Test Coverage Improver

Test Coverage Improver is an individual skill from OpenAI’s official open-source openai-agents-python repository. Its direct primary source is https://github.com/openai/openai-agents-python/tree/main/.agents/skills/test-coverage-improver. The skill supports a focused coverage review in the Python SDK when measurement evidence is missing, a coverage metric regresses, or caller-visible behavior is not adequately protected by tests. It is not a general instruction to test as many lines as possible. It is an investigation and implementation workflow for meaningful gaps.

Purpose and boundaries

According to the provider, the skill is intended for coverage audits, coverage-metric regressions, and finding gaps from coverage artifacts. When the user already specifies the behaviors to test, the source recommends the ordinary implementation or review workflow unless coverage measurement is also requested. This boundary matters because a higher percentage is not automatically higher quality. Public behavior and meaningful error, cancellation, and lifecycle paths have priority. The skill also distinguishes an assessment from an explicitly authorized implementation. For an assessment, it says to report gaps and suggested tests without editing files.

Measurement first

The workflow starts by checking existing artifacts such as .coverage, coverage.xml, and recorded command or environment evidence. They should be reused only when they represent the relevant source and test state. If they are missing or stale, the official instructions call for running make coverage in the repository’s verification sandbox. The next step can use uv run coverage report -m or coverage.xml to locate files and areas with low coverage. This order prevents an old measurement from creating false priorities. A coverage measurement also does not authorize live API calls or broader sandbox access.

Selection and implementation

Selection is performed at the highest controllable caller boundary. Tests should have independent expected results for meaningful behavior rather than merely reproducing helper logic or enumerating unsupported permutations. After selection, the tests are implemented and affected checks are run. The source also refers to a final implementation review and the SDK’s normal code-change verification gates. Only after a clean review should make coverage run as the final measurement. Reporting should state the scope, age of the evidence, protected behaviors, and remaining gaps instead of presenting only a percentage.

Safety and practical limits

The skill describes a repository workflow, not a guarantee of complete test coverage. Coverage can expose untested paths, but it proves neither business correctness nor security. Continue to apply project rules for tests, network access, credentials, and sandbox permissions. Do not store API keys, tokens, or personal data in coverage artifacts or example files. A local coverage result also does not mean that model calls or other connected services are processed locally. This description was checked against the official skill file and official OpenAI Agents documentation on September 9, 2026. According to the provider, the repository is open source and licensed under Apache-2.0; verify current details in the primary source.

Team fit

The workflow is useful for teams that want to protect SDK changes with evidence and prioritize test investment from observed gaps. It separates measurement, diagnosis, authorization, and implementation, so an assessment remains useful even when no code change has been approved. For a small project with no existing coverage artifacts, a complete measurement may cost more than a single focused test. In that situation, the team should deliberately decide whether measurement or the ordinary test workflow is the better starting point.