tlc-spec-driven

What problem does it solve?

The tlc-spec-driven skill standardizes how AI agents plan and execute software projects by enforcing a four-phase workflow (Specify, Design, Tasks, Implement+Validate) with persistent memory across sessions.

Core Features & Use Cases

• Structured product planning: captures vision, goals, and scope before coding.
• Granular task breakdown: converts specs into atomic tasks with clear dependencies and verification.
• Session continuity: maintains STATE across pauses and resumes for long-running work.
• Brownfield mapping and design reuse: analyzes existing codebases and suggests reusable components.
• Use Case: starting a new project by creating project docs, or mapping an existing project to generate architecture guidance.

Quick Start

To begin, initialize a new project or map an existing codebase. Use the triggers defined in SKILL.md to guide the agent through the four phases. For example: "Initialize project" or "Map codebase".