MCPInstall

openspec-explore

Think through ideas, investigate problems, and clarify requirements before committing to a change using /opsx:explore. Use when the user says "explore an idea", "think through this", "investigate options", or wants to brainstorm before creating a formal change.

Installs
48
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/partme-ai/openspec-skills --skill openspec-explore
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads openspec-explore automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

OpenSpec Explore Skill

Use /opsx:explore to think through ideas, investigate problems, compare options, and clarify requirements — all without creating any artifacts or committing to a structure. When insights crystallize, transition to openspec-new or openspec-ff.

When to Use

  • Requirements are unclear and the user needs to investigate first.
  • Comparing multiple approaches before deciding on one.
  • The user wants to explore the codebase for improvement opportunities.
  • Brainstorming before a formal change proposal.

Prerequisites

  • OpenSpec initialized in the project (see openspec-initial).

Workflow

  1. Start exploration

    • Run /opsx:explore or /opsx:explore [topic].
    • The agent opens an exploratory conversation with no structure required.
  2. Investigate

    • Analyze the codebase, compare options, create diagrams, answer questions.
    • No artifacts are created during exploration — it is purely a thinking exercise.
  3. Transition when ready

    • When the user has clarity, suggest /opsx:new <change-name> to start a formal change.
    • Or /opsx:ff <change-name> if they want to create all planning artifacts at once.

Outputs

  • No artifacts or files are created. The output is the conversation itself — insights, options, recommendations.

Next Steps

  • When ready to act: use openspec-new to start a change, or openspec-ff to fast-forward through planning.

Troubleshooting

  • "Commands not recognized": Ensure OpenSpec is initialized (openspec init). See openspec-initial.

References

FAQ

What does the openspec-explore skill do?

Think through ideas, investigate problems, and clarify requirements before committing to a change using /opsx:explore. Use when the user says "explore an idea", "think through this", "investigate options", or wants to brainstorm before creating a formal change.

How do I install openspec-explore?

Run npx skills add https://github.com/partme-ai/openspec-skills --skill openspec-explore in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/openspec-explore/ (personal) or .claude/skills/openspec-explore/ (project).

Which AI agents can use openspec-explore?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is openspec-explore safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains openspec-explore?

It is published by partme-ai in partme-ai/openspec-skills. It has 48 recorded installs.

More from partme-ai/openspec-skills

View all →

openspec-apply

partme-ai/openspec-skills

Open the skill to read its SKILL.md instructions.

39 installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.