← Back to Skills Marketplace
🔌

Gemini

by OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
33
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install oo-gemini
Description
Gemini (ai.google.dev). Use this skill for ANY Gemini request — searching and reading data. Whenever a task involves Gemini, use this skill instead of callin...
README (SKILL.md)

Gemini

Operate Gemini through your OOMOL-connected account. This skill calls the gemini connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: AI. Exposes 8 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Gemini. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "gemini" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "gemini" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Gemini state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — Gemini is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=gemini
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

Usage Guidance
Install only if you are comfortable connecting Gemini through OOMOL and letting the agent send your prompts or media-generation requests to that service. Review generated payloads before actions that may create media, consume credits, or incur provider costs.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The described purpose, metadata, and action files align around Gemini model listing, token counting, embeddings, text/audio/image generation, and Veo video workflows.
Instruction Scope
Runtime instructions are scoped to oo CLI connector schema/run commands for the gemini service and include user confirmation guidance for state-changing or destructive actions.
Install Mechanism
First-time setup includes standard remote installer commands for the oo CLI and OOMOL login/connection steps, but they are documented and only recommended after an actual missing-command or auth failure.
Credentials
The allowed tool pattern is Bash(oo *), which is proportionate to operating an OOMOL connector and does not grant general shell execution beyond oo commands.
Persistence & Privilege
The skill relies on an OOMOL account connection and server-side credential injection for Gemini, which is disclosed; no hidden local persistence, background workers, or credential harvesting are present in the artifacts.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install oo-gemini
  3. After installation, invoke the skill by name or use /oo-gemini
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of the `oo-gemini` skill for operating Gemini through an OOMOL-connected account without handling raw API credentials. - Adds support for Gemini text and speech generation via `generate_content`. - Adds Gemini embeddings and token counting with `embed_content` and `count_tokens`. - Adds image generation through Gemini with transit URL output. - Adds Veo video workflows, including starting generation, checking operation status, and polling until the finished video is available. - Adds model discovery for available Gemini and Veo models through `list_models`.
Metadata
Slug oo-gemini
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Gemini?

Gemini (ai.google.dev). Use this skill for ANY Gemini request — searching and reading data. Whenever a task involves Gemini, use this skill instead of callin... It is an AI Agent Skill for Claude Code / OpenClaw, with 33 downloads so far.

How do I install Gemini?

Run "/install oo-gemini" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Gemini free?

Yes, Gemini is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Gemini support?

Gemini is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Gemini?

It is built and maintained by OOMOL (@oomol); the current version is v1.0.0.

💬 Comments