Skip to content
Development
Skill

/explore

Map an unfamiliar codebase or trace a focused behavior without editing the project.

From plugin
vibecosystem
547200 skills138 agents7 hooks

Claude Code

$ npx -y skills add vibeeval/vibecosystem --skill explore --agent claude-code

SKILL.md

explore.SKILL.md
name: explore
description: Map an unfamiliar codebase or trace a focused behavior without editing the project.

Explore

Use `/explore [quick|deep|architecture] [--focus <area>] [--entry <symbol>] [--output doc|handoff]`. Default to a quick map and honor a deeper requested scope.

Begin with instructions, manifests, README and filenames. Use `rg --files` and scoped symbol searches, then read entry points and callers. Fall back to available file/search tools if ripgrep is absent.

  • **Quick:** Identify stack, entry points, key directories, test commands and main files for the requested area.
  • **Deep:** Trace input, state changes, output, errors, dependencies, tests and configuration.
  • **Architecture:** Map boundaries, import directions, shared state and external integrations. Confirm cycles from code.

Optional AST, `tldr` or semantic tools can help when installed and current. Raw code is the source of truth. Do not install tools, build indexes or read the entire repository by default. An installed Claude `scout` can answer an independent question; Codex keeps parent settings.

Return a concise map with locations, verified facts, uncertainties and next steps. Write an artifact only when requested, using the supplied destination or repository convention. Exploration is read-only; do not start memory, learning or swarm automation.

@vibeeval
Ships withvibecosystem

A focused runtime for Claude Code. A bounded worker for Codex. Catalog (in repo): Default core: vibecosystem packages agents, skills and hooks for software work.

547200 skills138 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
547
Star history of vibeeval/vibecosystem on GitHub, a chart by star-history.com

Other skills on vibecosystem.

achievements

achievements

Steam-style achievement system with XP, levels, streaks, and skill trees. Gamifies the development workflow. 25 achievements…

agent-benchmark

agent-benchmark

Framework for measuring and tracking agent response quality over time. Detects regressions before they reach production. Use when…

agent-linter

agent-linter

Agent ve skill dosyalarinin yapisal dogrulamasi. Frontmatter kontrol, naming convention, zorunlu bolum kontrolu, tutarlilik…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills2w309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc2w293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react5d252k
@facebook@facebookInstall Skill

Questions about explore.

Which coding agents can use explore?
explore installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.