sdlc-import

Map codebases into SDLC artifacts with AI-driven extraction and validation.

3|Updated Jan 12, 2026
One-click install
npx skills add https://github.com/arbgjr/sdlc_agentico --skill sdlc-import
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sdlc-import
Source: https://github.com/arbgjr/sdlc_agentico/tree/main/.claude/skills/sdlc-import
Command: npx skills add https://github.com/arbgjr/sdlc_agentico --skill sdlc-import

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyYAML, jinja2, tqdm, and includes scripts (resource) and references (resource) components.

What problem does it solve?

SDLC artifacts are often missing or outdated; this Skill automatically reverse engineers a codebase to generate complete SDLC documentation.

Core Features & Use Cases

  • AI-driven ADR extraction, threat modeling, and architecture diagrams from existing projects.
  • Builds a complete .agentic_sdlc structure including corpus decisions, threat models, and tech debt reports.
  • Generates an ADR index and knowledge graph to facilitate traceability.

Quick Start

Run the skill against your project path to generate the SDLC artifacts and validate results.

Frequently Asked Questions about sdlc-import

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

FAQPage Schema
How do I auto-generate SDLC documentation from an existing codebase?

To auto-generate SDLC documentation from an existing codebase, you can run an AI-driven extraction skill against your project path to map code into artifacts and validate results.

Can I automatically extract Architecture Decision Records from source code?

You can automatically extract Architecture Decision Records from source code by running an AI-driven reverse engineering skill that identifies decisions and generates an ADR index.

What is the best way to apply threat modeling to an undocumented project?

Applying threat modeling to an undocumented project is best handled by AI-driven reverse engineering that maps existing codebases to generate comprehensive threat models automatically.

Does this SDLC reverse engineering approach support generating a knowledge graph?

SDLC reverse engineering supports generating a knowledge graph by mapping existing codebases, applying detectable technologies, and creating a complete .agentic_sdlc structure for traceability.

Do I need PyYAML and jinja2 to generate software architecture diagrams?

You need PyYAML, jinja2, and tqdm installed to run the AI-driven extraction scripts that generate software architecture diagrams and the complete .agentic_sdlc structure.

How do I validate generated SDLC artifacts and integrate them with GitHub issues?

To validate generated SDLC artifacts and integrate with GitHub issues, activate the skill against your project path to create the .agentic_sdlc structure with built-in validation and optional issue tracking.