Allure Test Agent

Use this skill for feature or bug work that changes tests, for reviewing existing tests, auditing coverage, triaging failing suites, investigating weak evidence, or debugging flaky and environment-sensitive failures.

• If a command executes tests and its result will be used for smoke checking, reasoning, review, coverage analysis, debugging, or any user-facing conclusion, run it through allure agent. It preserves the original console logs and adds agent-mode artifacts without inheriting the normal report or export plugins from the project config.
• Use allure agent for smoke checks too, even when the change is small or mechanical.
• Only skip agent mode when it is impossible or when you are debugging agent mode itself.

Read First

If the project has docs/allure-test-agent.md, read it before writing or reviewing tests.

If it does not, use the guidance in this skill and suggest using $allure-configure-agent-workflow later.

Read references/agent-mode.md before setting up or troubleshooting agent-mode execution, inspecting existing local or CI Allure results/dumps, or changing output, state, rerun, capability-discovery, or reporting-boundary guidance.

Read references/test-design.md before adding, changing, deleting, skipping, suppressing, or reviewing tests.

Read references/allure-evidence.md before adding, reviewing, or fixing Allure steps, attachments, parameters, labels, descriptions, or weak evidence findings.