vibe-code-research

Trace data flow, dependencies, and architecture in existing code.

Updated Mar 1, 2026
One-click install
npx skills add https://github.com/adhi-jp/agent-skills --skill vibe-code-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vibe-code-research
Source: https://github.com/adhi-jp/agent-skills/tree/main/skills/vibe-code-research
Command: npx skills add https://github.com/adhi-jp/agent-skills --skill vibe-code-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps you understand, locate, trace, and assess existing code without modifying it, turning questions about a codebase into evidence-backed findings anchored to real files.

Core Features & Use Cases

  • Read-only research: identify modules, data flows, and dependencies without mutating the repository.
  • Evidence-backed findings: anchor conclusions to specific file paths, lines, or symbols.
  • Pre-planning and pre-debugging support: gather context for planning or debugging without edits.

Quick Start

Ask it to map how a feature works by tracing data paths from input to output and returning anchored evidence.

Frequently Asked Questions about vibe-code-research

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

FAQPage Schema
How do I understand existing code without modifying the repository?

Tracing data flow in an existing codebase involves mapping how data moves from input to output across modules and dependencies. This read-only analysis identifies implementation paths and anchors findings to specific file paths and symbols.

Can I assess the impact of changes before modifying existing code?

Yes, you can assess impact before changes by mapping dependencies and tracing data flows through read-only analysis. This identifies affected modules and anchors impact assessments to specific file paths and lines.

What is the best way to locate feature implementations in an unfamiliar codebase?

The best way to locate feature implementations is to trace data paths from input to output using read-only code research. This maps the architecture and returns evidence-backed findings anchored to real files.

Does read-only code research require write access to the repository?

No, read-only code research requires only read-only access to repository contents. It identifies modules, data flows, and dependencies to gather context for planning or debugging without making any edits.

How do I map code conventions and architecture for pre-planning?

You map code conventions and architecture by analyzing existing code behavior through read-only research. This traces dependencies and data flow, providing evidence-backed context anchored to file paths for pre-planning or pre-debugging.