RPI Research Phase - Systematic codebase exploration with parallel agents and chunked output
CommunityExplore code with parallel agents.
Software Engineering#code analysis#parallel agents#developer productivity#codebase exploration#research phase#chunked output
AuthorSireJeff
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the systematic exploration of a codebase by dividing the task among multiple parallel agents, ensuring comprehensive analysis and structured output.
Core Features & Use Cases
- Parallel Agent Execution: Spawns 3-5 agents to concurrently analyze different code domains (API, logic, database, integrations, tests).
- Chunked Output: Organizes findings into self-contained "chunks" (CHUNK-R1, CHUNK-R2, etc.), each representing a specific domain.
- Inter-Phase Awareness: Structures output specifically for a subsequent planning phase (RPI-Plan), creating a contract for how chunks will be processed.
- Use Case: When starting a new feature development, use this Skill to quickly understand the relevant parts of the existing codebase, identify dependencies, and pinpoint areas for testing, preparing a clear plan for the development team.
Quick Start
Initiate a research phase for the 'user-authentication' feature.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: RPI Research Phase - Systematic codebase exploration with parallel agents and chunked output Download link: https://github.com/SireJeff/k0ntext/archive/main.zip#rpi-research-phase-systematic-codebase-exploration-with-parallel-agents-and-chunked-output Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.