Skip to main content
Testing

Write focused tests for existing code

Point Gemini at a function and its framework, ask for the highest-value cases first (happy path, edges, failure modes), and have it flag behaviour that looks like a bug instead of testing it as correct.

プロンプト

Write tests for [FUNCTION] using [TEST FRAMEWORK]. Cover the happy path, edge cases, and failure modes, ordered by value. Use the existing test conventions in the repo. If any current behaviour looks like a bug, flag it instead of encoding it as expected. Code: [CODE].

変数を置き換える

[FUNCTION]

The unit under test.

[TEST FRAMEWORK]

e.g. Vitest, Jest, pytest.

どのモデルを使うか

  • Gemini 3.6 FlashTest scaffolding is fast and mechanical enough for Flash.

入力例

  • [FUNCTION] = "parsePrice(input)". [TEST FRAMEWORK] = "Vitest".

出力例

私たちは実際のモデル実行による出力例のみを公開しています。このテンプレートはまだ正式にテストされていないため、出力は表示されません。上記の入力を使ってご自身で実行してみてください。

この構造が機能する理由

  • Value-ordered cases give you the most coverage per test.
  • "Flag suspected bugs" avoids cementing wrong behaviour.

よくある失敗と修正

Tests pass but assert nothing meaningful.

修正: Require at least one edge case and one failure case with real assertions.

既知の制限事項

  • Run the tests; generated tests can be shallow or wrong.

Google との提携・承認関係はありません。Gemini、Nano Banana、Veo は Google LLC の商標です。