ワンクリックで
development-discipline
Developer-agent discipline for test judgment, validation evidence, and TDD-required task escalation.
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。
メニュー
Developer-agent discipline for test judgment, validation evidence, and TDD-required task escalation.
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
Instructions for using gcode CLI for code search and retrieval. Loaded on demand when project has a code index.
Pre-transition checklist for closing or reviewing tasks. Covers fresh verification evidence, commits, and memory gates.
Use when processing CodeRabbit review comments, CodeRabbit CLI reports, or `$gobby coderabbit [findings]` requests.
Use when creating, editing, or validating Gobby skills, especially when a skill must change agent behavior or become discoverable through gobby-skills.
Use when coordinating a full gobby build run for an epic or task, especially when the user assigns the current session as coordinator, asks for a coordination epic, wants build agents/worktrees monitored, or wants gobby build bugs fixed so future runs work unattended.
Router contract for provider-aware Gobby help and installed skill dispatch.
| name | development-discipline |
| description | Developer-agent discipline for test judgment, validation evidence, and TDD-required task escalation. |
| version | 1.0.0 |
| category | core |
| triggers | development discipline, developer validation, test judgment |
| metadata | {"gobby":{"audience":"agent","depth":1}} |
Use this for every developer-agent task.
Before editing, make an explicit test judgment: decide how behavior can be verified. Name the relevant test level: unit, integration, CLI/API, browser/UI, migration/storage, or documented manual check.
Every completion or review handoff must include:
Add or update tests when behavior changes. Skipping tests is acceptable only for pure documentation, mechanical metadata, or code paths that cannot be executed locally; document the reason in the task handoff.
When adding or heavily editing tests, run gobby test-quality audit on touched
test paths. For noisy areas, use:
uv run gobby test-quality audit <paths> --baseline .gobby/test-quality-baseline.json --fail-on-new --min-severity high
If the task has label tdd:required, additional_skills contains
test-driven-development, or validation criteria require TDD evidence, load
test-driven-development before implementation and follow it exactly.