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machine-readable specifications, forcing engineers and agents to infer behavior from scattered source files and outdated documentation; this Skill extracts the actual behavior and produces structured OpenSpec documentation grounded in code evidence.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