From bd2077feceeded0062934ea3ed2f4091cb627c05 Mon Sep 17 00:00:00 2001 From: Christopher Harrison Date: Tue, 29 Sep 2026 12:44:13 -0700 Subject: [PATCH] docs: align quality-checks lessons with the Tailspin skill Describe unit tests, lint, and type checks consistently across App and CLI lessons and App translations. Correct the report customization exercise and request only tool-reported metrics. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --- .../real-world-development/app/10-review.md | 6 ++-- .../app/5-agent-skills.md | 29 ++++++++--------- .../real-world-development/app/10-review.md | 6 ++-- .../app/5-agent-skills.md | 31 +++++++++---------- .../real-world-development/app/10-review.md | 6 ++-- .../app/5-agent-skills.md | 31 +++++++++---------- .../real-world-development/app/10-review.md | 6 ++-- .../app/5-agent-skills.md | 31 +++++++++---------- docs/real-world-development/app/10-review.md | 6 ++-- .../app/5-agent-skills.md | 31 +++++++++---------- docs/real-world-development/cli/10-review.md | 6 ++-- .../cli/5-agent-skills.md | 16 +++++----- .../real-world-development/app/10-review.md | 6 ++-- .../app/5-agent-skills.md | 29 ++++++++--------- 14 files changed, 111 insertions(+), 129 deletions(-) diff --git a/docs/es-es/real-world-development/app/10-review.md b/docs/es-es/real-world-development/app/10-review.md index 06685619..11d59759 100644 --- a/docs/es-es/real-world-development/app/10-review.md +++ b/docs/es-es/real-world-development/app/10-review.md @@ -3,7 +3,7 @@ title: "Lección 10 - Repaso y pasos siguientes" description: "Repasa el flujo de la aplicación, los dos hitos de PR, los ejercicios de lienzo y las prácticas de calidad reutilizables; después, explora otros recursos." authors: - geektrainer -lastUpdated: 2026-07-09 +lastUpdated: 2026-09-29 --- Has utilizado la aplicación GitHub Copilot durante un flujo continuo de Tailspin Toys. Has aprendido a: @@ -11,7 +11,7 @@ Has utilizado la aplicación GitHub Copilot durante un flujo continuo de Tailspi - conectar un repositorio, explorar el espacio de trabajo y la lista de trabajo pendiente inicial de la aplicación y probar un chat rápido. - iniciar una sesión específica de valoraciones por estrellas, revisar el resultado en un lienzo de navegador y combinar manualmente tu primera solicitud de incorporación de cambios (PR). - partir de la incidencia de filtrado, definir el enfoque en modo **Plan**, desarrollarlo en modo **Autopilot** y revisarlo en modo **Interactive**. -- orientar al agente con instrucciones personalizadas y después personalizar una habilidad existente y utilizarla para ejecutar lint, pruebas unitarias, pruebas de un extremo a otro y comprobaciones de tipos. +- orientar al agente con instrucciones personalizadas y después personalizar la habilidad `quality-checks` existente y utilizarla para ejecutar pruebas unitarias, lint y comprobaciones de tipos. - probar el trabajo con el servidor MCP de Playwright en un navegador real. - crear y seleccionar un agente personalizado QA para evaluar requisitos, cobertura, resultados de scripts de la habilidad y pruebas de observación del navegador. - revisar el cambio completo de filtrado y autorizar **Agent Merge** para la segunda PR. @@ -28,7 +28,7 @@ Desde la planificación del filtrado hasta la apertura de su PR, utilizaste la m ## Distintos tipos de verificación -Comprobaste el código de varias formas: pruebas automatizadas, tu propia inspección en el navegador y la exploración de Copilot en el navegador mediante MCP. La habilidad quality-checks ejecutó las comprobaciones del proyecto y presentó los resultados con el nuevo formato. QA reunió esos resultados junto con una revisión de los requisitos y la cobertura de pruebas antes de la PR. +Comprobaste el código de varias formas: pruebas automatizadas, tu propia inspección en el navegador y la exploración de Copilot en el navegador mediante MCP. La habilidad `quality-checks` ejecutó pruebas unitarias, lint y comprobaciones de tipos y presentó los resultados con el nuevo formato. QA reunió esos resultados junto con una revisión de los requisitos y la cobertura de pruebas antes de la PR. Las pruebas añadidas deben cubrir carencias reales; una ejecución QA que no necesita pruebas nuevas puede ser correcta. Las herramientas ausentes, las comprobaciones omitidas y los fallos son bloqueos visibles, no resultados satisfactorios. Revisa el código y las pruebas de verificación antes de autorizar la combinación y actualiza las afectadas después de los cambios. diff --git a/docs/es-es/real-world-development/app/5-agent-skills.md b/docs/es-es/real-world-development/app/5-agent-skills.md index 995ae86b..8a05edc7 100644 --- a/docs/es-es/real-world-development/app/5-agent-skills.md +++ b/docs/es-es/real-world-development/app/5-agent-skills.md @@ -3,7 +3,7 @@ title: "Lección 5 - Personalizar y utilizar una habilidad quality-checks" description: "Explora la habilidad quality-checks existente, personaliza el formato de su informe y utilízala para validar el filtrado." authors: - geektrainer -lastUpdated: 2026-09-11 +lastUpdated: 2026-09-29 --- Escribir código implica mucho más que limitarse a escribirlo. Hemos podido validar manualmente que funciona y hemos utilizado archivos de instrucciones para garantizar que sigue nuestros estándares. Pero ¿qué ocurre con las pruebas, lint y el resto de las tareas de integración continua (CI)? @@ -12,13 +12,13 @@ Para este tipo de tareas, las **habilidades de agente** son la mejor opción. La En esta lección: -- explorarás la habilidad `quality-checks` existente y sus scripts incluidos. +- explorarás la habilidad `quality-checks` existente. - personalizarás el formato de sus resultados. - ejecutarás la habilidad y revisarás su salida. ## Escenario -Tailspin Toys dispone de un conjunto de pruebas unitarias y de un extremo a otro que siempre deben ejecutarse antes de crear cualquier solicitud de incorporación de cambios (PR). Como cabe esperar, es importante garantizar que se ejecuten de forma correcta y coherente. El equipo ya ha creado una habilidad de agente para ejecutar estas pruebas, pero quiere mejorar la salida para facilitar su lectura. +Tailspin Toys utiliza la habilidad `quality-checks` para las pruebas unitarias, lint y las comprobaciones de tipos. El equipo quiere mejorar el informe para facilitar la lectura de los resultados. ## Instrucciones, scripts y recursos @@ -38,32 +38,29 @@ Las habilidades pueden residir en la carpeta `.github/skills` de un proyecto par ## Ejecutar la habilidad antes de realizar un cambio -Las habilidades se pueden invocar directamente mediante un comando con barra diagonal (`/`) o con lenguaje natural. La descripción destaca que la habilidad debe utilizarse cuando se solicite ejecutar pruebas o lint. Ejecutemos la habilidad pidiendo a Copilot que ejecute las pruebas. +Las habilidades se pueden invocar directamente mediante un comando con barra diagonal (`/`) o con lenguaje natural. Pidamos a Copilot que ejecute las tres comprobaciones de la habilidad. 1. Selecciona el modo **Interactive** en el menú desplegable para confirmar que Copilot lo utiliza. -2. Utiliza la indicación siguiente para pedir a Copilot que ejecute las pruebas y el linter, lo que invocará la habilidad: +2. Utiliza la indicación siguiente para invocar la habilidad: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Observa el informe final. ## Personalizar el informe -Queremos un informe mejor que muestre las pruebas ejecutadas, las tasas de éxito y error y cuánto han tardado. Actualicemos la habilidad para que Copilot genere ese informe. +Queremos un informe mejor que indique qué se ha ejecutado, si ha tenido éxito y qué han comunicado realmente las herramientas. Actualicemos la habilidad para generar ese informe. 1. Vuelve al lienzo **Files**. 2. Si aún no está abierto, abre `.github/skills/quality-checks/SKILL.md`. -3. Busca al final del archivo el encabezado **Results output formatting**. -4. Justo debajo, añade lo siguiente para que los resultados se muestren según nuestras especificaciones: +3. Añade la siguiente sección al final del archivo: ```markdown - Upon completion of all tests, generate a report that provides a quick overview of both success and failure of the tests, and how long they took to ran. In particular, we need sections for: + ## Results output formatting - - Unit tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - End to end tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - Linting, number of lines scanned, number of violations, and the percentage of lines of code that meet the linting requirements. + Upon completion, report each command that ran and whether it passed, failed, or was blocked. Include test counts, durations, errors, warnings, and other metrics only when the tool reports them. Identify the next action for any failure or blocker, and never describe a skipped or incomplete check as passed. ``` El archivo se guardará automáticamente. @@ -73,10 +70,10 @@ El archivo se guardará automáticamente. Una vez realizado el cambio, veamos cómo funciona. Utilizaremos exactamente la misma indicación que antes. 1. Selecciona el modo **Interactive** en el menú desplegable para confirmar que Copilot lo utiliza. -2. Utiliza la indicación siguiente para pedir a Copilot que ejecute las pruebas y el linter, lo que invocará la habilidad: +2. Utiliza la indicación siguiente para invocar la habilidad: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Observa el informe final. @@ -85,7 +82,7 @@ Una vez realizado el cambio, veamos cómo funciona. Utilizaremos exactamente la Has personalizado y utilizado una habilidad de agente existente. En esta lección: -- has explorado la habilidad `quality-checks` y sus scripts incluidos. +- has explorado la habilidad `quality-checks` para las pruebas unitarias, lint y las comprobaciones de tipos. - has personalizado el formato de sus resultados. - has ejecutado la habilidad y revisado su salida. diff --git a/docs/ja-jp/real-world-development/app/10-review.md b/docs/ja-jp/real-world-development/app/10-review.md index 4c781b05..85b03a6b 100644 --- a/docs/ja-jp/real-world-development/app/10-review.md +++ b/docs/ja-jp/real-world-development/app/10-review.md @@ -3,7 +3,7 @@ title: "レッスン 10 - 振り返りと次のステップ" description: "App のワークフロー、2つの PR マイルストーン、キャンバス演習、再利用可能な品質プラクティスを振り返り、追加のリソースを確認します。" authors: - geektrainer -lastUpdated: 2026-07-09 +lastUpdated: 2026-09-29 --- GitHub Copilot app を使用して、Tailspin Toys の1つの連続したワークフローに取り組みました。実施した内容は次のとおりです。 @@ -11,7 +11,7 @@ GitHub Copilot app を使用して、Tailspin Toys の1つの連続したワー - リポジトリを接続し、アプリのワークスペースと用意されたバックログを確認して、クイックチャットを試した。 - 星評価に対象を絞ったセッションを開始し、ブラウザーキャンバスで結果をレビューして、最初の pull request (PR) を手動でマージした。 - フィルター機能の Issue から開始し、**Plan** モードでアプローチを定義して、**Autopilot** モードで構築し、**Interactive** モードでレビューした。 -- カスタム指示でエージェントをガイドし、既存の `quality-checks` スキルをカスタマイズして、lint、単体テスト、E2E テスト、型チェックを実行した。 +- カスタム指示でエージェントをガイドし、既存の `quality-checks` スキルをカスタマイズして、単体テスト、lint、型チェックを実行した。 - Playwright Model Context Protocol (MCP) server を追加し、実際のブラウザーでフィルター機能を確認した。 - 要件、カバレッジ、スキルの結果、ブラウザーでの証拠を評価する品質保証 (QA) カスタムエージェントを作成して選択した。 - フィルター機能の変更全体をレビューし、2つ目の PR に **Agent Merge** を承認した。 @@ -28,7 +28,7 @@ GitHub Copilot app を使用して、Tailspin Toys の1つの連続したワー ## 検証方法の違い -自動テスト、手動のブラウザー確認、MCP を使った Copilot によるブラウザーでの調査など、複数の方法でコードを検証しました。quality-checks スキルはプロジェクトのチェックを実行し、新しい形式で結果を報告しました。QA では、PR の前にこれらの結果を要件とテストカバレッジのレビューと組み合わせました。 +自動テスト、手動のブラウザー確認、MCP を使った Copilot によるブラウザーでの調査など、複数の方法でコードを検証しました。`quality-checks` スキルは単体テスト、lint、型チェックを実行し、新しい形式で結果を報告しました。QA では、PR の前にこれらの結果を要件とテストカバレッジのレビューと組み合わせました。 追加するテストは実際の不足を補うものにします。新しいテストが不要な QA 実行も正しい結果になり得ます。ツールの不足、スキップされたチェック、失敗は明示すべき阻害要因であり、成功ではありません。マージを承認する前にコードと証拠をレビューし、変更後は関連する証拠を更新してください。 diff --git a/docs/ja-jp/real-world-development/app/5-agent-skills.md b/docs/ja-jp/real-world-development/app/5-agent-skills.md index 0d3f8c4b..53d957f8 100644 --- a/docs/ja-jp/real-world-development/app/5-agent-skills.md +++ b/docs/ja-jp/real-world-development/app/5-agent-skills.md @@ -3,7 +3,7 @@ title: "レッスン 5 - quality-checks スキルのカスタマイズと使用" description: "既存の quality-checks スキルを確認し、報告形式をカスタマイズして、フィルター機能の検証に使用します。" authors: - geektrainer -lastUpdated: 2026-09-11 +lastUpdated: 2026-09-29 --- コードを書く作業には、単にコードを書く以上のことが含まれます。コードが動作することは手動で検証し、指示ファイルを使用して標準に従っていることも確認しました。しかし、テストや lint、継続的インテグレーション (CI) のその他の作業はどうでしょうか。 @@ -12,13 +12,13 @@ lastUpdated: 2026-09-11 このレッスンでは、次の内容を学習します。 -- 既存の `quality-checks` スキルと同梱のスクリプトを確認する。 +- 既存の `quality-checks` スキルを確認する。 - 結果の報告形式をカスタマイズする。 - スキルを実行し、出力をレビューする。 ## シナリオ -Tailspin Toys には、pull request (PR) を作成する前に必ず実行する必要がある単体テストと E2E テストがあります。これらを正しく一貫して実行することが重要です。チームはすでにテスト実行用のエージェントスキルを作成していますが、読みやすい出力に改善したいと考えています。 +Tailspin Toys は、単体テスト、lint、型チェックに `quality-checks` スキルを使用します。チームは、結果を読みやすくするためにレポートを改善したいと考えています。 ## 指示、スクリプト、リソース @@ -31,7 +31,7 @@ Tailspin Toys には、pull request (PR) を作成する前に必ず実行する ## スキルを確認する -Tailspin Toys チームがテストと linter の実行用に作成した `quality-checks` というスキルを確認します。 +Tailspin Toys チームが単体テスト、lint、型チェックの実行用に作成した `quality-checks` というスキルを確認します。 1. **Files** キャンバスをまだ開いていない場合は、レビューパネルで **+**、**File** の順に選択します。 2. `.github/skills/quality-checks/SKILL.md` を検索します。 @@ -40,32 +40,29 @@ Tailspin Toys チームがテストと linter の実行用に作成した `quali ## 変更前にスキルを実行する -スキルはスラッシュ (`/`) コマンドで直接呼び出すことも、自然言語で呼び出すこともできます。このスキルの説明には、テストまたは lint の実行を依頼されたときに使用することが示されています。Copilot にテストの実行を依頼して、スキルを実行しましょう。 +スキルはスラッシュ (`/`) コマンドで直接呼び出すことも、自然言語で呼び出すこともできます。スキルの 3 種類のチェックを実行するよう Copilot に依頼しましょう。 1. モードのドロップダウンから **Interactive** を選択し、Copilot が Interactive モードになっていることを確認します。 -2. 次のプロンプトを使って Copilot にテストと linter の実行を依頼し、スキルを呼び出します。 +2. 次のプロンプトを使ってスキルを呼び出します。 ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. 最後に表示されるレポートを確認します。 ## 報告形式をカスタマイズする -実行したテスト、成功率と失敗率、実行にかかった時間を示す、よりわかりやすいレポートが必要です。Copilot がそのレポートを作成するようにスキルを更新しましょう。 +何を実行したか、成功したか、ツールが実際に何を報告したかがわかる、よりよいレポートが必要です。そのレポートを作成するようスキルを更新しましょう。 1. **Files** キャンバスに戻ります。 2. まだ開いていない場合は、`.github/skills/quality-checks/SKILL.md` を開きます。 -3. ファイルの末尾にある **Results output formatting** という見出しを見つけます。 -4. その見出しのすぐ下に次の内容を追加し、指定した形式で結果を表示するようにします。 +3. ファイルの末尾に次のセクションを追加します。 ```markdown - Upon completion of all tests, generate a report that provides a quick overview of both success and failure of the tests, and how long they took to ran. In particular, we need sections for: + ## Results output formatting - - Unit tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - End to end tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - Linting, number of lines scanned, number of violations, and the percentage of lines of code that meet the linting requirements. + Upon completion, report each command that ran and whether it passed, failed, or was blocked. Include test counts, durations, errors, warnings, and other metrics only when the tool reports them. Identify the next action for any failure or blocker, and never describe a skipped or incomplete check as passed. ``` ファイルは自動的に保存されます。 @@ -75,10 +72,10 @@ Tailspin Toys チームがテストと linter の実行用に作成した `quali 変更したスキルを実際に試してみましょう。先ほどとまったく同じプロンプトを使用します。 1. モードのドロップダウンから **Interactive** を選択し、Copilot が Interactive モードになっていることを確認します。 -2. 次のプロンプトを使って Copilot にテストと linter の実行を依頼し、スキルを呼び出します。 +2. 次のプロンプトを使ってスキルを呼び出します。 ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. 最後に表示されるレポートを確認します。 @@ -87,7 +84,7 @@ Tailspin Toys チームがテストと linter の実行用に作成した `quali 既存のエージェントスキルをカスタマイズして使用しました。このレッスンでは、次の作業を行いました。 -- `quality-checks` スキルと同梱のスクリプトを確認した。 +- 単体テスト、lint、型チェックを実行する `quality-checks` スキルを確認した。 - 結果の報告形式をカスタマイズした。 - スキルを実行し、出力をレビューした。 diff --git a/docs/ko-kr/real-world-development/app/10-review.md b/docs/ko-kr/real-world-development/app/10-review.md index f9e37690..aee793a7 100644 --- a/docs/ko-kr/real-world-development/app/10-review.md +++ b/docs/ko-kr/real-world-development/app/10-review.md @@ -3,7 +3,7 @@ title: "레슨 10 - 마무리 및 다음 단계" description: "App 워크플로, 두 PR 마일스톤, 캔버스 실습, 재사용 가능한 품질 관행을 돌아보고 추가 리소스를 살펴봅니다." authors: - geektrainer -lastUpdated: 2026-07-09 +lastUpdated: 2026-09-29 --- 하나로 이어지는 Tailspin Toys 워크플로 전체에서 GitHub Copilot app을 사용했습니다. 다음 작업을 수행했습니다. @@ -11,7 +11,7 @@ lastUpdated: 2026-07-09 - 리포지토리를 연결하고 앱의 워크스페이스와 미리 생성된 백로그를 살펴보고 빠른 채팅을 사용했습니다. - 별점에 초점을 맞춘 세션을 시작하고 브라우저 캔버스에서 결과를 검토한 다음 첫 번째 끌어오기 요청(PR)을 직접 병합했습니다. - 필터링 이슈에서 시작하여 **Plan** 모드에서 접근 방식을 정의하고, **Autopilot** 모드로 구축하고, **Interactive** 모드에서 검토했습니다. -- 사용자 지정 지침으로 에이전트를 안내한 다음 기존 `quality-checks` 스킬을 사용자 지정하고 린트, 단위 테스트, 엔드투엔드 테스트, 타입 검사를 실행하는 데 사용했습니다. +- 사용자 지정 지침으로 에이전트를 안내한 다음 기존 `quality-checks` 스킬을 사용자 지정하고 단위 테스트, 린트, 타입 검사를 실행하는 데 사용했습니다. - Playwright Model Context Protocol(MCP) 서버를 추가하고 실제 브라우저에서 필터링을 살펴보는 데 사용했습니다. - 품질 보증(QA) 사용자 지정 에이전트를 만들고 선택하여 요구 사항, 커버리지, 스킬 결과, 브라우저 근거를 평가했습니다. - 완성된 필터링 변경을 검토하고 두 번째 PR에 **Agent Merge**를 승인했습니다. @@ -28,7 +28,7 @@ lastUpdated: 2026-07-09 ## 서로 다른 검증 방식 -자동 테스트, 직접 수행한 브라우저 확인, MCP를 통한 Copilot의 브라우저 탐색 등 여러 방식으로 코드를 검사했습니다. quality-checks 스킬은 프로젝트 검사를 실행하고 새로운 형식으로 결과를 보고했습니다. QA는 PR 전에 이 결과를 요구 사항 및 테스트 커버리지 검토와 결합했습니다. +자동 테스트, 직접 수행한 브라우저 확인, MCP를 통한 Copilot의 브라우저 탐색 등 여러 방식으로 코드를 검사했습니다. `quality-checks` 스킬은 단위 테스트, 린트, 타입 검사를 실행하여 새로운 형식으로 결과를 보고했습니다. QA는 PR 전에 이 결과를 요구 사항 및 테스트 커버리지 검토와 결합했습니다. 추가한 테스트는 실제 커버리지 부족을 해결해야 합니다. 새 테스트가 필요 없는 QA 실행도 올바를 수 있습니다. 누락된 도구, 건너뛴 검사, 실패는 드러내야 할 차단 요인이지 통과가 아닙니다. 병합 승인 전에 코드와 근거를 검토하고 변경 후 관련 근거를 갱신합니다. diff --git a/docs/ko-kr/real-world-development/app/5-agent-skills.md b/docs/ko-kr/real-world-development/app/5-agent-skills.md index 5d10876f..b690ff41 100644 --- a/docs/ko-kr/real-world-development/app/5-agent-skills.md +++ b/docs/ko-kr/real-world-development/app/5-agent-skills.md @@ -3,7 +3,7 @@ title: "레슨 5 - quality-checks 스킬 사용자 지정 및 사용" description: "기존 quality-checks 스킬을 살펴보고 보고서 형식을 사용자 지정한 다음 필터링을 검증합니다." authors: - geektrainer -lastUpdated: 2026-09-11 +lastUpdated: 2026-09-29 --- 코드 작성에는 코드 자체를 작성하는 것보다 더 많은 작업이 필요합니다. 코드가 작동하는지 수동으로 검증하고 지침 파일을 사용하여 표준을 따르게 했습니다. 하지만 테스트, 린트, 그 밖의 지속적 통합(CI) 요소는 어떻게 처리해야 할까요? @@ -12,13 +12,13 @@ lastUpdated: 2026-09-11 이 레슨에서는 다음 작업을 수행합니다. -- 기존 `quality-checks` 스킬과 함께 제공되는 스크립트를 살펴봅니다. +- 기존 `quality-checks` 스킬을 살펴봅니다. - 결과 형식을 사용자 지정합니다. - 스킬을 실행하고 출력을 검토합니다. ## 시나리오 -Tailspin Toys에는 끌어오기 요청(PR)을 만들기 전에 항상 실행해야 하는 단위 테스트와 엔드투엔드 테스트 모음이 있습니다. 예상할 수 있듯 이러한 테스트를 올바르고 일관되게 실행하는 것이 중요합니다. 팀은 이미 이러한 테스트를 실행하는 에이전트 스킬을 만들었지만, 더 읽기 쉬운 출력을 원합니다. +Tailspin Toys는 단위 테스트, 린트, 타입 검사에 `quality-checks` 스킬을 사용합니다. 팀은 결과를 더 쉽게 읽을 수 있도록 보고서를 개선하려고 합니다. ## 지침, 스크립트, 리소스 @@ -31,7 +31,7 @@ Tailspin Toys에는 끌어오기 요청(PR)을 만들기 전에 항상 실행해 ## 스킬 살펴보기 -Tailspin Toys 팀이 테스트와 린터 실행을 위해 만든 `quality-checks` 스킬을 살펴봅니다. +Tailspin Toys 팀이 단위 테스트, 린트, 타입 검사 실행을 위해 만든 `quality-checks` 스킬을 살펴봅니다. 1. **Files** 캔버스가 열려 있지 않으면 검토 패널에서 **+**, **File**을 차례로 선택합니다. 2. `.github/skills/quality-checks/SKILL.md`를 검색합니다. @@ -40,32 +40,29 @@ Tailspin Toys 팀이 테스트와 린터 실행을 위해 만든 `quality-checks ## 변경 전 스킬 실행 -스킬은 슬래시(`/`) 명령으로 직접 호출하거나 자연어로 호출할 수 있습니다. 설명에는 테스트나 린트 실행 요청이 있을 때마다 이 스킬을 사용한다고 명시되어 있습니다. Copilot에 테스트 실행을 요청하여 스킬을 실행합니다. +스킬은 슬래시(`/`) 명령으로 직접 호출하거나 자연어로 호출할 수 있습니다. 스킬의 세 가지 검사를 실행하도록 Copilot에 요청합니다. 1. 모드 드롭다운에서 **Interactive**를 선택하여 Copilot이 해당 모드인지 확인합니다. -2. 다음 프롬프트로 Copilot에 테스트와 린터 실행을 요청합니다. 그러면 스킬이 호출됩니다. +2. 다음 프롬프트로 스킬을 호출합니다. ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. 마지막에 표시되는 보고서를 확인합니다. ## 보고서 사용자 지정 -실행한 테스트, 성공률과 실패율, 실행 시간을 보여 주는 더 나은 보고서를 원합니다. Copilot이 이 보고서를 만들도록 스킬을 업데이트합니다. +무엇을 실행했는지, 성공했는지, 도구가 실제로 무엇을 보고했는지 보여 주는 더 나은 보고서를 원합니다. 이 보고서를 생성하도록 스킬을 업데이트합니다. 1. **Files** 캔버스로 돌아갑니다. 2. 아직 열려 있지 않으면 `.github/skills/quality-checks/SKILL.md`를 엽니다. -3. 파일 아래쪽의 **Results output formatting** 헤더를 찾습니다. -4. 해당 헤더 바로 아래에 다음 내용을 추가하여 원하는 형식으로 결과가 표시되게 합니다. +3. 파일 끝에 다음 섹션을 추가합니다. ```markdown - Upon completion of all tests, generate a report that provides a quick overview of both success and failure of the tests, and how long they took to ran. In particular, we need sections for: + ## Results output formatting - - Unit tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - End to end tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - Linting, number of lines scanned, number of violations, and the percentage of lines of code that meet the linting requirements. + Upon completion, report each command that ran and whether it passed, failed, or was blocked. Include test counts, durations, errors, warnings, and other metrics only when the tool reports them. Identify the next action for any failure or blocker, and never describe a skipped or incomplete check as passed. ``` 파일이 자동으로 저장됩니다. @@ -75,10 +72,10 @@ Tailspin Toys 팀이 테스트와 린터 실행을 위해 만든 `quality-checks 변경 사항을 적용했으므로 같은 프롬프트를 사용하여 스킬을 실행해 봅니다. 1. 모드 드롭다운에서 **Interactive**를 선택하여 Copilot이 해당 모드인지 확인합니다. -2. 다음 프롬프트로 Copilot에 테스트와 린터 실행을 요청합니다. 그러면 스킬이 호출됩니다. +2. 다음 프롬프트로 스킬을 호출합니다. ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. 마지막에 표시되는 보고서를 확인합니다. @@ -87,7 +84,7 @@ Tailspin Toys 팀이 테스트와 린터 실행을 위해 만든 `quality-checks 기존 에이전트 스킬을 사용자 지정하고 사용했습니다. 이 레슨에서는 다음 작업을 수행했습니다. -- `quality-checks` 스킬과 함께 제공되는 스크립트를 살펴봤습니다. +- 단위 테스트, 린트, 타입 검사를 위한 `quality-checks` 스킬을 살펴봤습니다. - 결과 형식을 사용자 지정했습니다. - 스킬을 실행하고 출력을 검토했습니다. diff --git a/docs/pt-br/real-world-development/app/10-review.md b/docs/pt-br/real-world-development/app/10-review.md index 7ad83349..d1732bd2 100644 --- a/docs/pt-br/real-world-development/app/10-review.md +++ b/docs/pt-br/real-world-development/app/10-review.md @@ -3,7 +3,7 @@ title: "Lição 10 - Encerramento e próximos passos" description: "Recapitule o fluxo do aplicativo, os dois marcos de PR, os exercícios de canvas e as práticas reutilizáveis de qualidade e explore outros recursos." authors: - geektrainer -lastUpdated: 2026-07-09 +lastUpdated: 2026-09-29 --- Você usou o aplicativo GitHub Copilot em um fluxo contínuo da Tailspin Toys. Você: @@ -11,7 +11,7 @@ Você usou o aplicativo GitHub Copilot em um fluxo contínuo da Tailspin Toys. V - conectou um repositório, explorou o espaço de trabalho do aplicativo e o backlog predefinido e experimentou um chat rápido. - iniciou uma sessão específica de avaliação por estrelas, revisou o resultado em um canvas de navegador e fez manualmente o merge do primeiro pull request (PR). - começou pela issue de filtragem, definiu a abordagem no modo **Plan**, desenvolveu-a no modo **Autopilot** e a revisou no modo **Interactive**. -- orientou o agente com instruções personalizadas e depois personalizou a skill `quality-checks` existente e a usou para executar lint, testes de unidade, testes de ponta a ponta e verificações de tipos. +- orientou o agente com instruções personalizadas e depois personalizou a skill `quality-checks` existente e a usou para executar testes de unidade, lint e verificações de tipos. - adicionou o servidor do Model Context Protocol (MCP) do Playwright e o usou para explorar a filtragem em um navegador real. - criou e selecionou um agente personalizado QA para avaliar requisitos, cobertura, resultados dos scripts da skill e evidências do navegador. - revisou toda a alteração de filtragem e autorizou o **Agent Merge** no segundo PR. @@ -28,7 +28,7 @@ Desde o planejamento da filtragem até a abertura do PR, você usou a mesma sess ## Diferentes tipos de verificação -Você verificou o código de várias formas: testes automatizados, sua própria inspeção no navegador e a exploração do navegador pelo Copilot via MCP. A skill quality-checks executou as verificações do projeto e apresentou os resultados no novo formato. O QA reuniu esses resultados com uma revisão dos requisitos e da cobertura de testes antes do PR. +Você verificou o código de várias formas: testes automatizados, sua própria inspeção no navegador e a exploração do navegador pelo Copilot via MCP. A skill `quality-checks` executou testes de unidade, lint e verificações de tipos e apresentou os resultados no novo formato. O QA reuniu esses resultados com uma revisão dos requisitos e da cobertura de testes antes do PR. Os testes adicionados devem cobrir lacunas reais; uma execução de QA que não precisa de testes novos pode estar correta. Ferramentas ausentes, verificações ignoradas e falhas são bloqueios visíveis, não aprovações. Revise código e evidências antes de autorizar o merge e atualize as evidências afetadas após alterações. diff --git a/docs/pt-br/real-world-development/app/5-agent-skills.md b/docs/pt-br/real-world-development/app/5-agent-skills.md index 6b1f163c..a8dc7412 100644 --- a/docs/pt-br/real-world-development/app/5-agent-skills.md +++ b/docs/pt-br/real-world-development/app/5-agent-skills.md @@ -3,7 +3,7 @@ title: "Lição 5 - Personalizar e usar uma skill quality-checks" description: "Explore a skill quality-checks existente, personalize o formato do relatório e use-a para validar a filtragem." authors: - geektrainer -lastUpdated: 2026-09-11 +lastUpdated: 2026-09-29 --- Escrever código envolve mais do que apenas escrever código. Conseguimos validar manualmente que o código funciona e usamos arquivos de instruções para garantir que ele siga nossos padrões. Mas e os testes? O lint? Todas as outras partes da integração contínua (CI)? @@ -12,13 +12,13 @@ Para esses tipos de tarefa, as **skills de agente** são a melhor opção! As sk Nesta lição, você vai: -- explorar a skill `quality-checks` existente e os scripts incluídos nela. +- explorar a skill `quality-checks` existente. - personalizar o formato dos resultados. - executar a skill e revisar sua saída. ## Cenário -A Tailspin Toys tem um conjunto de testes de unidade e de ponta a ponta que sempre precisam ser executados antes da criação de qualquer pull request (PR). Como você pode imaginar, é importante garantir que esses testes sejam executados de forma correta e consistente. A equipe já criou uma skill de agente para executar esses testes, mas quer melhorar a saída para facilitar a leitura. +A Tailspin Toys usa a skill `quality-checks` para testes de unidade, lint e verificações de tipos. A equipe quer melhorar o relatório para facilitar a leitura dos resultados. ## Instruções, scripts e recursos @@ -31,7 +31,7 @@ As skills podem ficar na pasta `.github/skills` de um projeto para se tornarem u ## Explorar a skill -Vamos explorar a skill criada pela equipe da Tailspin Toys para executar testes e linters, chamada `quality-checks`. +Vamos explorar a skill criada pela equipe da Tailspin Toys para executar testes de unidade, lint e verificações de tipos, chamada `quality-checks`. 1. Se você ainda não tiver um canvas de **Files** aberto, selecione **+** no painel de revisão e depois **File**. 2. Pesquise `.github/skills/quality-checks/SKILL.md`. @@ -40,32 +40,29 @@ Vamos explorar a skill criada pela equipe da Tailspin Toys para executar testes ## Executar a skill antes de fazer uma alteração -As skills podem ser chamadas diretamente com um comando de barra (`/`) ou por meio de linguagem natural. Como você pode observar na descrição, a skill deve ser usada sempre que houver uma solicitação para executar testes ou lint. Vamos executar a skill pedindo ao Copilot que rode nossos testes! +As skills podem ser chamadas diretamente com um comando de barra (`/`) ou por meio de linguagem natural. Vamos pedir ao Copilot que execute as três verificações da skill. 1. Confirme que o Copilot está no modo **Interactive**, selecionando-o no menu suspenso de modo. -2. Use o prompt a seguir para pedir ao Copilot que execute os testes e o linter, o que chamará a skill: +2. Use o prompt a seguir para chamar a skill: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Observe o relatório ao final. ## Personalizar o relatório -Queremos um relatório melhor, que mostre os testes executados, as taxas de sucesso e falha e o tempo de execução. Vamos atualizar a skill para que o Copilot crie esse relatório! +Queremos um relatório melhor, que mostre o que foi executado, se teve sucesso e o que as ferramentas realmente informaram. Vamos atualizar a skill para criar esse relatório! 1. Volte ao canvas de **Files**. 2. Se ainda não estiver aberto, abra `.github/skills/quality-checks/SKILL.md`. -3. Localize o cabeçalho **Results output formatting** na parte inferior do arquivo. -4. Logo abaixo desse cabeçalho, adicione o seguinte para garantir que os resultados sejam exibidos de acordo com nossas especificações: +3. Adicione a seção a seguir ao final do arquivo: ```markdown - Upon completion of all tests, generate a report that provides a quick overview of both success and failure of the tests, and how long they took to ran. In particular, we need sections for: + ## Results output formatting - - Unit tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - End to end tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - Linting, number of lines scanned, number of violations, and the percentage of lines of code that meet the linting requirements. + Upon completion, report each command that ran and whether it passed, failed, or was blocked. Include test counts, durations, errors, warnings, and other metrics only when the tool reports them. Identify the next action for any failure or blocker, and never describe a skipped or incomplete check as passed. ``` O arquivo será salvo automaticamente. @@ -75,10 +72,10 @@ O arquivo será salvo automaticamente. Com a alteração feita, vamos vê-la em ação! Usaremos exatamente o mesmo prompt de antes. 1. Confirme que o Copilot está no modo **Interactive**, selecionando-o no menu suspenso de modo. -2. Use o prompt a seguir para pedir ao Copilot que execute os testes e o linter, o que chamará a skill: +2. Use o prompt a seguir para chamar a skill: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Observe o relatório ao final. @@ -87,7 +84,7 @@ Com a alteração feita, vamos vê-la em ação! Usaremos exatamente o mesmo pro Você personalizou e usou uma skill de agente existente. Nesta lição, você: -- explorou a skill `quality-checks` e os scripts incluídos nela. +- explorou a skill `quality-checks` para testes de unidade, lint e verificações de tipos. - personalizou o formato dos resultados. - executou a skill e revisou sua saída. diff --git a/docs/real-world-development/app/10-review.md b/docs/real-world-development/app/10-review.md index 8d0eff6f..20db2964 100644 --- a/docs/real-world-development/app/10-review.md +++ b/docs/real-world-development/app/10-review.md @@ -3,7 +3,7 @@ title: "Lesson 10 - Wrap-up and next steps" description: "Recap the App workflow, two PR milestones, canvas exercises, and reusable quality practices, then explore further resources." authors: - geektrainer -lastUpdated: 2026-07-09 +lastUpdated: 2026-09-29 --- You used the GitHub Copilot app across a continuous Tailspin Toys workflow. You: @@ -11,7 +11,7 @@ You used the GitHub Copilot app across a continuous Tailspin Toys workflow. You: - connected a repository, explored the app's workspace and seeded backlog, and tried a quick chat. - started a focused star-rating session, reviewed the result in a browser canvas, and manually merged your first pull request (PR). - started from the filtering issue, defined the approach in **Plan** mode, built it in **Autopilot** mode, and reviewed it in **Interactive** mode. -- guided the agent with custom instructions, then customized the existing `quality-checks` skill and used it to run lint, unit tests, end-to-end tests, and type checks. +- guided the agent with custom instructions, then customized the existing `quality-checks` skill and used it to run unit tests, lint, and type checks. - added the Playwright Model Context Protocol (MCP) server and used it to explore filtering in a real browser. - created and selected a quality assurance (QA) custom agent to assess requirements, coverage, skill results, and browser evidence. - reviewed the complete filtering change and authorized **Agent Merge** for your second PR. @@ -28,7 +28,7 @@ From planning filtering through opening its PR, you used the same session, workt ## Different kinds of verification -You checked the code in several ways: automated tests, your own browser inspection, and Copilot's browser exploration through MCP. The quality-checks skill ran the project checks and reported them in your new format. QA brought those results together with a review of requirements and test coverage before the PR. +You checked the code in several ways: automated tests, your own browser inspection, and Copilot's browser exploration through MCP. The `quality-checks` skill ran unit tests, lint, and type checks and reported them in your new format. QA brought those results together with a review of requirements and test coverage before the PR. Tests added should close genuine gaps; a QA run that needs no new tests can be correct. Missing tools, skipped checks, and failures are visible blockers, not passes. Review code and evidence before authorizing merge, and refresh affected evidence after changes. diff --git a/docs/real-world-development/app/5-agent-skills.md b/docs/real-world-development/app/5-agent-skills.md index e4565ceb..bcec7ea8 100644 --- a/docs/real-world-development/app/5-agent-skills.md +++ b/docs/real-world-development/app/5-agent-skills.md @@ -3,7 +3,7 @@ title: "Lesson 5 - Customize and use a quality-checks skill" description: "Explore the existing quality-checks skill, customize its report format, and use it to validate filtering." authors: - geektrainer -lastUpdated: 2026-09-11 +lastUpdated: 2026-09-29 --- There's more to writing code that just writing code. We've been able to validate the code works manually, and used instructions files to ensure it follows our standards. But how about testing? Linting? All the other parts of continuous integration (CI)? @@ -12,13 +12,13 @@ For these types of tasks, **agent skills** are the best fit! Skills help Copilot In this lesson, you will: -- explore the existing `quality-checks` skill and its bundled scripts. +- explore the existing `quality-checks` skill. - customize the format of its results. - run the skill and review its output. ## Scenario -Tailspin Toys has a collection of unit and end to end tests which always need to be run before any pull request (PR) is made. As you might expect, ensuring these are run correctly and consistently is important. The team has already created an agent skill to run these tests, but they want to enhance the output for better readability. +Tailspin Toys uses the `quality-checks` skill for unit tests, lint, and type checks. The team wants to improve the report to make the results easier to read. ## Instructions, scripts, and resources @@ -31,7 +31,7 @@ Skills can reside in a projects `.github/skills` folder to become a repository a ## Explore the skill -Let's explore the skill the Tailspin Toys team created for running tests and linters, named `quality-checks`. +Let's explore the skill the Tailspin Toys team created for running unit tests, lint, and type checks, named `quality-checks`. 1. If you don't already have a **Files** canvas open, in the review panel, select **+**, then **File** 2. Search for `.github/skills/quality-checks/SKILL.md`. @@ -40,32 +40,29 @@ Let's explore the skill the Tailspin Toys team created for running tests and lin ## Run the skill before making a change -Skills are callable directly via a slash (`/`) command, or by using natural language to call the skill. If you notice the description, it highlights the fact the skill is to be used whenever a request is made to run tests or linting. Let's run the skill by asking Copilot to run our tests! +Skills are callable directly via a slash (`/`) command, or by using natural language to call the skill. Let's ask Copilot to run the skill's three checks. 1. Ensure Copilot is in **Interactive** mode by selecting it from the mode dropdown. -2. Use the following prompt to ask Copilot to run the tests and linter, which will call the skill: +2. Use the following prompt to call the skill: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Note the report at the end. ## Customize the report -OK, we'd like to get a better report that shows us the tests that ran, success/failure rates, and how long they took to run. Let's update our skill to have Copilot create that report for us! +OK, we'd like a better report that tells us what ran, whether it succeeded, and what the tools actually reported. Let's update our skill to create that report! 1. Return to the **Files** canvas. 2. If not already open, open `.github/skills/quality-checks/SKILL.md`. -3. Find the header at the bottom of the file that reads **Results output formatting**. -4. Just below that header, add the following to ensure our results are displayed to our specifications: +3. Add the following section to the end of the file: ```markdown - Upon completion of all tests, generate a report that provides a quick overview of both success and failure of the tests, and how long they took to ran. In particular, we need sections for: + ## Results output formatting - - Unit tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - End to end tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - Linting, number of lines scanned, number of violations, and the percentage of lines of code that meet the linting requirements. + Upon completion, report each command that ran and whether it passed, failed, or was blocked. Include test counts, durations, errors, warnings, and other metrics only when the tool reports them. Identify the next action for any failure or blocker, and never describe a skipped or incomplete check as passed. ``` The file will automatically be saved. @@ -75,10 +72,10 @@ The file will automatically be saved. With our change made, let's see it in action! We'll use the exact same prompt as before. 1. Ensure Copilot is in **Interactive** mode by selecting it from the mode dropdown. -2. Use the following prompt to ask Copilot to run the tests and linter, which will call the skill: +2. Use the following prompt to call the skill: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Note the report at the end. @@ -87,7 +84,7 @@ With our change made, let's see it in action! We'll use the exact same prompt as You've customized and used an existing agent skill. In this lesson, you: -- explored the `quality-checks` skill and its bundled scripts. +- explored the `quality-checks` skill for unit tests, lint, and type checks. - customized the format of its results. - ran the skill and reviewed its output. diff --git a/docs/real-world-development/cli/10-review.md b/docs/real-world-development/cli/10-review.md index 5b46d42f..4e78e85c 100644 --- a/docs/real-world-development/cli/10-review.md +++ b/docs/real-world-development/cli/10-review.md @@ -3,7 +3,7 @@ title: "Lesson 10 - Wrap-up and next steps" description: "Recap the Copilot CLI workflow, two pull requests, reusable customizations, and further resources." authors: - geektrainer -lastUpdated: 2026-09-18 +lastUpdated: 2026-09-29 --- You used GitHub Copilot CLI across a continuous Tailspin Toys workflow. You: @@ -11,7 +11,7 @@ You used GitHub Copilot CLI across a continuous Tailspin Toys workflow. You: - prepared a Codespace, installed Copilot CLI, explored the project, and found the seeded filtering issue. - added star ratings, reviewed the result in a forwarded browser, and manually merged your first pull request (PR). - started from the filtering issue, defined the approach in Plan mode, built it in Autopilot mode, and reviewed it in Interactive mode. -- guided the agent with custom instructions, then customized the existing `quality-checks` skill and used it to run the project checks. +- guided the agent with custom instructions, then customized the existing `quality-checks` skill and used it to run unit tests, lint, and type checks. - added the Playwright Model Context Protocol (MCP) server and used it to explore filtering in a real browser. - created and selected a quality assurance (QA) custom agent to assess requirements, coverage, skill results, and browser evidence. - reviewed the complete filtering change and authorized Agent Merge for the filtering PR. @@ -28,7 +28,7 @@ From planning filtering through opening its PR, you used the same conversation a ## Different kinds of verification -You checked the code in several ways: automated tests, your own browser inspection, and Copilot's browser exploration through MCP. The `quality-checks` skill ran the project checks and reported them in your new format. QA brought those results together with a review of requirements and test coverage before the PR. +You checked the code in several ways: automated tests, your own browser inspection, and Copilot's browser exploration through MCP. The `quality-checks` skill ran unit tests, lint, and type checks and reported them in your new format. QA brought those results together with a review of requirements and test coverage before the PR. Tests added should close genuine gaps; a QA run that needs no new tests can be correct. Review code and evidence before authorizing merge, and refresh affected evidence after changes. diff --git a/docs/real-world-development/cli/5-agent-skills.md b/docs/real-world-development/cli/5-agent-skills.md index e26f219f..9626ed67 100644 --- a/docs/real-world-development/cli/5-agent-skills.md +++ b/docs/real-world-development/cli/5-agent-skills.md @@ -3,7 +3,7 @@ title: "Lesson 5 - Customize and use a quality-checks skill" description: "Explore the existing quality-checks skill, customize its report format, and use it to validate filtering." authors: - geektrainer -lastUpdated: 2026-09-18 +lastUpdated: 2026-09-29 --- There's more to writing code than just writing code. We've been able to validate the code works manually and used instruction files to ensure it follows our standards. But how about testing? Linting? All the other parts of continuous integration (CI)? @@ -18,7 +18,7 @@ In this lesson, you will: ## Scenario -Tailspin Toys has a collection of unit and end to end tests which always need to be run before any pull request (PR) is made. As you might expect, ensuring these are run correctly and consistently is important. The team has already created an agent skill to run these tests, but they want to enhance the output for better readability. +Tailspin Toys uses the `quality-checks` skill for unit tests, lint, and type checks. The team wants to improve the report to make the results easier to read. ## Instructions, scripts, and resources @@ -31,7 +31,7 @@ Skills can reside in a project's `.github/skills` folder to become a repository ## Explore the skill -Let's explore the skill the Tailspin Toys team created for running tests and linters, named `quality-checks`. +Let's explore the skill the Tailspin Toys team created for running unit tests, lint, and type checks, named `quality-checks`. 1. Return to your Codespace. In the Codespaces editor, open `.github/skills/quality-checks/SKILL.md`. 2. Read the `name` and `description` at the top. The description helps Copilot understand when to call the skill. @@ -40,20 +40,20 @@ Let's explore the skill the Tailspin Toys team created for running tests and lin ## Run the skill before making a change -Skills are callable directly through Copilot CLI or by using natural language. Let's run the skill by asking Copilot to run our tests! +Skills are callable directly through Copilot CLI or by using natural language. Let's ask Copilot to run the skill's three checks. 1. Return to the filtering conversation in Interactive mode. 2. Use the following prompt: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Note the report at the end. ## Customize the report -OK, we'd like a better report that tells us what ran, whether it succeeded, and what the tools actually reported. Let's update our skill to create that report for us! +OK, we'd like a better report that tells us what ran, whether it succeeded, and what the tools actually reported. Let's update our skill to create that report! 1. Return to `.github/skills/quality-checks/SKILL.md`. 2. Add the following section to the end of the file: @@ -79,7 +79,7 @@ With our change made, let's see it in action! Copilot CLI can reload edited skil 2. Use the exact same prompt as before: ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. Note the report at the end and compare it with the first report. @@ -88,7 +88,7 @@ With our change made, let's see it in action! Copilot CLI can reload edited skil You've customized and used an existing agent skill. In this lesson, you: -- explored the existing `quality-checks` skill. +- explored the `quality-checks` skill for unit tests, lint, and type checks. - customized the format of its results. - reloaded and ran the skill. diff --git a/docs/zh-cn/real-world-development/app/10-review.md b/docs/zh-cn/real-world-development/app/10-review.md index 3ca1e22d..5b21ea1c 100644 --- a/docs/zh-cn/real-world-development/app/10-review.md +++ b/docs/zh-cn/real-world-development/app/10-review.md @@ -3,7 +3,7 @@ title: "第 10 课 - 总结与后续步骤" description: "回顾 App 工作流、两个 PR 里程碑、画布练习和可复用质量实践，再探索更多资源。" authors: - geektrainer -lastUpdated: 2026-07-09 +lastUpdated: 2026-09-29 --- 你在一套连续的 Tailspin Toys 工作流中使用了 GitHub Copilot app。你： @@ -11,7 +11,7 @@ lastUpdated: 2026-07-09 - 连接了存储库，探索了应用工作区和模板创建的待办事项，并尝试了快速聊天。 - 启动范围明确的星级评分会话，在浏览器画布中审查结果，并手动合并了第一个拉取请求 (PR)。 - 从筛选功能议题启动会话，在 **Plan** 模式中确定方案，在 **Autopilot** 模式中构建，再在 **Interactive** 模式中审查。 -- 使用自定义指令引导智能体，再自定义现有的 `quality-checks` 技能，用它运行 lint、单元测试、端到端测试和类型检查。 +- 使用自定义指令引导智能体，再自定义现有的 `quality-checks` 技能，用它运行单元测试、lint 和类型检查。 - 添加 Playwright 模型上下文协议 (MCP) 服务器，并用它在真实浏览器中探索筛选功能。 - 创建并选择 QA 自定义智能体，以评估需求、覆盖情况、技能脚本结果和浏览器证据。 - 审查完整的筛选功能更改，并为第二个 PR 授权 **Agent Merge**。 @@ -28,7 +28,7 @@ lastUpdated: 2026-07-09 ## 不同类型的验证 -你通过多种方式检查了代码：自动化测试、自己的浏览器检查，以及 Copilot 通过 MCP 进行的浏览器探索。quality-checks 技能运行项目检查，并按新的格式报告结果。创建 PR 前，QA 将这些结果与需求和测试覆盖情况的审查结合起来。 +你通过多种方式检查了代码：自动化测试、自己的浏览器检查，以及 Copilot 通过 MCP 进行的浏览器探索。`quality-checks` 技能运行单元测试、lint 和类型检查，并按新的格式报告结果。创建 PR 前，QA 将这些结果与需求和测试覆盖情况的审查结合起来。 新增测试应填补真实缺口；不需要新增测试的 QA 运行也可能完全正确。缺少工具、跳过检查和失败都是需要明确报告的阻塞项，而不是通过。授权合并前审查代码和证据，并在改动后更新受影响的证据。 diff --git a/docs/zh-cn/real-world-development/app/5-agent-skills.md b/docs/zh-cn/real-world-development/app/5-agent-skills.md index a1f04497..e81d9cee 100644 --- a/docs/zh-cn/real-world-development/app/5-agent-skills.md +++ b/docs/zh-cn/real-world-development/app/5-agent-skills.md @@ -3,7 +3,7 @@ title: "第 5 课 - 自定义并使用 quality-checks 技能" description: "探索现有的 quality-checks 技能，自定义其报告格式，并用它验证筛选功能。" authors: - geektrainer -lastUpdated: 2026-09-11 +lastUpdated: 2026-09-29 --- 编写代码不只是写出代码。我们已经手动验证代码能够运行，并使用指令文件确保它符合标准。但测试、lint 以及持续集成 (CI) 的其他环节又该如何处理？ @@ -12,13 +12,13 @@ lastUpdated: 2026-09-11 在本课中，将： -- 探索现有的 `quality-checks` 技能及其配套脚本。 +- 探索现有的 `quality-checks` 技能。 - 自定义结果格式。 - 运行技能并审查输出。 ## 场景 -Tailspin Toys 有一组单元测试和端到端测试，每次创建拉取请求 (PR) 前都必须运行。确保正确且一致地运行这些测试非常重要。团队已创建一个运行这些测试的智能体技能，但希望增强输出，提高可读性。 +Tailspin Toys 使用 `quality-checks` 技能运行单元测试、lint 和类型检查。团队希望改进报告，让结果更易于阅读。 ## 指令、脚本和资源 @@ -38,32 +38,29 @@ Tailspin Toys 有一组单元测试和端到端测试，每次创建拉取请求 ## 更改前运行技能 -技能既可通过斜杠 (`/`) 命令直接调用，也可使用自然语言调用。说明指出，只要请求运行测试或 lint，就应使用此技能。下面要求 Copilot 运行测试，以调用该技能。 +技能既可通过斜杠 (`/`) 命令直接调用，也可使用自然语言调用。下面要求 Copilot 运行该技能的三类检查。 1. 从模式下拉菜单选择 **Interactive**，确保 Copilot 处于该模式。 -2. 使用以下提示词让 Copilot 运行测试和 linter，从而调用该技能： +2. 使用以下提示词调用该技能： ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. 查看最后生成的报告。 ## 自定义报告 -现在，希望报告更清晰地显示所运行的测试、成功和失败率以及运行时长。下面更新技能，让 Copilot 生成该报告。 +现在，希望报告更清晰地显示运行了哪些检查、是否成功，以及工具实际报告了什么。下面更新技能，让它生成该报告。 1. 返回 **Files** 画布。 2. 如果尚未打开，请打开 `.github/skills/quality-checks/SKILL.md`。 -3. 找到文件底部的 **Results output formatting** 标题。 -4. 在该标题下方添加以下内容，确保按指定格式显示结果： +3. 将以下章节添加到文件末尾： ```markdown - Upon completion of all tests, generate a report that provides a quick overview of both success and failure of the tests, and how long they took to ran. In particular, we need sections for: + ## Results output formatting - - Unit tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - End to end tests, total number of tests, number succeeded, number failed, a percentage thereof, and the amount of time testing took. - - Linting, number of lines scanned, number of violations, and the percentage of lines of code that meet the linting requirements. + Upon completion, report each command that ran and whether it passed, failed, or was blocked. Include test counts, durations, errors, warnings, and other metrics only when the tool reports them. Identify the next action for any failure or blocker, and never describe a skipped or incomplete check as passed. ``` 文件会自动保存。 @@ -73,10 +70,10 @@ Tailspin Toys 有一组单元测试和端到端测试，每次创建拉取请求 完成更改后，使用与之前完全相同的提示词查看效果。 1. 从模式下拉菜单选择 **Interactive**，确保 Copilot 处于该模式。 -2. 使用以下提示词让 Copilot 运行测试和 linter，从而调用该技能： +2. 使用以下提示词调用该技能： ```plaintext - Run the tests and linters. + Run the quality-checks skill for unit tests, lint, and type checks. ``` 3. 查看最后生成的报告。 @@ -85,7 +82,7 @@ Tailspin Toys 有一组单元测试和端到端测试，每次创建拉取请求 你已自定义并使用现有智能体技能。本课中，你： -- 探索了 `quality-checks` 技能及其配套脚本。 +- 探索了用于单元测试、lint 和类型检查的 `quality-checks` 技能。 - 自定义了结果格式。 - 运行技能并审查了输出。