spec-reverse-engineering

Reverse-engineer codebases into architectural specifications and security audit reports.

Updated May 16, 2026
One-click install
npx skills add https://github.com/alimtvnetwork/img-pdf-v2 --skill spec-reverse-engineering-alimtvnetwork
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-reverse-engineering
Source: https://github.com/alimtvnetwork/img-pdf-v2/tree/main/.agents/skills/spec-reverse-engineering
Command: npx skills add https://github.com/alimtvnetwork/img-pdf-v2 --skill spec-reverse-engineering-alimtvnetwork

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Understanding an unfamiliar or undocumented codebase requires manually reading hundreds of files, which is slow and error-prone. This Skill automates the discovery, analysis, and documentation of any codebase into structured architectural specifications. ## Core Features & Use Cases - Automated Codebase Inventory: Crawls the repository, detects programming languages, and builds a file inventory with language breakdown percentages. - Parallel Reverse Engineering: Dispatches concurrent sub-agents to analyze code semantics, data flow, exported types, and dependencies across disjoint file sets. - Spec & Security Report Generation: Produces modular specification files (domain models, service layer, API endpoints) plus a security audit covering hardcoded credentials, unauthenticated endpoints, and dependency vulnerabilities. - Use Case: Onboard onto a legacy project by generating a complete 02-spec/21-app/ documentation tree with an architecture index and risk assessment before writing any new code. ## Quick Start Ask the AI to reverse-engineer this repository and generate a full architectural specification with a security audit under the spec folder.

Frequently Asked Questions about spec-reverse-engineering

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

FAQPage Schema
How do I generate architecture documentation from an existing codebase?

Run this Skill against the repository root. It crawls all files, detects languages, analyzes code semantics with parallel sub-agents, and writes modular specification files such as domain models, service layer, and API endpoints under the spec folder.

How to reverse-engineer a legacy codebase with no documentation?

The Skill builds a file inventory first, then partitions analysis across concurrent agents that document data flow, exported types, and dependencies. It finishes with an index file summarizing architecture, tech stack, and component topology.

Does the security audit detect hardcoded credentials and vulnerabilities?

Yes. The security phase identifies hardcoded credentials, unauthenticated endpoints, input sanitization flaws, and dependency vulnerabilities, then publishes a risk evaluation in a dedicated security-and-risks specification file.

Can it handle large codebases with many files?

Yes. It uses a batched, multi-phase workflow with a file-assignment ledger so sub-agents process disjoint file sets without collisions, working across an 80-step budget rather than attempting everything in one pass.

What are the limitations of automated codebase reverse engineering?

Generated specifications reflect static code structure and may miss runtime behavior, dynamic configuration, or business context not present in the source. Results should be reviewed by engineers familiar with the system before driving major decisions.