This skill orchestrates full-cycle TDD development by integrating multiple specialized plugins into a cohesive workflow.
From tech-leadnpx claudepluginhub ruslan-korneev/claude-plugins --plugin tech-leadThis skill uses the workspace's default tool permissions.
references/context-handoff.mdreferences/plan-format.mdreferences/plugin-integration.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Guides agent creation for Claude Code plugins with file templates, frontmatter specs (name, description, model), triggering examples, system prompts, and best practices.
This skill orchestrates full-cycle TDD development by integrating multiple specialized plugins into a cohesive workflow.
Use this skill when the user wants to:
Trigger phrases:
┌─────────────────────────────────────────────────────────┐
│ TDD CYCLE │
│ │
│ ┌─────────┐ ┌─────────┐ ┌───────────┐ │
│ │ RED │───▶│ GREEN │───▶│ REFACTOR │──┐ │
│ │ Write │ │ Make │ │ Improve │ │ │
│ │ Failing│ │ Test │ │ Code │ │ │
│ │ Test │ │ Pass │ │ Quality │ │ │
│ └─────────┘ └─────────┘ └───────────┘ │ │
│ ▲ │ │
│ └────────────────────────────────────────┘ │
│ │
└─────────────────────────────────────────────────────────┘
| Phase | Agent | Model | Purpose |
|---|---|---|---|
| Explore | codebase-explorer | sonnet | Fast module discovery |
| Plan | planning-agent | opus | Deep analysis, user questions |
| Execute | execution-agent | opus | TDD implementation |
This workflow integrates with existing plugins:
User Prompt
│
▼
┌─────────────────┐
│ Codebase │ Find relevant modules
│ Explorer │ Understand project structure
└────────┬────────┘
│
▼
┌─────────────────┐
│ Planning │ Ask clarifying questions
│ Agent │ Create development plan
└────────┬────────┘ Define test cases
│
▼
┌─────────────────┐
│ EnterPlanMode │ User reviews and approves
│ (Claude Code) │ the development plan
└────────┬────────┘
│
▼
┌─────────────────┐
│ Execution │ TDD cycle for each test
│ Agent │ Quality gates
└────────┬────────┘ Documentation
│
▼
Completed Feature
Plans include Memory Anchors — structured context that persists across sessions:
---
id: dev-{uuid}
feature: {name}
status: draft | approved | in_progress | completed
---
Anchors capture:
Each TDD phase should be tracked explicitly. Use TaskCreate to make phase transitions visible:
TaskCreate: "RED — Write failing test for <feature>"
→ Write test, verify it fails
→ TaskUpdate: completed
TaskCreate: "GREEN — Minimal implementation for <feature>"
→ Write just enough code to pass
→ TaskUpdate: completed
TaskCreate: "REFACTOR — Clean up <feature> implementation"
→ Improve code quality, tests stay green
→ TaskUpdate: completed
Why: Without explicit separation, phases blur together. Developers skip Red (writing tests after code) or skip Refactor (moving on too quickly). Tracking forces discipline.