Agent Plugins Marketplace
← All plugins

gemini-bridge

v0.16.0

Hand a task to Gemini and get a structured answer back -- video and audio analysis, perceptual image comparison, or any ad-hoc question with model, thinking level, and schema set per call. Explicit, auditable, one run directory per call.

Claude Code1 Skill

By fblissjr2 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 24, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install gemini-bridge for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install gemini-bridge@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/fblissjr/fb-claude-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is apps/gemini-bridge/.

Plugin files

apps/gemini-bridge/
├── .claude-plugin/plugin.json
└── skills/gemini-multimodal/SKILL.md

Included Skills1

gemini-multimodalskills/gemini-multimodal/SKILL.md

Send a task to a Gemini model and get a structured answer back - perceptual work Claude cannot do directly, or any ad-hoc question worth a second model's take. Handles images, video, audio, and PDFs, singly or mixed in one call. Use when comparing two renders or screenshots to find visual differences, when checking that a change had no visual effect, or when a visual question is being answered with pixel math, histograms, or diff statistics because looking at the images is not working. Use for anything involving a video or audio file, which Claude cannot open at all - "watch this video", "what happens in this screen recording", "turn this recording into code", "transcribe this audio". Also use when the user says "ask Gemini", "have Gemini compare these", "send this to Gemini", or names Gemini alongside a question or file. Calls need no recipe - model, thinking level, system prompt, and schema are all settable per call. Every call is an explicit, billed external request that leaves a run directory on disk.

Plugin manifests1

apps/gemini-bridge/.claude-plugin/plugin.json
{
  "name": "gemini-bridge",
  "version": "0.16.0",
  "description": "Hand a task to Gemini and get a structured answer back -- video and audio analysis, perceptual image comparison, or any ad-hoc question with model, thinking level, and schema set per call. Explicit, auditable, one run directory per call.",
  "author": {
    "name": "fblissjr"
  },
  "repository": "https://github.com/fblissjr/fb-claude-skills"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[gemini-bridge on Agent Plugins Marketplace](https://pluginsmp.com/plugins/gemini-bridge)