gemini-cli
Use Google's Gemini CLI for web-grounded research (Google Search), automation via one-shot prompts, and second-opinion review. Use when you need structured JSON output, fast scripting workflows, or cross-AI validation.
npx skills add majiayu000/claude-skill-registry --skill gemini-cli-alexandrbasis-wythm-claude-workflo --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Gemini CLI Integration Skill This skill enables Claude Code to orchestrate Google's **Gemini CLI** reliably using **one-shot prompts** (positional prompt) for scripting and automation. ## When to Use This Skill ### Ideal Use Cases 1. **Second Opinion / Cross-Validation** - Code review after writing code (different AI perspective) - Security audit with alternative analysis - Finding bugs Claude might have missed 2. **Google Search Grounding** - Questions requiring current internet information - Latest library versions, API changes, documentation updates - Current events or recent releases 3. **Automation (One-Shot)** - One-shot prompts in CI/scripts with `gemini "..."` (positional prompt) - Structured output via `--output-format json` - Streaming JSON events via `--output-format stream-json` (only when you explicitly need detailed event traces) 4. **Parallel Processing** - Offload tasks while continuing other work - Run multiple code generations simultaneously - Background documentation generation 5. **Specialized Generation** - Test suite generation - JSDoc/documentation generation - Code translation between languages ### When NOT to Use - Simple, quick tasks (overhead not worth
- When to Use This Skill
- Ideal Use Cases
- When NOT to Use
- Core Instructions
- Model policy (pinned for consistency)
- 1. Verify Installation & Auth (Gemini CLI itself)
- 2. Critical Concept: Gemini CLI Has NO Claude Context
- 3. Basic One-Shot Pattern (Recommended)
- 3.1 One-shot prompt checklist (must be exhaustive)
- 3.2 Multi-line prompts (practical pattern)
- 4. Output Handling Best Practice (Low-Token, Reliable)
- Output only the final answer (no logs / no event stream)
- 5. Critical Behavioral Notes
- 6. Injecting Files & Directories into Prompts (@ commands)
gemini --model gemini-3-pro-preview "..." command -v gemini && gemini --version npm install -g @google/gemini-cli gemini --model gemini-3-pro-preview "Your prompt here" --output-format text gemini --model gemini-3-pro-preview "$PROMPT" --output-format json > /tmp/gemini.json 2> /tmp/gemini.err \ gemini --model gemini-3-pro-preview "Review @backend/src/app.module.ts for security issues" \ Then read with Read tool: gemini --model gemini-3-pro-preview "Answer with ONLY the final result. No reasoning. Task: ..." \ gemini --model gemini-3-pro-preview "Summarize @README.md in 5 bullets" \ Extract just the response:
What does the gemini-cli skill do?
Use Google's Gemini CLI for web-grounded research (Google Search), automation via one-shot prompts, and second-opinion review. Use when you need structured JSON output, fast scripting workflows, or cross-AI validation.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill gemini-cli-alexandrbasis-wythm-claude-workflo --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.