aif-explore

Explores ideas, investigates codebases, and clarifies requirements through guided thinking sessions.

31|2|Updated Mar 21, 2026
One-click install
npx skills add https://github.com/letuhao/lore-weave --skill aif-explore-letuhao
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aif-explore
Source: https://github.com/letuhao/lore-weave/tree/main/.cursor/skills/aif-explore
Command: npx skills add https://github.com/letuhao/lore-weave --skill aif-explore-letuhao

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Developers often jump into implementation before fully understanding a problem, leading to rework and misaligned solutions. This Skill provides a structured thinking partner mode that helps you explore ideas, investigate your codebase, compare options, and clarify requirements before writing any code. ## Core Features & Use Cases - Guided Exploration Mode: Acts as a curious thinking partner that asks questions, challenges assumptions, and surfaces risks without following a rigid script. - Codebase Investigation: Reads project context files (DESCRIPTION.md, ARCHITECTURE.md, RULES.md, plans) and maps existing architecture to ground discussions in reality. - Visual Thinking: Generates ASCII diagrams, comparison tables, and architecture sketches to clarify complex problems. - Research Persistence: Optionally saves exploration summaries and session notes to a RESEARCH.md file so context survives across sessions and feeds into later planning. - Use Case: Before adding real-time collaboration to your app, enter explore mode to map the collaboration spectrum (presence, cursors, CRDTs), investigate your current architecture, and capture decisions for the planning phase. ## Quick Start Ask the AI to enter explore mode with a topic like "/aif-explore real-time collaboration" to think through the problem before implementing anything.

Frequently Asked Questions about aif-explore

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

FAQPage Schema
How do I explore a software idea before writing code?

Invoke explore mode with a topic, problem, or plan name as the argument. The AI acts as a thinking partner that asks clarifying questions, investigates your codebase, draws diagrams, and helps the shape of the problem emerge without implementing anything.

What is the difference between explore mode and planning mode?

Explore mode is for open-ended thinking with no required outputs or fixed steps, while planning mode produces structured implementation plans. Explore mode explicitly forbids writing code and suggests running the plan command once ideas crystallize.

Can explore mode modify my project files?

No, explore mode never implements features or modifies project code. The only file it may write is the configured research artifact (default RESEARCH.md), and only after asking for your permission to save exploration context.

How do I save exploration results for later sessions?

When the conversation crystallizes, the skill offers to save a research snapshot with an active summary and session log. This lets you clear the conversation and resume later, or feed the summary directly into the planning command.

Does explore mode work with existing project plans?

Yes, it reads active plan files matched to your current git branch and references them naturally during discussion. It can suggest updating plans or adding investigation tasks when exploration reveals new information.