A sophisticated TDD workflow for AI agents featuring a unique de-sloppify pattern to ensure clean, behavior-driven code.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tdd-ecc
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tdd-ecc using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TDD & De-Sloppify Agent Skill?
This skill implements a rigorous Test-Driven Development (TDD) workflow designed specifically for AI coding agents. Unlike standard approaches that often lead to poor code structure, this Openclaw Skills implementation emphasizes vertical slicing via tracer bullets. It focuses on testing observable behavior through public interfaces rather than implementation details, ensuring your test suite remains resilient during refactors.
By prioritizing the red-green-refactor loop, this skill helps developers build features that are robust and easy to maintain. It addresses the common pitfall of implementation-coupled testing by enforcing a philosophy where tests verify what the system does, not how it does it. This makes it an essential tool within the Openclaw Skills ecosystem for anyone looking to improve software quality through automation.
TDD & De-Sloppify Agent Skill Use Cases
- Building new features from scratch using a strict test-first approach.
- Refactoring complex legacy logic while maintaining behavioral integrity.
- Eliminating AI-generated slop such as redundant type checks or framework-specific tests.
- Implementing bug fixes with dedicated regression tests to prevent future regressions.
How TDD & De-Sloppify Agent Skill Works
- Planning: The agent confirms interface changes and identifies core behaviors to test before writing any code.
- Tracer Bullet: A single test is written to confirm an end-to-end path, followed by minimal code to pass (Red-Green).
- Incremental Loop: The agent repeats the cycle for each remaining behavior, ensuring only enough code is written to pass the current test.
- Refactor: Once in a green state, the agent extracts duplication and deepens modules without breaking existing tests.
- De-Sloppify: A dedicated cleanup pass removes redundant tests, type guards, and logs to ensure the final output is professional and clean.
TDD & De-Sloppify Agent Skill Setup
To integrate this TDD pattern within your Openclaw Skills environment, ensure your agent has access to your project's test runner and execution environment.
# Example command to trigger the TDD workflow
claude -p "Implement the user authentication feature with TDD."
# Followed by the cleanup pass to remove slop
claude -p "Cleanup pass: review changes, remove test/code slop, run tests."
TDD & De-Sloppify Agent Skill Data Schema & Taxonomy
The skill manages data and feedback loops through the following structure:
| Component | Description |
|---|---|
| Tests Directory | Contains integration-style tests focused on public APIs and business logic. |
| Source Code | Minimal implementation code designed to fulfill test requirements. |
| Context Files | Includes tests.md and mocking.md to guide the agent on quality standards. |
| Cleanup Checklist | A metadata taxonomy used during the de-sloppify phase to identify redundant code. |
TDD & De-Sloppify Agent Skill Advanced Features
- Vertical Slicing: Avoids horizontal anti-patterns by building features one behavior at a time.
- De-Sloppify Pattern: A unique multi-agent approach where a second agent cleans up LLM-specific artifacts like redundant type checks.
- Deep Module Support: Encourages the creation of modules with small interfaces and deep implementation logic.
- Automated Refactor Loops: Leverages Openclaw Skills to safely perform code cleanup while maintaining a passing test suite.
SKILL.md
Loading
Related Openclaw Skills
TCM Diagnosis
An advanced AI-driven Traditional Chinese Medicine diagnostic agent providing pattern differentiation and wellness recommendations.
Self-Improving Agent
An advanced learning framework that captures atomic behaviors and project-specific patterns to turn AI agents into continuously evolving coding partners.
Performance Optimization (Web & LLM Cost)
A comprehensive optimization toolkit for boosting web application speed and minimizing LLM API expenditures through intelligent resource management.
OpenClaw Security Practice Guide
A comprehensive security framework for AI agents with root access, covering lifecycle auditing, permission hardening, and automated disaster recovery.
Web Quality Audit
A comprehensive web audit tool for performance, accessibility, SEO, and security validation powered by PinchTab browser automation.
Writing Assistant
A sophisticated three-layer AI writing agent designed for professional content generation, rewriting, and strategic ideation.
Featured*
