Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs.
.claude/skills/microsoft-code-reference/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
| case-15 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
| Need | Tool | Example | |------|------|---------| | API method/class lookup | microsoft_docs_search | "BlobClient UploadAsync Azure.Storage.Blobs" | | Working code sample | microsoft_code_sample_search | query: "upload blob managed identity", language: "python" | | Full API reference | microsoft_docs_fetch | Fetch URL from microsoft_docs_search (for overloads, full signatures) |
Use microsoft_code_sample_search to get official, working examples:
microsoft_code_sample_search(query: "upload file to blob storage", language: "csharp")
microsoft_code_sample_search(query: "authenticate with managed identity", language: "python")
microsoft_code_sample_search(query: "send message service bus", language: "javascript")When to use:
# Verify method exists (include namespace for precision)
"BlobClient UploadAsync Azure.Storage.Blobs"
"GraphServiceClient Users Microsoft.Graph"
# Find class/interface
"DefaultAzureCredential class Azure.Identity"
# Find correct package
"Azure Blob Storage NuGet package"
"azure-storage-blob pip package"Fetch full page when method has multiple overloads or you need complete parameter details.
Use microsoft_code_sample_search to find working code samples and compare with your implementation. For specific errors, use microsoft_docs_search and microsoft_docs_fetch:
| Error Type | Query | |------------|-------| | Method not found | "[ClassName] methods [Namespace]" | | Type not found | "[TypeName] NuGet package namespace" | | Wrong signature | "[ClassName] [MethodName] overloads" → fetch full page | | Deprecated warning | "[OldType] migration v12" | | Auth failure | "DefaultAzureCredential troubleshooting" | | 403 Forbidden | "[ServiceName] RBAC permissions" |
Always verify when:
UploadFile vs actual Upload)CloudBlobClient vs v12 BlobServiceClient)Azure.* for .NET, azure-* for Python)Before generating code using Microsoft SDKs, verify it's correct:
microsoft_docs_search(query: "[ClassName] [MethodName] [Namespace]")microsoft_docs_fetch(url: "...")microsoft_code_sample_search(query: "[task]", language: "[lang]")For simple lookups, step 1 alone may suffice. For complex API usage, complete all three steps.
If the Learn MCP server is not available, use the mslearn CLI from a terminal or shell (for example, Bash, PowerShell, or cmd) instead:
sh# Run directly (no install needed) npx @microsoft/learn-cli search "BlobClient UploadAsync Azure.Storage.Blobs" # Or install globally, then run npm install -g @microsoft/learn-cli mslearn search "BlobClient UploadAsync Azure.Storage.Blobs"
| MCP Tool | CLI Command | |----------|-------------| | microsoft_docs_search(query: "...") | mslearn search "..." | | microsoft_code_sample_search(query: "...", language: "...") | mslearn code-search "..." --language ... | | microsoft_docs_fetch(url: "...") | mslearn fetch "..." |
Pass --json to search or code-search to get raw JSON output for further processing.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 18 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +26 percentage points is the difference between those two pass rates over the 18 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.