メニュー
Autonomous end-to-end feature development with phased validation gates. Use when building major new functionality or adding substantial features.
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。
SOC 職業分類に基づく
Drives implementation outside-in: starts from an acceptance test for user-visible behavior, then works inward layer by layer, stubbing what doesn't exist yet. Use when building a feature across collaborating components to let design emerge from usage rather than speculation.
End-to-end GitHub issue lifecycle: pick up an issue, create a worktree, build the fix or feature, open a PR, watch CI, and iterate until green. Use when picking up, fixing, or implementing a GitHub issue or ticket.
Decomposes work into ordered, shippable slices. Use when breaking down features, planning implementation order, or slicing work into deliverable increments.
Test-driven development (TDD) process used when writing code. Use whenever you are adding any new code, unless the user explicitly asks to skip TDD or the code is exploratory/spike.
Refactoring process. Invoke immediately when user or document mentions refactoring, or proactively when code gets too complex or messy.
Defines acceptance criteria from requirements through persona analysis and refinement. Use when clarifying requirements, defining what done looks like, or writing acceptance criteria.
| name | feature-development |
| description | Autonomous end-to-end feature development with phased validation gates. Use when building major new functionality or adding substantial features. |
STARTER_CHARACTER = 🏗️
Structured workflow for complex features. Each step invokes a focused skill with its own gate. No step may be skipped. No gate may be skipped.
Invoke /acceptance-criteria. Write criteria to playground/{feature-name}-criteria.md.
Use a short, hyphenated feature name (e.g., user-auth, invoice-export) consistently across all playground files.
If modifying existing code, invoke /scout-codebase. Write scout report to playground/{feature-name}-scout.md. Once validated, scout report improvements become preparatory scenarios in step 3.
If greenfield, review the surrounding codebase for conventions, patterns, test infrastructure, and architecture the new code must align with.
Invoke /sketch-slices. Write sketch to playground/{feature-name}-sketch.md.
Invoke /atdd for each scenario from the sketch — preparatory first, then feature scenarios.
Invoke /harden on all files touched.
Invoke /verify-criteria against playground/{feature-name}-criteria.md.
Delete all playground/{feature-name}-* files. These are working artifacts, not project files — they must not be committed.
Stay autonomous, but stop and ask when:
Don't ask about: routine implementation, refactoring choices, test structure, naming.
