spec-miner

Reverse-engineer codebases into EARS-formatted specifications using Read, Grep, and Glob.

16|Updated Apr 19, 2026
One-click install
npx skills add https://github.com/Marwan78888/Neuron-Cli --skill spec-miner-marwan78888
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-miner
Source: https://github.com/Marwan78888/Neuron-Cli/tree/main/scratch/claude-skills-main/skills/spec-miner
Command: npx skills add https://github.com/Marwan78888/Neuron-Cli --skill spec-miner-marwan78888

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Reverse-engineering specifications from existing codebases to uncover architecture, data flows, and undocumented business logic, enabling teams to generate documentation and onboarding material from code.

Core Features & Use Cases

  • Map code dependencies and entry points across languages and frameworks.
  • Generate API documentation from source and create architecture documentation from implementation.
  • Use during onboarding to understand a new codebase or during refactoring to capture current behavior.

Quick Start

Analyze a target project with Glob, Grep, and Read to produce an EARS-formatted specification.

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 specifications from an existing codebase?

To reverse-engineer specifications from a codebase, you map code dependencies and entry points using Glob, Grep, and Read. This process uncovers architecture and data flows to generate EARS-formatted executable specifications.

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

Generating API documentation from source code involves analyzing implementation files to identify endpoints and data flows. It maps dependencies across frameworks to produce architecture documentation directly from the implementation.

Can I map code dependencies across multiple programming languages?

Yes, you can map code dependencies across multiple languages and frameworks. It identifies entry points and traces data flows regardless of the language, making it applicable for legacy or inherited projects.

How do I create architecture documentation from implementation during onboarding?

Creating architecture documentation during onboarding involves analyzing the target project to uncover undocumented business logic. It maps dependencies and generates an EARS-formatted specification to capture current behavior.

When do I need to use EARS-formatted specifications for code analysis?

You need EARS-formatted specifications when transforming undocumented or inherited codebases into clear, executable requirements. This format captures architecture and data flows systematically during refactoring or onboarding.

Does this approach work for legacy projects with poor documentation?

Yes, this approach works for legacy or poorly documented projects by reverse-engineering the existing implementation. It identifies entry points and maps dependencies to generate comprehensive onboarding material.