Which tools does it integrate with?

Understand (SciTools), Lattix, CodeScene, Sourcetrail, and ast-grep; integration via CLI/API.

What does the output look like?

An interpretation payload with businessLogic, controlFlow, dataFlow, and undocumented sections, plus an analysisId and timestamp.

legacy-code-interpreter

npx machina-cli add skill a5c-ai/babysitter/legacy-code-interpreter --openclaw

Files (1)

SKILL.md

2.6 KB

Legacy Code Interpreter Skill

Deep analysis and interpretation of legacy code to understand undocumented behavior, extract business logic, and characterize system functionality.

Purpose

Enable legacy code understanding for:

Business logic extraction
Undocumented feature discovery
Behavior characterization
Migration planning
Knowledge preservation

Capabilities

1. Business Logic Extraction

Parse conditional logic
Extract calculation formulas
Identify validation rules
Document decision trees

2. Undocumented Feature Discovery

Find hidden functionality
Identify feature flags
Discover Easter eggs
Map admin features

3. Control Flow Analysis

Trace execution paths
Map state machines
Identify loops and recursion
Document entry points

4. Data Flow Tracking

Trace data transformations
Map input to output
Identify side effects
Document state changes

5. Side Effect Identification

Find external calls
Identify I/O operations
Map database operations
Document messaging

6. Behavior Characterization

Create behavior summaries
Generate pseudo-code
Document edge cases
Map error handling

Tool Integrations

Tool	Purpose	Integration Method
Understand (SciTools)	Deep analysis	CLI / API
Lattix	Architecture analysis	CLI
CodeScene	Behavioral analysis	API
Sourcetrail	Code exploration	CLI
ast-grep	Pattern matching	MCP / CLI

Output Schema

{
  "analysisId": "string",
  "timestamp": "ISO8601",
  "interpretation": {
    "businessLogic": [
      {
        "name": "string",
        "location": "string",
        "description": "string",
        "pseudoCode": "string",
        "inputs": [],
        "outputs": [],
        "sideEffects": []
      }
    ],
    "controlFlow": {
      "entryPoints": [],
      "stateMachines": [],
      "criticalPaths": []
    },
    "dataFlow": {
      "transformations": [],
      "stateChanges": []
    },
    "undocumented": []
  }
}

Integration with Migration Processes

legacy-codebase-assessment: Primary interpretation tool
migration-planning-roadmap: Knowledge source

Related Skills

static-code-analyzer: Structural analysis
knowledge-extractor: Documentation mining

Related Agents

legacy-system-archaeologist: Uses for excavation

Source

git clone https://github.com/a5c-ai/babysitter/blob/main/plugins/babysitter/skills/babysit/process/specializations/code-migration-modernization/skills/legacy-code-interpreter/SKILL.md

View on GitHub

Overview

Legacy Code Interpreter analyzes old codebases to reveal undocumented behavior, extract business logic, and characterize system functionality. This enables migration planning, feature discovery, and knowledge preservation across teams.

How This Skill Works

It performs deep analysis using integrated tools (Understand, Lattix, CodeScene, Sourcetrail, ast-grep) to trace control flow, data flow, and side effects. The results are organized into an interpretation payload that includes businessLogic, controlFlow, dataFlow, and undocumented elements for migration and documentation.

When to Use It

When planning migration of a legacy system to a modern stack
When undocumented behavior or hidden features must be discovered
When extracting business logic, validation rules, and decision trees
When mapping data transformations and external side effects
When preserving knowledge for onboarding and audit trails

Quick Start

Step 1: Target a legacy module and initialize analysis with legacy-code-interpreter
Step 2: Run deep analysis to generate businessLogic, controlFlow, and dataFlow interpretations
Step 3: Review the interpretation and attach documentation to the output schema

Best Practices

Define target modules and scope before analysis
Cross-check findings with existing docs and tests
Document each business rule with inputs/outputs and pseudo-code
Capture entry points, state machines, and edge cases
Record external calls, I/O, and database interactions for traceability

Example Use Cases

Extract pricing calculations from a legacy billing module
Identify feature flags and admin tools in an old CMS
Map ETL data transformations in a legacy data warehouse
Characterize error handling and edge cases in a legacy service
Discover undocumented features or Easter eggs in a legacy app

Frequently Asked Questions

Add this skill to your agents