow. The only minor weakness is that all content is inline rather than using progressive disclosure to separate the CLI fallback and detailed troubleshooting into referenced files, though the current length is borderline acceptable for a single file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It avoids explaining what Azure SDKs are or how package managers work, instead jumping straight into tool usage patterns and query examples. Every section earns its place with actionable reference material. | 3 / 3 |
Actionability | Provides concrete, copy-paste-ready tool invocations, specific query strings, CLI commands, and a clear mapping table between MCP tools and CLI alternatives. The error troubleshooting table gives specific query patterns for each error type. | 3 / 3 |
Workflow Clarity | The 'Validation Workflow' section provides a clear 3-step sequence with explicit guidance on when to stop early (simple lookups) vs. complete all steps (complex API usage). The 'When to Verify' section acts as a trigger checklist, and the error troubleshooting table provides clear recovery paths. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and tables, but everything is inline in a single file. For a skill of this length (~90 lines of content), some sections like the CLI alternative or the full error troubleshooting table could be split into referenced files. However, the organization within the single file is logical and navigable. | 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
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.