Developer-agent discipline for test judgment, validation evidence, and TDD-required task escalation.
Scanned 5/28/2026
Install via CLI
openskills install GobbyAI/gobby---
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
---
# Development Discipline
Use this for every developer-agent task.
## Required Judgment
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:
- Exact validation commands run.
- Result of each command.
- Why those commands cover the changed behavior.
- Any test gap that remains, with the reason it is acceptable.
## Test Changes
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:
```bash
uv run gobby test-quality audit <paths> --baseline .gobby/test-quality-baseline.json --fail-on-new --min-severity high
```
## TDD-Required Tasks
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.
No comments yet. Be the first to comment!