Workflow Patterns for Openclaw

A rigorous TDD-based workflow for AI agents that ensures code quality through automated testing, coverage gates, and structured git commits.

wpank
v1.0.0
Feb 10, 2026
0
1.9k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install workflow-patterns

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install workflow-patterns 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 Workflow Patterns?

Workflow Patterns is a specialized skill designed to bring software engineering discipline to AI-driven development. By enforcing a strict Test-Driven Development (TDD) cycle, this skill ensures that every piece of code is verified against requirements before it is even written. It provides a roadmap for Openclaw Skills to follow, moving through Red, Green, and Refactor phases while maintaining 80% test coverage as a non-negotiable quality gate.

Beyond just writing code, Workflow Patterns focuses on the lifecycle of a task, from selection and implementation to documentation and final verification. It bridges the gap between AI generation and professional-grade software standards by integrating phase-based checkpoints that require explicit user approval, ensuring that no technical debt or unverified changes slip into the codebase.

Workflow Patterns Use Cases

  • Executing complex feature implementations from a predefined development plan.
  • Projects requiring strict adherence to Test-Driven Development (TDD) methodologies.
  • Maintaining high-quality standards in environments with mandatory 80% code coverage.
  • Building traceable project histories using structured Git commit messages and SHA-linked task updates.
  • Multi-phase development cycles that require human-in-the-loop verification at critical checkpoints.

How Workflow Patterns Works

  1. Task Selection: The agent identifies the next pending task from the project plan without skipping ahead.
  2. Status Update: The task is marked as In Progress to prevent overlapping work.
  3. Red Phase: Failing tests are written first to define the expected behavior and edge cases.
  4. Green Phase: Minimum code is implemented to make the newly written tests pass.
  5. Refactor Phase: The implementation is cleaned up and optimized while ensuring tests remain green.
  6. Coverage Verification: A check is performed to ensure the new code meets the 80% coverage threshold.
  7. Git Implementation: Changes are committed using a structured format (type, scope, subject) including the task ID.
  8. Traceability: The project plan is updated with the specific commit SHA for the completed task.
  9. Phase Verification: Upon completing all tasks in a phase, a verification checklist is presented for user approval.

Workflow Patterns Setup

To install this skill for use with your AI agent, run the following command in your terminal:

npx clawhub@latest install workflow-patterns

Workflow Patterns Data Schema & Taxonomy

Workflow Patterns utilizes a structured system for tracking progress and maintaining history:

Symbol Meaning Description
[ ] Pending Task is awaiting implementation
[~] In Progress Task is currently being handled by the agent
[x] Complete Task is finished and verified with a commit SHA
[-] Skipped Task was deemed unnecessary
[!] Blocked Task cannot proceed due to dependencies

Git Commit Taxonomy:

  • feat: New functionality
  • fix: Bug resolution
  • refactor: Structural changes without logic modification
  • test: Adding or improving tests
  • docs: Documentation updates
  • chore: Maintenance tasks

Workflow Patterns Advanced Features

  • Quality Gate Enforcement: Automatically blocks task completion if test coverage falls below the 80% target.
  • Human-in-the-Loop Checkpoints: Stops execution at the end of each phase to wait for explicit approval confirmation from the developer.
  • Rich Metadata Traceability: Links every task in the project plan to a specific Git commit SHA for full auditability.
  • Automated Deviation Documentation: Requires the agent to record and justify any changes made to the original technical specification or plan.
  • Phase Completion Protocols: Conducts a full test suite run and generates a verification checklist before finalizing development stages.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*