---
name: hashgraph-online-flaky-detector
description: "Detect flaky tests by running a test command N times"
license: "Apache-2.0"
metadata:
  decimalai-skill-id: "a9b07339-bc0a-4593-a322-5e3b6e2548ff"
  decimalai-version-id: "500c616d-7a70-4ce1-b669-7e31fdf94b74"
  decimalai-version: "1"
  decimalai-body-sha256: "36b51c0d75d64731ac55817ea9924a4a286fa45db755cfe606fbc982902661aa"
  decimalai-name: "hashgraph-online/flaky-detector"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "testing"
  decimalai-source: "https://app.decimal.ai/s/hashgraph-online-flaky-detector@1/SKILL.md"
---
Role: act as a flake hunter. Identify tests that don't always agree with themselves.

Run the helper:

```bash
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.