explorer

supabase/supabase · Agent Skill

Builds and modifies Studio Explorer interfaces, including notebooks, chats, SQL snippets, and query cells.

Jump to install ↓

Overview

PublishersupabaseOrganization
Repositorysupabase/supabase ↗
Skill folderexplorer
Stars108,943
Bundled files1
LicenseApache-2.0
Last updatedAugust 30, 2026
LinksSkill source ↗ · Repository ↗

Mozgi check

What we found in the skill files. Details come with a subscription.

Security
low risk · no obvious risks found — the full report shows the details
Compatibility
instructions only — works with most agents
Similar skills
144 similar skills found
Also with subscription

Installation

A skill is a folder with a SKILL.md file. Pick your agent and run the commands in a terminal (macOS, Linux or Git Bash on Windows) from your project root.

Copy the prompt into Claude, Codex or another assistant: it will review the skill and install it for you.

Install the “explorer” skill from mozgi.io (https://mozgi.io/skills/explorer/) for me.

1. Download the archive: https://mozgi.io/skills/explorer/download
   If it fails, take the skill folder from the source: https://github.com/supabase/supabase/tree/master/apps/studio/.claude/skills/explorer
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “explorer” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/explorer/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

Review the source files

1 file Download Zip

Read SKILL.md and any companion files before deciding whether to install. Click a file to preview it.

SKILL.md contents

Original author text · read-only

Studio Explorer

Use this skill when working in apps/studio/components/interfaces/Explorer or building notebook, chat, snippet, or query-cell UI for Explorer.

Explorer UI is Studio-specific. Keep its components under apps/studio/components/interfaces/Explorer; do not move them into ui-patterns or duplicate them in the design-system app.

Explorer toolbar

Import the toolbar primitives from:

import {
  ExplorerToolbar,
  ExplorerToolbarAction,
  ExplorerToolbarActions,
  ExplorerToolbarIcon,
  ExplorerToolbarTitle,
} from '@/components/interfaces/Explorer/ExplorerToolbar'

Compose the toolbar from slots rather than adding resource-specific props:

<ExplorerToolbar aria-label="Query toolbar">
  <ExplorerToolbarIcon>{/* decorative resource icon */}</ExplorerToolbarIcon>
  <ExplorerToolbarTitle>{/* static or editable title */}</ExplorerToolbarTitle>
  <ExplorerToolbarActions>
    {/* badges, source controls, display controls, and direct actions */}
    <ExplorerToolbarAction aria-label="Run query" icon={<Play size={16} strokeWidth={2} />} />
  </ExplorerToolbarActions>
</ExplorerToolbar>
  • The row defaults to 40px and follows --header-height at the md breakpoint.
  • Use ExplorerToolbarAction for compact direct actions. Icon-only actions are 28px wide automatically. It defaults to text-tertiary-foreground and hover:text-foreground. Pass size={16} strokeWidth={2} on Lucide icons.
  • Keep execution, persistence, source selection, and other resource state in the consuming Explorer surface.
  • Extend layouts with children and className; avoid boolean props for resource-specific variants.

Explorer query shell

Import the layout regions from:

import {
  ExplorerQuery,
  ExplorerQueryEditor,
  ExplorerQueryFooter,
  ExplorerQueryResults,
  ExplorerQueryViewport,
} from '@/components/interfaces/Explorer/ExplorerQuery'

Use ExplorerQuery for a framed query embedded in a notebook, chat, or another surface. Give it an explicit height when the surrounding surface constrains the cell:

<ExplorerQuery className="h-96">
  <ExplorerToolbar>{/* title and actions */}</ExplorerToolbar>
  <ExplorerQueryEditor>{/* editable or read-only SQL */}</ExplorerQueryEditor>
  <ExplorerQueryResults>{/* idle, loading, error, or result display */}</ExplorerQueryResults>
  <ExplorerQueryFooter>{/* row count or surface metadata */}</ExplorerQueryFooter>
</ExplorerQuery>

Use ExplorerQueryViewport when a query owns the content area of an Explorer tab. Its parent must provide a bounded height and min-h-0:

<div className="min-h-0 flex-1">
  <ExplorerQueryViewport>{/* the same query composition */}</ExplorerQueryViewport>
</div>
  • ExplorerQueryResults is always present and fills the space left by the toolbar, editor, and footer.
  • A result renderer that can grow supplies its own min-h-0 flex-1 overflow-auto container.
  • The shell owns layout only. Query models, source resolution, execution, results, display selection, and saved configuration stay controlled by the consumer.
  • Compose approval prompts, confirmation notices, and other surface-specific content as children between the standard regions.

Frequently asked questions

What does the explorer skill do?

Builds and modifies Studio Explorer interfaces, including notebooks, chats, SQL snippets, and query cells.

How do I install explorer?

Open the “Installation” block on this page and pick your agent — Claude Code, Codex, Cursor or Gemini CLI — for ready-made commands that copy the skill folder to the right place. Or copy the prompt from the “Via assistant” tab and let the assistant review and install the skill.

Which AI models work with explorer?

Skills are plain Markdown instructions (the Agent Skills format), so explorer works with any agent that reads SKILL.md: Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and more. The model loads the instructions only when a task matches the skill's description.

Is explorer free?

The skill is published openly by supabase under the Apache-2.0 license. The skill itself costs nothing — you only pay your AI provider for the tokens you use.

Is it safe to install skills?

A skill is a set of instructions your agent will follow, so read SKILL.md and its companion files before installing. Scripts in the skill folder only run if your agent runs them — keep an eye on what it does and do not grant unnecessary permissions.

How is a skill different from an MCP server or a plugin?

An MCP server or plugin gives the model new tools — code that runs and returns a result. A skill gives it knowledge and process: how to approach a task, which steps to follow and what good output looks like. It needs no server or API key.

Related skills

All skills →