agentleFS
AurelienClere-365AurelienClere-365/ado-cowork-plugin/skills/ado-pipelines/SKILL.md

ado-pipelines

Skill5 starsChanged 5 months agoMITView on GitHub

Use when the user asks about Azure DevOps build or release pipelines, CI/CD status, build logs, pipeline definitions, artifacts, or wants to trigger a run. "what failed in the last build", "show me the build log for pipeline api-gateway", "trigger a build on the main branch", "list all pipeline definitions in the Platform project", "download the artifact from build #456", "why did the CI fail", "create a new pipeline", "show pipeline run history for release-2.0", "how long does the build take on average", "queue a new run with custom variables"

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 1 is distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read pipeline status, inspect build logs, trigger runs, manage pipeline definitions, and download artifacts for Azure DevOps CI/CD …

    line 18
  2. Very specific:

    Call pipelines_build(project, pipelineName, branch) — returns the latest N builds with status (succeeded, failed, running, cancelled) and …

    line 46
  3. Very specific:

    Call pipelines_build to get the failing build ID.

    line 52
  4. Very specific:

    Call pipelines_build_log(buildId) — returns the structured task timeline with each step's result (succeeded / failed / skipped) and log URL.

    line 53
  5. Very specific:

    Call pipelines_definition(project) — returns all defined pipelines with ID, name, folder, and default branch.

    line 68
  6. Very specific:

    Call pipelines_artifact(buildId, artifactName) — returns the artifact download URL or file list.

    line 75
  7. Very specific:

    When triggering a run, always confirm the branch and variables with the user before calling pipelines_run — a misfire on a release pipeline …

    line 120
  8. Very specific:

    If activeProject is set, use it automatically as the project parameter — do not ask the user to re-specify it.

    line 126
  9. Very specific:

    If no context is set and a project is required, invoke Workflow E of ado-context to resolve it (list projects, ask user to pick, then …

    line 128

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ADO Pipelines

Read pipeline status, inspect build logs, trigger runs, manage pipeline definitions, and download artifacts for Azure DevOps CI/CD pipelines.

When to use

  • User wants to know if a build passed or failed
  • User wants to read error output from a failing build
  • User wants to trigger (queue) a new pipeline run
  • User wants to list available pipeline definitions in a project
  • User wants to download or inspect a pipeline artifact
  • User wants to create or update a pipeline definition (YAML)

MCP tools used

ToolPurpose
pipelines_buildList builds / get the latest build for a pipeline or branch
pipelines_build_logRetrieve the log output of a specific build task
pipelines_runQueue (trigger) a new pipeline run
pipelines_writeCreate or update a pipeline definition
pipelines_definitionGet the full YAML definition of a pipeline
pipelines_artifactList or download artifacts produced by a build

Workflow

Getting the latest build status

  1. Identify: project name and either pipeline name or repository+branch.
  2. Call pipelines_build(project, pipelineName, branch) — returns the latest N builds with status (succeeded, failed, running, cancelled) and duration.
  3. Present the Build Status table.

Reading build logs (failure triage)

  1. Call pipelines_build to get the failing build ID.
  2. Call pipelines_build_log(buildId) — returns the structured task timeline with each step's result (succeeded / failed / skipped) and log URL.
  3. Focus on the first failed step. Extract error lines (lines containing error:, Error, FAILED, Exception).
  4. Present the Failure Summary with the failing step name and extracted error lines.
  5. Offer to create a bug work item from the failure.

Triggering a run

  1. Identify: project, pipeline name/ID, branch, and any variable overrides.
  2. Call pipelines_run(project, pipelineId, branch, variables).
  3. Confirm with the new run ID and a link to the run page.

Listing pipeline definitions

  1. Call pipelines_definition(project) — returns all defined pipelines with ID, name, folder, and default branch.
  2. Present as a Pipeline Definitions table.

Downloading an artifact

  1. Identify build ID and artifact name.
  2. Call pipelines_artifact(buildId, artifactName) — returns the artifact download URL or file list.
  3. Present the artifact content or URL.

Output Format

Build Status

Build #PipelineBranchStatusDurationStarted
456api-gatewaymainFailed2m 14s10 min ago
455api-gatewaymainSucceeded2m 07s2h ago
454api-gatewayfeature/redisSucceeded1m 58s4h ago

Failure Summary

Build #456 — api-gateway / main — FAILED

StepResultDuration
Restore NuGet packagesSucceeded0m 23s
BuildSucceeded0m 51s
Run unit testsFailed0m 58s
error: Test run failed.
  FAILED  AuthServiceTests.TokenExpiry (0.23s)
    System.UnauthorizedAccessException: Token expired before validation
    at AuthService.ValidateToken() line 87

Pipeline Definitions

IDNameFolderDefault Branch
12api-gateway\Backendmain
17identity-service\Backendmain
23release-2.0\Releaserelease/2.0

Notes

  • pipelines_build returns builds in reverse-chronological order. To get a specific build, pass the build ID directly.
  • Log lines can be very long. Truncate to the first 50 error lines; offer to show more if the user asks.
  • When triggering a run, always confirm the branch and variables with the user before calling pipelines_run — a misfire on a release pipeline can be disruptive.

Active context

This skill respects the session context set by the ado-context skill.

  • If activeProject is set, use it automatically as the project parameter — do not ask the user to re-specify it.
  • If no context is set and a project is required, invoke Workflow E of ado-context to resolve it (list projects, ask user to pick, then proceed).

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.