Workflow Patterns

Systematic task implementation using TDD, phase checkpoints, and structured commits. Ensures quality through red-green-refactor cycles, 80% coverage gates, and verification protocols before proceeding.

This skill is an instruction-only checklist for applying TDD and checkpointed commits; it does not request secrets or install code. Before installing or enabling it for autonomous use, consider: 1) the skill will instruct the agent to run git commands and modify repository files — only grant it access to repos you trust; 2) the SKILL.md requires explicit human approval between phases, but that is procedural (not enforced) — if you allow autonomous runs, the agent may still act without manual confirmation; 3) provenance is unknown (no homepage/source) — if you want higher assurance, copy the SKILL.md into a vetted local skill repository or inspect/modify it before enabling; 4) test the workflow in a sandbox or non-critical repo first to confirm behavior matches expectations.

Type: OpenClaw Skill Name: workflow-patterns Version: 1.0.0 The skill bundle defines a structured software development workflow for an AI agent, focusing on Test-Driven Development (TDD), quality gates, and Git practices. All instructions within SKILL.md, including the 'NEVER Do' section, are aimed at guiding the agent through this workflow and reinforcing best practices, such as waiting for user approval at checkpoints. The shell commands are standard development tools (e.g., git, pytest, npx) and are used in context. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's core security or ethical guidelines. The installation instructions in README.md are also standard for skill deployment.