Skill1.9k repo starsupdated 1mo ago

test-driven-development

This Claude Code skill enforces strict test-driven development discipline by requiring the RED-GREEN-REFACTOR cycle in all BUILD workflows. It mandates that failing tests be written first with exit code 1, followed by minimal implementation with exit code 0, then refactoring while maintaining passing tests. The skill prohibits watch mode and deferred testing, uses run mode exclusively with timeout guards, and requires exit code evidence at each phase to prevent incomplete cycles and hanging processes.

View source Repository: babysitter

Install in Claude Code

Copy

git clone --depth 1 https://github.com/a5c-ai/babysitter /tmp/test-driven-development && cp -r /tmp/test-driven-development/library/methodologies/cc10x/skills/test-driven-development ~/.claude/skills/test-driven-development

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

## Non-Negotiable Rules

- Always use run mode (`CI=true npm test` or `--run` flag)
- NEVER use watch mode (prevents hanging processes)
- Use timeout guards (`timeout 60s`) as backup
- Record exit codes as evidence at each phase
- If tests fail 3 consecutive times in GREEN, report failure status
- Never skip RED phase (failing test must exist before implementation)
- Never defer tests to "later" -- TDD means tests first

## Scope Discipline

- If implementation requires >3 file changes, flag for scope review
- Architectural choices require user approval unless pre-approved in plan
- New dependencies require user approval

## When to Use

- Every feature implementation in BUILD workflow
- Every bug fix in DEBUG workflow (regression test)

## Agents Used

- `component-builder` (primary consumer)
- `bug-investigator` (regression tests)

More from this repository

agent-coordinationSkill

Coordinate Crew (persistent) and Polecat (transient) agents using Gas Town's hook-based work distribution and GUPP principle.

agent-dispatchSkill

architecture-designSkill

architecture-patternsSkill

System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.

assimilate-popular-workflowsSkill

This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable processes, babysitter plugins, and reusable procedural insights. Searches GitHub for SKILL.md files, classifies repos by archetype, and maintains structured research under docs/reference-repos/.

audit-trailSkill

babysitSkill

babysit-babysitter-issuesSkill

This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.