mcpbeat Sign in

Pipelines Build Summary Agent Skill

List, inspect, and troubleshoot Azure DevOps pipeline builds. Shows recent builds for a pipeline definition, drills into a specific build's status and result, displays logs for failed steps, and lists the changes associated with a build.

1.3k tokens
context cost
SKILL.md, read when the skill is used
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
36
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/microsoft/azure-devops-skills --skill pipelines-build-summary

The instruction itself

14 sections, as written by the author

Pipeline build summary

This skill works in the context of a project. A pipeline definition or build ID is optional and depends on what the user asks.

Project selection

  • If the user provides a project name in their request (for example, "for Contoso"), use that project directly and do not call core_list_projects.
  • If the user does not provide a project name, first ask the user once to provide the project name.
  • If the project name is still not provided after asking once, call core_list_projects to return a list of projects the user can choose from.

Pipeline definition selection

  • If the user provides a pipeline or definition name, use pipelines_definition with action list and a name filter to find it.
  • If the user does not specify a pipeline and the request requires one (for example, "show recent builds"), ask the user once for the pipeline name.
  • If the pipeline name is still not provided after asking once, call pipelines_definition with action list to list available definitions for the user to choose from.

Tools

Use Azure DevOps MCP Server tools for all interactions with Azure DevOps.

  • core_list_projects: Get a list of projects in the organization.
  • pipelines_definition (action: list): Get a list of build/pipeline definitions for a project.
  • pipelines_build (action: list): Get a list of builds, optionally filtered by definition, branch, or status.
  • pipelines_build (action: get_status): Get the status and result of a specific build by ID.
  • pipelines_build_log (action: list): Get the list of logs for a specific build.
  • pipelines_build_log (action: get_content): Get a specific log by log ID for a build (use to retrieve failed step logs).
  • pipelines_build (action: get_changes): Get the commits/changes associated with a specific build.

Rules

1. List recent builds for a pipeline

  • When the user asks to list builds or show recent builds for a pipeline, call pipelines_build with action list filtered by the definition ID.
  • Optionally filter by branchName, statusFilter, or resultFilter if the user specifies (for example, "failed builds on main").
  • Do not fetch logs or changes unless the user asks.
  • Show the results in a table.
  • If there are no builds, explicitly state that there are no builds for this pipeline.

Example

  • "show recent builds for pipeline 'CI-Main' in project Contoso"

2. Get build status by ID

  • When the user asks about a specific build (for example, "build 12345"), call pipelines_build with action get_status with that build ID.
  • Show the build number, status, result, source branch, start/finish time, requested by, and definition name.
  • If the build failed, suggest viewing the logs.

Example

  • "what is the status of build 12345 in project Contoso?"

3. View logs for a failed build

  • When the user asks to view logs or why a build failed, first call pipelines_build_log with action list to get the list of all log entries for the build.
  • Identify failed steps from the log list (look for steps that indicate errors or failures).
  • Call pipelines_build_log with action get_content for the relevant failed log entries to retrieve the actual log content.
  • Present the log output in a code block so it is easy to read.
  • Do not dump all logs. Focus on the failed steps and the last portion of each relevant log.

Example

  • "show me the logs for build 12345 in project Contoso"
  • "why did build 12345 fail?"

4. List changes for a build

  • When the user asks to see what changed or list commits for a build, call pipelines_build with action get_changes with the build ID.
  • Show the results in a table with commit ID, author, and message.
  • If there are no changes, explicitly state that there are no changes associated with this build.

Example

  • "what changes were in build 12345?"
  • "list commits for build 12345 in project Contoso"

Display results

When displaying build lists, show the following in a table:

  • Build ID as a clickable hyperlink in this format: {buildId}
  • Definition name
  • Status (for example: completed, inProgress, cancelling, notStarted)
  • Result (for example: succeeded, failed, canceled, partiallySucceeded) — use emoji: ✅ succeeded, ❌ failed, ⚠️ partiallySucceeded, 🚫 canceled
  • Source branch
  • Start time formatted as MM/DD/YYYY HH:MM
  • Requested by (display name only)

When displaying a single build's status, show all the above fields plus:

  • Finish time formatted as MM/DD/YYYY HH:MM
  • Build number
  • Duration (calculated from start and finish time)

When displaying changes, show in a table:

  • Commit ID (short hash, first 8 characters)
  • Author
  • Message (first line only)
  • Timestamp

Other skills for the same job

different authors, same section of the catalogue
Deploying To Production
by ZhanlinCui
×4

Automate creating a GitHub repository and deploying a web project to Vercel. Use when the user asks to deploy a website/app to production, publish a project, or set up GitHub + Vercel deployment.

325 tokens
Vercel Deploy
by ZhanlinCui
×4

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

793 tokens scripts
Lamindb
by christophacham
×3

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

3.8k tokens
Latchbio Integration
by christophacham
×3

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

2.7k tokens
Modal
by christophacham
×3

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

2.9k tokens
Pyhealth
by christophacham
×3

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

4.6k tokens
Github Workflow Automation
by ComeOnOliver
×3

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

6k tokens
Lamindb
by ComeOnOliver
×3

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

3.6k tokens

How to use it

Copy the folder

Take microsoft/pipelines-build-summary from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.