spec-gen-generate

Extract OpenSpec specifications from codebases using static analysis and LLM-assisted inference.

270|34|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/clay-good/spec-gen --skill spec-gen-generate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-gen-generate
Source: https://github.com/clay-good/spec-gen/tree/main/examples/mistral-vibe/skills/spec-gen-generate
Command: npx skills add https://github.com/clay-good/spec-gen --skill spec-gen-generate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many codebases lack up-to-date, machine-readable specifications, forcing engineers and agents to infer behavior from scattered source files and outdated documentation; this Skill extracts the actual behavior and produces structured OpenSpec documentation grounded in code evidence.

Core Features & Use Cases

  • Automated Spec Extraction: Performs a codebase survey and deep analysis to identify domains, entities, APIs, and implementation links, then emits OpenSpec-compliant spec.md files.
  • Evidence-Based Requirements: Traces each requirement and scenario back to concrete source files and preserves existing openspec/config.yaml while appending generated metadata.
  • Drift Detection & Integration: Maps code changes to specs to surface gaps, stale references, uncovered files, or orphaned specs and supports CLI-driven workflows for verification and CI gates.
  • Use Case: Run against a monorepo to generate domain-level specifications, an architecture overview, and a drift report to prioritize test and refactor work.

Quick Start

Run the spec-gen-generate skill to reverse-engineer OpenSpec specifications from the target repository and output openspec/specs.

Frequently Asked Questions about spec-gen-generate

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

FAQPage Schema
How do I generate OpenSpec specifications from an existing codebase?

To generate OpenSpec specifications from an existing codebase, you use static analysis and LLM-assisted inference to extract domains, API surfaces, and entities. This process produces OpenSpec-compliant spec.md files grounded in concrete source code evidence.

What programming languages are supported for extracting domain specifications and API definitions?

Domain specifications and API definitions can be extracted from repositories written in TypeScript, JavaScript, Python, Go, Rust, Java, C++, and Swift. The static analysis surveys these codebases to identify domains, entities, and implementation links.

Can I trace generated requirements back to concrete source files?

Yes, you can trace generated requirements back to concrete source files. The spec extraction process identifies implementation links and preserves existing openspec/config.yaml metadata while appending evidence-based requirement traces.

How do I detect documentation drift between my source code and specifications?

You detect documentation drift by mapping code changes to existing specifications. This surfaces gaps, stale references, uncovered files, and orphaned specs, producing a drift report to help prioritize testing and refactoring work.

What is the best way to reverse-engineer architecture documentation for a monorepo?

The best way to reverse-engineer architecture documentation for a monorepo is running automated spec extraction. It performs deep codebase analysis to generate domain-level specifications, an architecture overview, and a drift report.