Run quick AI tasks, summaries, and generation from your terminal using the Gemini CLI.
Install
mkdir -p .claude/skills/gemini-annex-ai && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18972" && unzip -o skill.zip -d .claude/skills/gemini-annex-ai && rm skill.zipInstalls to .claude/skills/gemini-annex-ai
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Gemini CLI for one-shot Q&A, summaries, and generation.Key capabilities
- →Answer questions using Gemini
- →Generate text with Gemini
- →Summarize content with Gemini
- →List available Gemini extensions
- →Manage Gemini extensions
How it works
The skill uses the Gemini CLI in one-shot mode to process a positional prompt and return a response. It can specify a model or output format.
Inputs & outputs
When to use gemini
- →Summarizing logs
- →Generating boilerplate code
- →Quick terminal-based Q&A
- →Formatting CLI output as JSON
About this skill
Gemini CLI
Use Gemini in one-shot mode with a positional prompt (avoid interactive mode).
Quick start
gemini "Answer this question..."gemini --model <name> "Prompt..."gemini --output-format json "Return JSON"
Extensions
- List:
gemini --list-extensions - Manage:
gemini extensions <command>
Notes
- If auth is required, run
geminionce interactively and follow the login flow. - Avoid
--yolofor safety.
When not to use it
- →Interactive mode for Gemini
Prerequisites
Limitations
- →Does not support interactive mode
- →Requires prior authentication if not already logged in
How it compares
This skill provides a direct command-line interface for Gemini, allowing quick, non-interactive use without needing to enter a separate shell.
Compared to similar skills
gemini side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gemini (this skill) | 0 | 5mo | No flags | Beginner |
| openrouter-function-calling | 5 | 10d | Review | Intermediate |
| agentic-development | 1 | 3mo | No flags | Advanced |
| context-engineering | 1 | 5mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by annex-ai
View all by annex-ai →You might also like
openrouter-function-calling
jeremylongshore
Implement function/tool calling with OpenRouter models. Use when building agents or structured outputs. Trigger with phrases like 'openrouter functions', 'openrouter tools', 'openrouter agent', 'function calling'.
agentic-development
alinaqi
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
context-engineering
mrgoonie
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.
mcp-builder
UnderUndreGH
MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
copilot-sdk
vivi3172
This skill provides guidance for creating agents and applications with the GitHub Copilot SDK. IMPORTANT - When using the SDK with TypeScript/Node.js, the project MUST use ESM (ECMAScript Modules). CommonJS (require/module.exports) is NOT supported. It should be used when the user wants to create, m
langsmith-evaluator
dhar174
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run v