tlc-spec-driven

Plan and execute software projects through four specification-driven phases.

5.0k|454|Updated Jan 19, 2026
One-click install
npx skills add https://github.com/tech-leads-club/agent-skills --skill tlc-spec-driven
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tlc-spec-driven
Source: https://github.com/tech-leads-club/agent-skills/tree/main/packages/skills-catalog/skills/%28development%29/tlc-spec-driven
Command: npx skills add https://github.com/tech-leads-club/agent-skills --skill tlc-spec-driven

SYSTEM DOCUMENTATION & REQUIREMENTS

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".

Frequently Asked Questions about tlc-spec-driven

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I plan software projects using spec-driven development with an AI agent?▼

Spec-driven project planning uses a four-phase workflow: Specify, Design, Tasks, and Implement with validation. This enforces structured product planning and granular task breakdown before writing code.

What is the best way to map an existing codebase for architecture reuse?▼

Mapping an existing codebase analyzes project structure to generate architecture guidance and suggest reusable components, supporting brownfield development and design reuse.

How do I maintain session state for long-running AI coding tasks across pauses?▼

Maintaining session state for long-running AI coding tasks uses persistent memory to track progress across pauses and resumes, ensuring continuity throughout the four-phase workflow.

Does spec-driven AI planning support converting project specs into atomic tasks?▼

Spec-driven AI planning converts project specs into atomic tasks with clear dependencies and verification steps, ensuring granular task breakdown during the planning phase.

Can I use this spec-driven workflow for both new projects and existing codebases?▼

The spec-driven workflow supports both starting new projects by creating project docs and mapping existing codebases to generate architecture guidance, covering brownfield and greenfield scenarios.