Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →openai/test-coverage-improver
Improve test coverage in the OpenAI Agents Python repository: run `make coverage`, inspect coverage artifacts, identify low-coverage files, propose high-impact tests, and confirm with the user before writing tests.
Passed 5 of 11 test cases with the skill, and 6 of 11 without it.
3 fixed7 passed either way6 still failing6 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have an existing .coverage database for the notification package and want to pinpoint exact line gaps across modules from the command line. Which tool command should be used to display missing line numbers?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies using uv run coverage report -m to locate missing lines. | Missed | Passed |
The instructions your model reads when the skill loads.
Use current coverage evidence to identify missing caller-visible behavior tests. Select this workflow for coverage measurement, coverage-metric regressions, or finding gaps from coverage artifacts. When the user already specifies the behaviors to test, use the ordinary implementation/review workflow without coverage measurement unless measurement is also requested. Adding tests alone does not trigger this skill or its final make coverage step.
For assessment or proposal-only requests, report gaps and suggested tests without editing. When the user requests test improvements or has approved a plan, implement the scoped tests and complete review and verification without asking again. Ask only when a new contract decision, expanded scope, or additional authority is needed. Coverage work never authorizes live API calls or broader sandbox access.
.coverage, coverage.xml, and any recorded command/environment evidence. Reuse them only when they represent the relevant source and test state. If missing or stale, run make coverage under the repository's verification sandbox and credential policy; this initial measurement precedes implementation review. Respect host-capacity guidance before broad measurement.uv run coverage report -m or coverage.xml to locate gaps.$implementation-final-review. Keep iterative verification focused; do not repeatedly run full coverage while review is incomplete.make coverage for the final measurement and $code-change-verification for the required SDK gates. These have different purposes; reuse an already valid final measurement rather than repeating it. Report coverage changes, verified behaviors, and material gaps that remain.State the scope and age of coverage evidence, the behavior each new test protects, validation results, and unresolved gaps. Keep comments and code in English. Do not treat coverage percentages alone as proof of correctness.
test cases passed, vs 6 / 11 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.