メニュー
Use when completing a TDD phase or before committing — self-discipline checkpoints the software-engineer runs against their own output. Not a review contract. The reviewer verifies artifacts independently.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/SebastienDegodez/meetup-coding-with-ai --skill craft-disciplineコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Use when running mutation testing, killing mutants, verifying test quality, checking mutation score, or analyzing survivors after the test baseline is green
Use when selecting architecture patterns for a new feature, performing Event Modeling, defining bounded contexts, choosing DDD tactical patterns, evaluating pattern fitness, or understanding how patterns compose. Covers Event Modeling methodology, DDD strategic design, DDD tactical patterns, Clean Architecture, CQRS, and Event Sourcing.
Use when reviewing DESIGN artefacts (event models, ADRs, component diagrams, context maps, interface contracts) for quality, DDD compliance, architectural correctness, and prohibition of negative or baseline-restating ADRs. Contains gate definitions and scoring rubric for the solution-architect-reviewer lenses.
SOC 職業分類に基づく
SKILL.md を表示中
| name | craft-discipline |
| description | Use when completing a TDD phase or before committing — self-discipline checkpoints the software-engineer runs against their own output. Not a review contract. The reviewer verifies artifacts independently. |
10 self-discipline checkpoints for the software-engineer.
Run at every COMMIT & VERIFY phase, before committing.
What this skill is NOT: a review contract. The reviewer does not read this skill. It audits artifacts independently through its own gates.
Execute in order. Each checkpoint must pass before proceeding.
dotnet test --filter "Category=Acceptance"
The acceptance test targeted by this iteration MUST pass. No [Skip].
dotnet test
Zero red tests. Zero ignored tests.
dotnet build
All projects compile without warnings. Treat warnings as errors.
Verify that the linter/analyzer reports no new findings.
No [Skip], [Ignore], #if false, or disabling comments
in tests. Every test is active.
Check UnitTest files:
A.Fake<>(), Mock<>(), Substitute.For<>()
on a Domain or Application type.Test names, variables, and assertions use business vocabulary
(see the project's FR→EN lexicon). No test1, data, ProcessData.
S7 DETERMINISTIC TOOL BRIDGE — execute via terminal, not prose.
runInTerminal:dotnet stryker \
--project <Domain-or-Application.csproj> \
-tp <UnitTests.csproj> \
--since:main \
--break-at 100 \
-r json -r cleartext
Zero surviving mutants in Domain and Application (equivalent mutants documented if accepted).
Load the mutation-testing skill for full workflow.
Format: type(scope): subject
Types: feat, fix, refactor, test, docs, chore.
Verify the 9 rules (see references/object-calisthenics.md). Applicable to Domain code only.
Multiple input variants for the same behavior MUST be a single parameterized test
([Theory]/[InlineData] in .NET, @ParameterizedTest in Java, pytest.mark.parametrize in Python),
not duplicated test methods. One test method per behavior, one row per case.
| TDD Phase | Applicable Checkpoints |
|---|---|
| PREPARE | None |
| RED | None |
| SYNTHESIZE-GREEN | C3 only (build) |
| COMMIT & VERIFY | All (C1-C11) |
--ignore.