One-click install
npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill spec-miner-enigmaicon-eng
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-miner
Source: https://github.com/enigmaicon-eng/AI-Enterprise-OS/tree/main/examples/claude-skills/skills/spec-miner
Command: npx skills add https://github.com/enigmaicon-eng/AI-Enterprise-OS --skill spec-miner-enigmaicon-eng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you recover clear, actionable specifications from legacy or undocumented codebases when you need to understand how the system actually behaves.

Core Features & Use Cases

  • Evidence-grounded spec extraction: Maps behaviors and requirements directly from code evidence, reducing guesswork when documentation is missing.
  • Trace data flows and request paths: Identifies entry points, routes/controllers, and downstream logic so you can document what the system does end-to-end.
  • EARS-format requirements: Produces structured requirements (Ubiquitous, Event-driven, State-driven, Optional) suitable for implementation planning and alignment.

Quick Start

Use spec-miner on the repository to discover entry points, trace flows, and output an EARS-based reverse specification based on the existing code behavior.

Frequently Asked Questions about spec-miner

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

FAQPage Schema
How do I reverse-engineer system specifications from legacy code?

Reverse-engineer system specifications from legacy code by mapping entry points, routes, data models, and business logic to produce documented requirements. This approach grounds the extracted specifications in actual code behavior, reducing guesswork when original documentation is missing or outdated.

What is the EARS format for requirements extraction?

The EARS format is a structured requirements notation that categorizes extracted specifications into Ubiquitous, Event-driven, State-driven, and Optional types. Applying this format to reverse-engineered legacy code yields clear, actionable requirements suitable for implementation planning and modernization alignment.

How do I document undocumented features in a legacy codebase?

Document undocumented features in a legacy codebase by tracing data flows and request paths from entry points through downstream logic. This maps end-to-end system behaviors into grounded observations, distinguishing factual code evidence from inferences and flagging uncertainties for later clarification.

Can I generate API documentation from implementation details without prior specs?

Yes, you can generate architecture or API documentation from implementation details by identifying routes and controllers, tracing downstream logic, and mapping data models. This produces structured documentation that reflects the actual system behavior rather than missing or outdated original specifications.

Does spec mining work for modernization planning of legacy systems?

Spec mining works for modernization planning of legacy systems by extracting evidence-grounded specifications that reveal actual system behavior. It maps end-to-end flows and outputs EARS-format requirements, providing the clear baseline needed to plan migrations and align new implementations with existing functionality.