Summary
This is basically a "thinking mode" for Claude that stops it from jumping straight to implementation. It encourages asking questions, drawing ASCII diagrams to visualize problems, and exploring multiple angles before committing to code. The core rule is simple: read files and investigate all you want, but don't write code. If you try to implement something, Claude reminds you to exit explore mode first. It's aware of OpenSpec artifacts, so it can read your existing proposals and designs to ground the conversation, and it'll offer to capture decisions when they crystallize. Nice for when you need to think through architecture or clarify requirements without Claude auto-generating solutions.
Install to Claude Code
npx -y skills add vila-lab/figmirror --skill openspec-explore --agent claude-codeInstalls into .claude/skills of the current project.
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Files
SKILL.md
Select a file.
Featured
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →First SeenJun 11, 2026
