AI Dialogue TDD Workflow
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_6bedba2d/tddai.
About this skill
Problem
In routine AI collaboration, the bottleneck is often not generation speed, but output that misses the acceptance criteria: vague requirements, overcomplete first drafts, and no staged validation. tddai maps test-driven development to AI dialogue, asking the user to define success with RED, obtain a minimal acceptable result with GREEN, and refine with REFACTOR.
How It Works
- RED: define acceptance criteria - specify deliverables, constraints, format, counterexamples, and the expected outcome.
- GREEN: reach minimum viable output - produce a usable version that satisfies the basic criteria without overengineering.
- REFACTOR: bounded optimization - tighten wording, restructure, add examples, while preserving core conclusions and facts.
The skill fits feature development, bug fixing, refactoring, requirements analysis, writing, research, and planning. It does not execute code or access the network; its main value is staged review gates in a chat workflow. Simple questions can be answered in one turn; complex deliverables should keep the three-stage record, and failed checks should route back to RED.
Use Cases
- Define acceptance criteria, format limits, and counterexamples before asking AI to draft a technical plan.
- Split bug fixing into RED criteria, GREEN minimal patch, and REFACTOR cleanup notes.
- Check research report drafts against itemized acceptance criteria, then refine structure and examples.
- Use staged confirmation for long copy to prevent AI from overgenerating off-target content.
Best For
- Frontend engineers who need AI drafts that can be accepted against clear task requirements
- Product managers turning requirements analysis and planning into reviewable deliverables
- Developers collaborating repeatedly with Claude Code or Cursor to refactor code
- Team leads who set AI collaboration norms and review output quality
Related Skills
Provides Claw with character-library selection, switching, saving, and global SOUL.md style sync for role-based conversation.
An AIONE Agentic AI Infrastructure SDK wrapper for building production AI agents with memory, skills, workflows, and hooks.
A Python/TypeScript SDK wrapper for the DeepSeek-Reasonix native AI coding agent, with prefix-cache support.
A browser automation tool for analysts, operators, and developers that locates elements, fills forms, extracts structured content, and supports no-code scheduling and export.