Default test workflow. RED-GREEN-REFACTOR cycle for all new TypeScript code.
Enforces strict test-driven development for TypeScript: writes failing tests first (RED), implements minimal code (GREEN), then refactors. Triggers on any "implement" or "add feature" request to ensure test-first discipline.
/plugin marketplace add settlemint/agent-marketplace/plugin install devtools@settlemintThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/project-setup.mdreferences/test-coverage-patterns.mdreferences/test-data-strategies.mdreferences/test-naming-conventions.mdreferences/test-strategy-checklist.mdworkflows/tdd-cycle.md<essential_principles> The TDD Discipline
TDD is not about testing—it's about design. Writing tests first forces you to think about the API, edge cases, and behavior BEFORE writing implementation code.
Three Laws of TDD:
Coverage Requirements (Non-Negotiable):
| Metric | Minimum | Critical Paths |
|---|---|---|
| Line coverage | 80% | 100% |
| Branch coverage | 75% | 100% |
| Function coverage | 90% | 100% |
Coverage targets are minimum thresholds, not aspirational goals. See references/test-coverage-patterns.md for blocking criteria.
Context Isolation: Each phase (RED, GREEN, REFACTOR) runs with isolated context. The test writer cannot see implementation plans—this ensures genuinely test-first thinking rather than tests designed around anticipated code.
Phase Gates: Do NOT proceed to the next phase until the current phase verification succeeds:
See references/test-strategy-checklist.md for complete phase gate requirements.
</essential_principles>
<quick_start> For any implementation task:
workflows/tdd-cycle.md and follow it exactlyreferences/test-coverage-patterns.md for coverage targets and blocking criteriareferences/test-data-strategies.md for factories, fixtures, and mocksreferences/test-naming-conventions.md for consistent namingreferences/test-strategy-checklist.md for phase gates and governanceInvoke with: Any prompt containing "implement", "add feature", "build", or "create functionality" </quick_start>
<workflow_index>
| Workflow | Purpose |
|---|---|
| tdd-cycle.md | Complete RED-GREEN-REFACTOR cycle for feature implementation |
| </workflow_index> |
<reference_index>
| Reference | Content |
|---|---|
| test-coverage-patterns.md | Coverage targets, blocking criteria, priority analysis, test categories |
| test-naming-conventions.md | Naming conventions, test structure patterns |
| test-data-strategies.md | Factories, fixtures, mocks, determinism patterns |
| test-strategy-checklist.md | Phase gates, test pyramid, coverage matrix, anti-patterns |
| project-setup.md | CLAUDE.md instructions and hook configuration for enforcement |
| </reference_index> |
This skill handles the TDD WORKFLOW (when/what to test). The vitest skill handles TEST SYNTAX (how to write tests). Load both for full coverage. </integration>
<success_criteria> TDD workflow complete when:
should_<expected>_when_<condition> patternThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.