How do I install the Maestro Run Test skill?

Run npx skillmds add majiayu000/maestro-run-test in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Maestro Run Test safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Maestro Run Test?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Maestro Run Test free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Maestro Run Test?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Maestro Run Test by majiayu000 — Agent Skill

Name: Maestro Run Test
Rating: 4.2 (5 reviews)
Author: majiayu000

Maestro Run Test

Run Maestro E2E tests from a file or directory path and capture output to a results directory. Use when the user wants to run a Maestro test, execute a test flow, run E2E tests with output, or mentions "maestro test" with a path.

majiayu000 df2f921 2 files · 3.1 KB Updated Sep 9, 2026 567 repo stars

File contents

Run Maestro Test

Run a Maestro test flow (or directory of flows) and capture structured output.

Instructions

1. Resolve the test path

The user provides a path to a .yml flow file or a directory of flows. If the path is relative, resolve it from the workspace root.

Verify the path exists before running:

ls <resolved-path>

2. Clean previous results

rm -rf build/maestro-results

3. Run the test

maestro test --test-output-dir=build/maestro-results <resolved-path>

If the user specifies extra flags (e.g. --include-tags, --exclude-tags, --device), append them.

4. Report results

After the command finishes:

Read the exit code — 0 means all tests passed, non-zero means failures.
List the results directory to find output files:

ls -la build/maestro-results/

Read the XML report if present (build/maestro-results/*.xml) for a structured summary of pass/fail counts.
If there are screenshots in the output dir, mention them to the user.
Summarize: total tests, passed, failed, and which tests failed (with the failure reason if available).

5. On failure

If tests fail:

Show the failing test name and the error message from the output.
If a screenshot was captured at the failure point, reference it.
Suggest next steps: re-run with --debug-output or use the fix-maestro-test skill to debug interactively.

Examples

Run a single test:

User: run the login test at maestro/flows/auth/LoginWithGustoWelcome.yml

rm -rf build/maestro-results
maestro test --test-output-dir=build/maestro-results maestro/flows/auth/LoginWithGustoWelcome.yml

Run all tests in a directory:

User: run all the auth tests

rm -rf build/maestro-results
maestro test --test-output-dir=build/maestro-results maestro/flows/auth/

Run with tags:

User: run smoke tests from maestro/flows

rm -rf build/maestro-results
maestro test --test-output-dir=build/maestro-results --include-tags=smoke maestro/flows/

---name: maestro-run-testdescription: Run Maestro E2E tests from a file or directory path and capture output to a results directory. Use when the user wants to run a Maestro test, execute a test flow, run E2E tests with output, or mentions "maestro test" with a path.--- # Run Maestro Test Run a Maestro test flow (or directory of flows) and capture structured output. ## Instructions ### 1. Resolve the test path The user provides a path to a `.yml` flow file or a directory of flows. If the path is relative, resolve it from the workspace root. Verify the path exists before running: ```bash ls <resolved-path> ``` ### 2. Clean previous results ```bash rm -rf build/maestro-results ``` ### 3. Run the test ```bash maestro test --test-output-dir=build/maestro-results <resolved-path> ``` If the user specifies extra flags (e.g. `--include-tags`, `--exclude-tags`, `--device`), append them. ### 4. Report results After the command finishes: 1. Read the exit code — `0` means all tests passed, non-zero means failures. 2. List the results directory to find output files: ```bash ls -la build/maestro-results/ ``` 3. Read the XML report if present (`build/maestro-results/*.xml`) for a structured summary of pass/fail counts. 4. If there are screenshots in the output dir, mention them to the user. 5. Summarize: total tests, passed, failed, and which tests failed (with the failure reason if available). ### 5. On failure If tests fail: - Show the failing test name and the error message from the output. - If a screenshot was captured at the failure point, reference it. - Suggest next steps: re-run with `--debug-output` or use the `fix-maestro-test` skill to debug interactively. ## Examples **Run a single test:** ``` User: run the login test at maestro/flows/auth/LoginWithGustoWelcome.yml ``` ```bash rm -rf build/maestro-results maestro test --test-output-dir=build/maestro-results maestro/flows/auth/LoginWithGustoWelcome.yml ``` **Run all tests in a directory:** ``` User: run all the auth tests ``` ```bash rm -rf build/maestro-results maestro test --test-output-dir=build/maestro-results maestro/flows/auth/ ``` **Run with tags:** ``` User: run smoke tests from maestro/flows ``` ```bash rm -rf build/maestro-results maestro test --test-output-dir=build/maestro-results --include-tags=smoke maestro/flows/ ```

Frequently asked questions