azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdk_analyze_pipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in CI", "analyze pipeline", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing, applying code fixes (instead use azsdk-common-pipeline-fixer). INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts, azure-sdk-mcp:azsdk_get_failed_test_run_data, azure-sdk-mcp:azsdk_get_failed_test_case_data, azure-sdk-mcp:azsdk_get_pr_checks, azure-sdk-mcp:azsdk_get_pipeline_status.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 6.1k
- Forks
- 5.2k
01 前言 Front Matter
- name
- azsdk-common-pipeline-analysis
- license
- MIT
- metadata
- { "version": "1.0.0", "distribution": "shared" }
- description
- Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdk_analyze_pipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in CI", "analyze pipeline", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing, applying code fixes (instead use azsdk-common-pipeline-fixer). INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts, azure-sdk-mcp:azsdk_get_failed_test_run_data, azure-sdk-mcp:azsdk_get_failed_test_case_data, azure-sdk-mcp:azsdk_get_pr_checks, azure-sdk-mcp:azsdk_get_pipeline_status.
- compatibility
- azure-sdk-mcp server, Azure DevOps pipeline build ID or GitHub PR link
02 资源文件 4
- 参考文档evals/trigger.eval.yaml4.0 KB
- 参考文档references/failure-patterns.md6.3 KB
- 参考文档references/output-format.md1.3 KB
- 参考文档testing-anti-patterns.md8.1 KB
03 SKILL.md 正文
Pipeline Analysis
This skill analyzes Azure SDK CI/CD pipeline failures and provides a structured diagnosis including root cause, affected files, and concrete instructions for how to fix each issue. It does NOT apply fixes - it tells you exactly what's wrong and how to resolve it.
Rules
- Load this skill before running
azsdk_analyze_pipeline— the tool returns raw failure data that this skill interprets and formats per output format. - Requires the
azure-sdk-mcpserver; without it, inspect logs in the Azure DevOps UI. - Analysis-only: never edit files or apply fixes — use
azsdk-common-pipeline-fixerfor changes. - Run
azsdk_analyze_pipelinefirst, then categorize each failure and cite specific files/lines. - For infrastructure failures (network timeouts, agent crashes, throttling), recommend retry, not code changes.
MCP Tools
| Tool | Purpose |
|---|---|
azure-sdk-mcp:azsdk_analyze_pipeline |
Analyze pipeline failure (logs + test results) |
azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts |
Download test result artifacts from pipeline |
azure-sdk-mcp:azsdk_get_failed_test_run_data |
Full details for every failure in one artifact file |
azure-sdk-mcp:azsdk_get_failed_test_case_data |
Full details for a single failing test in a file |
azure-sdk-mcp:azsdk_get_pr_checks |
Get pipeline/check results linked to a PR |
azure-sdk-mcp:azsdk_get_pipeline_status |
Get pipeline run status |
Steps
- Identify - Get the build ID, pipeline URL, or PR link (use the PR link when triggered from a PR comment).
- Analyze - Run
azsdk_analyze_pipeline. It returnsfailed_pipeline_tasks(log errors from failed steps) andfailed_pipeline_tests, a lightweight index of failed tests grouped by artifact file. Each entry hasartifact_file_path,platform, andfailed_test_titles— titles only, no error text, to keep the response small. - Fetch failure details - Fetch failure details lazily so you don't overload context: call
azsdk_get_failed_test_run_datawith the parameterfailedTestRunsPathset toartifact_file_pathonce per file to get every failure in it. Or callazsdk_get_failed_test_case_datawithfailedTestRunsPathset toartifact_file_pathandtestCaseTitleset to one exact title fromfailed_test_titles. Prefer the per-file call when triaging a whole file's failures. - Categorize each failure: test, build/compilation, validation/lint, or infrastructure.
- Diagnose - Give each failure's root cause and affected file(s)/line(s), and note if several share one root cause. See failure patterns.
- Report - Use the output format: root cause, affected files, per-failure fix + verify command, and fixable vs infrastructure. Recommend
azsdk-common-pipeline-fixerto apply fixes.
Examples
- "My pipeline build 6447834 failed, what went wrong?"
- PR comment:
@copilot Analyze the failed pipeline on this PR - "Why is my CI red? Build ID is 6455939"
Troubleshooting
- If
azsdk_analyze_pipelinereturns no data, verify the build ID is correct and the run has completed. - If
failed_pipeline_testsis empty, rely onfailed_pipeline_taskslog analysis (test-artifact upload may not be configured). - For a private/internal pipeline, the user may need to
az login. See failure patterns.
04 同仓库更多 Skills
update-chat-api
Use when: updating, exporting, refreshing, or validating the public API baseline for Azure.Messaging.WebPubSub.Chat after a public API change.
search-documents
E2E workflow skill for Azure.Search.Documents SDK (TypeSpec + heavy customization). Handles full release cycles and partial updates: SHA update; code generation; build; customization fixes; ServiceVersion sync; testing; API export; changelog; version; samples; formatting; release metadata. WHEN: create new package version for Azure.Search.Documents; regenerate Azure.Search.Documents; fix Azure.Search.Documents bug; release Azure.Search.Documents; update Azure.Search.Documents spec. Do not use for Azure.ResourceManager.Search or Azure.Provisioning.Search.
search-documents-version-diff
Diff the current Azure.Search.Documents public API surface against a previous published version and detect preview-to-preview regressions where the SDK customization layer was not bubbled up after a TypeSpec change. Use whenever the user asks to compare Azure.Search.Documents betas, verify no Azure.Search.Documents preview features dropped, regression audit between Azure.Search.Documents versions, sanity-check a release branch for Azure.Search.Documents, or investigate a missing Azure.Search.Documents preview feature — even if they don't say the word "diff". Specifically catches dropped wrappers (QueryAnswer/QueryCaption/QueryRewrites style), lost SearchOptions aggregator redirectors, `@@access("internal")` flips, deleted-instead-of-gated `#if AZURE_SEARCH_PREVIEW` blocks, dropped `ServiceVersion` enum values, and convenience-to-protocol downgrades.
search-documents-typespec-validation
TypeSpec validation skill for Azure.Search.Documents SDK. Performs a COMPLETE validation of ALL operations, ALL models, ALL enums, and ALL properties against the TypeSpec definition at any pinned commit. Works for any API version. Generates a full gap report: missing features, extra features, naming mismatches, and recommended fix location. WHEN: "validate Azure.Search.Documents SDK against TypeSpec", "detect Azure.Search.Documents typespec feature gaps", "what is missing from the Azure.Search.Documents SDK", "compare Azure.Search.Documents SDK to spec", "full spec coverage audit for Azure.Search.Documents". Do NOT use for version-to-version diff or regression detection — use search-documents-version-diff instead.
test-skill_file
Roll dice using a random number generator.
roll-dice
Roll dice using a random number generator. Use when asked to roll a die (d6, d20, etc.), roll dice, or generate a random dice roll.