Menu
Gemini CLI for one-shot prompts, summaries, structured output, and extension-aware calls.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
| name | gemini |
| description | Gemini CLI for one-shot prompts, summaries, structured output, and extension-aware calls. |
| version | 1.0.0 |
| author | local |
| license | MIT |
| metadata | {"hermes":{"tags":["Gemini","CLI","Google AI","LLM","One-shot"]}} |
Use Gemini CLI in one-shot mode with a positional prompt.
Core usage
gemini "Answer this question..."gemini --model <name> "Prompt..."gemini --output-format json "Return JSON"Extensions
gemini --list-extensionsgemini extensions <command>Auth and safety notes
gemini once interactively and complete login.--yolo mode for safety-sensitive workflows.Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Gmail, Calendar, Drive, Contacts, Sheets, and Docs integration via Python. Uses OAuth2 with automatic token refresh. No external binaries needed — runs entirely with Google's Python client libraries in the Hermes venv.
Use the local F5TTS-FASTAPI service for voice-cloned text-to-speech, voice discovery, and direct synthesis. Trigger when working with the user's local F5 TTS Docker service, listing available voice profiles, validating health or auth, generating speech in a specific cloned voice, or using the F5 API independently of Hermes' built-in text_to_speech provider.
Use OBS as a generic screenshot API. List scenes, inspect scene sources, and capture still images from scenes or sources via obs-websocket.
X/Twitter CLI for reading, searching, timelines, bookmarks, and posting via cookie auth.
Based on SOC occupation classification
