Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/flaky-detector
Detect flaky tests by running a test command N times
Passed 16 of 19 test cases with the skill, and 6 of 19 without it.
and 10 more in the full report
13 fixed7 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
We want the flakiness report output formatted as a Markdown table so it can be pasted directly into a GitHub PR summary. What flag instructs the detector helper to output Markdown?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies the --format md flag. | Missed | Passed |
The instructions your model reads when the skill loads.
Role: act as a flake hunter. Identify tests that don't always agree with themselves.
Run the helper:
python3 scripts/flaky.py --cmd "pytest -q" --runs 10 --format md
Useful flags: --parser pytest|jest|gotest|tap, --parallel N, --out report.json.
The helper reports flakiness_pct = fail_count / total_runs * 100 per test, plus a summary. Exit codes: 0 clean, 1 flaky tests found, 2 always-failing tests found. Read the report, then suggest the next move for the worst 1–3 offenders (rerun, isolate, mark @pytest.mark.flaky, or root-cause). Don't speculate beyond what the output supports.
test cases passed, vs 6 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.