spec-miner

Extract EARS-formatted specifications from existing codebases using Glob, Grep, and Read.

Updated May 14, 2026
One-click install
npx skills add https://github.com/nkseth/copilot-dev-skills --skill spec-miner-nkseth
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-miner
Source: https://github.com/nkseth/copilot-dev-skills/tree/main/skills/spec-miner
Command: npx skills add https://github.com/nkseth/copilot-dev-skills --skill spec-miner-nkseth

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Complex, undocumented, or legacy codebases obscure system behavior. Spec Miner helps teams extract explicit specifications and architecture insights directly from code, enabling accurate documentation and safer modernization.

Core Features & Use Cases

  • Identify analysis scope and boundaries across a codebase.
  • Explore code with Glob, Grep, and Read to surface entry points, dependencies, and data flows.
  • Document requirements in EARS format and generate architecture views.
  • Flag uncertainties and create clear handoff notes for stakeholders.

Quick Start

Analyze a legacy codebase to generate an initial specification draft in EARS format.

Frequently Asked Questions about spec-miner

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

FAQPage Schema
How do I extract specifications from undocumented legacy code?

Reverse-engineering legacy code to extract specifications involves identifying analysis boundaries, exploring code with Glob, Grep, and Read to surface dependencies, and documenting requirements in EARS format with uncertainty notes.

What is the best way to generate API documentation from inherited code?

The best way to generate API documentation from inherited code is through reverse-engineering, mapping dependencies and data flows via code exploration to produce architecture views and explicit EARS-formatted specifications.

Can I map dependencies and create architecture diagrams for an existing codebase?

Yes, you can map dependencies and create architecture diagrams by defining analysis boundaries across the codebase and using tools like Glob, Grep, and Read to trace data flows and surface structural relationships.

How do EARS-formatted specifications help with legacy code modernization?

EARS-formatted specifications aid legacy code modernization by translating raw code evidence into structured requirement documentation, enabling accurate documentation and safer modernization for stakeholders.

How does reverse-engineering handle uncertainty in undocumented codebases?

When reverse-engineering undocumented codebases, uncertainty is handled by requiring ground-truth observations from code evidence and explicitly flagging uncertainties to generate clear handoff notes for stakeholders.