openspec-explore

Explore codebases and clarify requirements through questions and diagrams.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/chuangkevin/project-bridge --skill openspec-explore-chuangkevin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openspec-explore
Source: https://github.com/chuangkevin/project-bridge/tree/main/.gemini/skills/openspec-explore
Command: npx skills add https://github.com/chuangkevin/project-bridge --skill openspec-explore-chuangkevin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enter explore mode. Think deeply. Visualize freely. Follow the conversation wherever it goes.

IMPORTANT: Explore mode is for thinking, not implementing. You may read files, search code, and investigate the codebase, but you must NEVER write code or implement features. If the user asks you to implement something, remind them to exit explore mode first and create a change proposal. You MAY create OpenSpec artifacts (proposals, designs, specs) if the user asks—that's capturing thinking, not implementing.

This is a stance, not a workflow. There are no fixed steps, no required sequence, no mandatory outputs. You're a thinking partner helping the user explore.

Core Features & Use Cases

  • Surface multiple directions and surface questions to better understand the problem space.
  • Map the codebase, architecture, and dependencies to ground discussions in reality.
  • Visualize ideas with ASCII diagrams and architecture sketches to communicate complex flows.
  • Surface risks, unknowns, and assumptions, and suggest focused spikes or investigations.
  • Keep thinking artifacts (proposals, designs, specs) separate from implementation work.

Quick Start

Enter explore mode and think deeply before taking any action.

Frequently Asked Questions about openspec-explore

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

FAQPage Schema
How do I explore codebase architecture and clarify requirements before writing code?

To explore codebase architecture and clarify requirements before implementation, use a thinking partner stance that reads files, surfaces questions, and maps dependencies without writing code. You investigate problems, validate requirements, and create ASCII diagrams to visualize flows.

Can I use explore mode to brainstorm ideas and investigate problems without implementing features?

Explore mode is strictly for brainstorming ideas and investigating problems without implementing features. You may read files, search code, and create OpenSpec artifacts like proposals and designs, but you must never write code or edit features while in this stance.

What is the best way to map dependencies and surface risks during an architecture review?

The best way to map dependencies and surface risks during an architecture review is to use a thinking partner that grounds discussions in the actual codebase. It visualizes architecture with ASCII diagrams, highlights unknowns, and suggests focused spikes to validate assumptions.

Does explore mode allow creating OpenSpec proposals and design specs?

Explore mode does allow creating OpenSpec proposals and design specs because capturing thinking artifacts is permitted. You can generate proposals, designs, and specs to document your exploration, but you must exit explore mode to perform any actual code edits or feature implementations.

When should I not use explore mode for problem-solving?

You should not use explore mode for problem-solving when you need to write code, edit files, or implement features. It is a stance for thinking and visualizing, not executing; if a task requires direct code changes, you must exit explore mode first and create a change proposal.

Why does explore mode enforce guardrails against code edits during requirements validation?

Explore mode enforces guardrails against code edits during requirements validation to keep thinking artifacts separate from implementation work. This ensures architecture reviews and brainstorming sessions remain focused on surfacing risks and clarifying problems without prematurely committing to code changes.