azsdk-common-pipeline-analysis
Skill135 starsChanged 2 months agoMITView on GitHub
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.
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Run azsdk_analyze_pipeline first, then categorize each failure and cite specific files/lines.
- Very specific: line 37
Analyze: - Run azsdk_analyze_pipeline.
- Very specific: line 42
Report: - Use the output format: root cause, affected files, per-failure fix + verify command, and fixable vs infrastructure.
- Very specific: line 52
If azsdk_analyze_pipeline returns no data, verify the build ID is correct and the run has completed.
- Very specific: line 53
If failed_pipeline_tests is empty, rely on failed_pipeline_tasks log analysis (test-artifact upload may not be configured).
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Other versions5 projects use a version of this.
Word for word · 5
- Azure/azure-sdk-for-net★ 6.1k100% same
- Azure/azure-sdk-for-python★ 5.6k100% same
- Azure/azure-sdk-for-java★ 2.6k100% same
- Azure/azure-sdk-for-js★ 2.3k100% same
- Azure/azure-sdk★ 600100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository43 other files it gives its agents.
- packages/python-packages/apiview-copilot/AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- azsdk-common-apiview-feedback-resolutionSkill
- azsdk-common-generate-sdk-locallySkill
- azsdk-common-generate-sdk-pipelineSkill
- azsdk-common-pipeline-fixerSkill
- azsdk-common-prepare-release-planSkill
- azsdk-common-sdk-breaking-changeSkill
- azsdk-common-sdk-releaseSkill
- azsdk-common-typespec-namingSkill
- azure-typespec-assessmentSkill
- azure-typespec-authorSkill
- code-reviewSkill
- eval-authoring-skillSkill
- eval-authoring-toolSkill
- eval-authoring-workflowSkill
- markdown-token-optimizerSkill
- sdk-ai-bot-eval-datasetSkill
- sdk-ai-bot-run-evaluationSkill
- skill-authoringSkill
- add-endpointSkill
- audit-filtersSkill
- dev-setupSkill
- kb-searchSkill
- report-active-reviewsSkill
- report-apiview-metricsSkill
- report-architect-commentsSkill
- report-feedbackSkill
- report-memorySkill
- report-revisionsSkill
- run-evalsSkill
- run-metricsSkill
- update-guidelinesSkill
- apiview-feedback-resolutionSkill
- azure-typespec-authorSkill
- generate-sdk-locallySkill
- azsdk-common-live-and-recorded-testsSkill
- markdown-token-optimizerSkill
- pipeline-troubleshootingSkill
- azsdk-common-prepare-release-planSkill
- azsdk-common-sdk-releaseSkill
- skill-authoringSkill
- pr-review-helpSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

