agentleFS
Sign inStart free
AurelienClere-365AurelienClere-365/ado-cowork-plugin/skills/ado-test-plans/SKILL.md

ado-test-plans

Skill5 starsChanged 5 months agoMITView on GitHub

Use when the user asks about Azure DevOps test plans, test suites, test cases, or test execution results. "show test results for the last build", "create a test plan for Sprint 12 regression", "add a test case for the login flow", "what is the pass rate for pipeline release-2.0", "create a test suite for authentication scenarios", "list all test plans in the Platform project", "write a test case for the MFA feature", "show failed test cases from build #512", "how many tests are in the smoke suite"

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 1 is distinctive, and 7 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.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If only pipeline name is known, use ado-pipelines skill to get the build ID first.

    line 43
  2. Very specific:

    Call testplan_show_test_results_from_build_id(buildId) — returns pass/fail/skipped counts per test suite, and the list of failed test cases …

    line 44
  3. Very specific:

    Call testplan(project) — returns all test plans with ID, name, state, iteration, and suite count.

    line 51
  4. Very specific:

    Test results are associated with a build via the build definition ID and build number.

    line 107
  5. Very specific:

    If the user gives a pipeline name instead of a build ID, resolve it via ado-pipelines skill first.

    line 108
  6. Distinctive:

    When creating test steps, each step has an Action (what the tester does) and an

    line 110
  7. Very specific:

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

    line 118
  8. 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 120

≈ “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 Test Plans

Manage Azure DevOps test plans, test suites, and test cases. Read test execution results from pipeline builds and create structured test artefacts.

When to use

  • User wants to see test results for a build or pipeline run
  • User wants to create a new test plan or test suite
  • User wants to create or update test cases
  • User wants to know the pass/fail rate for a release or sprint
  • User is preparing a release sign-off and needs test coverage evidence

MCP tools used

ToolPurpose
testplanList test plans and test suites in a project
testplan_show_test_results_from_build_idGet test execution results for a build
testplan_test_plan_writeCreate or update a test plan
testplan_test_suite_writeCreate or update a test suite within a plan
testplan_test_case_writeCreate or update a test case

Workflow

Getting test results for a build

  1. Identify: build ID (if known) or pipeline name + branch.
  2. If only pipeline name is known, use ado-pipelines skill to get the build ID first.
  3. Call testplan_show_test_results_from_build_id(buildId) — returns pass/fail/skipped counts per test suite, and the list of failed test cases with error messages.
  4. Present the Test Results Summary table.
  5. List failing tests in the Failing Tests table.

Listing test plans

  1. Call testplan(project) — returns all test plans with ID, name, state, iteration, and suite count.
  2. Present the Test Plan List table.

Creating a test plan

  1. Extract: project, plan name, and iteration path.
  2. Call testplan_test_plan_write(project, name, iteration).
  3. Confirm with the new plan ID.

Creating a test suite

  1. Identify the parent test plan ID.
  2. Extract: suite name, suite type (static, requirement-based, query-based).
  3. Call testplan_test_suite_write(planId, suiteName, suiteType).
  4. Confirm with the new suite ID.

Creating a test case

  1. Identify the test suite or plan to add the test case to.
  2. Extract: test case title, steps (action + expected result pairs), and any associated work item ID.
  3. Call testplan_test_case_write(suiteId, title, steps).
  4. Confirm with the new test case ID.

Output Format

Test Results Summary

Build #512 — release-2.0 pipeline

SuiteTotalPassedFailedSkippedPass rate
API Integration1451423097.9%
Unit Tests31231200100%
E2E Smoke18160288.9%
Total4754703298.9%

Failing Tests

Test CaseSuiteError
TokenExpiry_ShouldReturn401API IntegrationUnauthorizedAccessException: Token expired
Login_WithExpiredMFAAPI IntegrationAssert.Equal failed: expected 401 got 200
OrderService_NullRefAPI IntegrationNullReferenceException at OrderService.cs:87

Test Plan List

IDPlanIterationStateSuites
5Sprint 12 RegressionSprint 12Active4
3Release 2.0 Sign-offRelease 2.0Active7
1Sprint 11 RegressionSprint 11Inactive3

Notes

  • Test results are associated with a build via the build definition ID and build number. If the user gives a pipeline name instead of a build ID, resolve it via ado-pipelines skill first.
  • When creating test steps, each step has an Action (what the tester does) and an Expected Result (what should happen). Prompt the user for both if not provided.
  • testplan_test_case_write creates a work item of type Test Case in addition to adding it to the suite — both happen in one call.

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.

Check your setup, free