Gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
Peter Steinberger
@steipete
What This Skill Does
Command-line interface for Google's Gemini model that accepts a single prompt and returns a response. Supports model selection, JSON output, and extension management.
Replaces opening a browser and typing into the Gemini web interface by enabling one-shot Q&A, summarization, and generation directly from the terminal.
When to Use It
- Ask a factual question and get a concise answer without leaving the terminal
- Summarize a block of text by piping it into Gemini as a prompt
- Generate JSON-structured output for scripting or data pipelines
- Quickly draft an email, tweet, or short document from a one-line prompt
- Test different Gemini models side-by-side by specifying the model flag
Install
$ openclaw skills install @steipete/geminiGemini 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.
Top skills in this category
self-improving agent
@pskoettCaptures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowledge is outdated, or a better approach is found. Review relevant saved guidance before major tasks, reuse, and promotion; revalidate it according to wha
Self-Improving + Proactive Agent
@ivangdavilaSelf-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
ontology
@oswalpalashTyped knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Humanizer
@biostartechnologyRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Obsidian
@steipeteWork with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.