All skills

gemini

Official
by Api.AirforcePrepends a system promptAI & Agent Building000 uses376,200

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

open-sourceclaude-codeai-agent-buildingsteipete
Share

What this skill does

When applied, it prepends a system prompt before your request is sent — no extra calls and no change to how you are billed beyond the added tokens.

---
name: gemini
description: "Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing."
homepage: https://ai.google.dev/
metadata:
  {
    "openclaw":
      {
        "emoji": "✨",
        "requires": { "bins": ["gemini"] },
        "install":
          [
            {
              "id": "brew",
              "kind": "brew",
              "formula": "gemini-cli",
              "bins": ["gemini"],
              "label": "Install Gemini CLI (brew)",
            },
          ],
      },
  }
---

# Gemini CLI

Use Gemini in headless one-shot mode. Positional text starts interactive mode; use `-p/--prompt`.

Quick start

- `gemini -p "Answer this question..."`
- `gemini -m <model> -p "Prompt..."`
- `gemini -p "Return JSON" --output-format json`
- stdin appends to `-p`: `cat notes.md | gemini -p "Summarize"`

Extensions

- List: `gemini --list-extensions`
- Manage: `gemini extensions <command>`
- Skills: `gemini skills <command>`
- Hooks: `gemini hooks <command>`
- MCP: `gemini mcp <command>`

Notes

- If auth is required, run `gemini` once interactively and follow the login flow.
- Avoid `--yolo` for safety.

Use this skill

Per request

Add a "skill" field with the skill’s ID to your chat completion request. It is applied server-side before your prompt is sent — no extra calls.

{
  "model": "gpt-4o-mini",
  "skill": "imp-7a93c2bc-22a2-49d0-9e11-1cce77cfd208",
  "messages": [{ "role": "user", "content": "…" }]
}
Always on — no field to send

Install the skill, enable it in your dashboard and (optionally) limit it to specific models. It then applies automatically to every matching request — with no "skill" field to send each time.

Set it up in your dashboard