caidish/cai-tools/gemini-cli
Claude Code and agent skill by caidish/cai-tools
- community
Checking that the SKILL.md file is still in the repository.
Wield Google's Gemini CLI as a powerful auxiliary tool for code generation, review, analysis, and web research. Use when tasks benefit from a second AI perspective, current web information via Google Search, codebase architecture analysis, or parallel code generation. Also use when user explicitly requests Gemini operations.
Install
npx vskill@latest install caidish/cai-tools/gemini-cliSKILL.md
Gemini CLI Skill Guide
When to Use Gemini
| Use Case | Why Gemini | |
|---|---|---|
| Current web information | google_web_search - real-time Google Search | |
| Codebase architecture analysis | codebase_investigator - deep analysis tool | |
| Second opinion / code review | Different AI perspective catches different bugs | |
| Parallel code generation | Offload tasks while continuing other work |
When NOT to use: Simple quick tasks (overhead not worth it), interactive refinement, context already understood.
Running a Task
- Verify installation:
command -v gemini - Select the mode required for the task; default to read-only (no
--yolo) unless edits are necessary. - Always use `AskUserQuestion` before using `--yolo` or `-s` flags. These modes allow file writes or sandboxed execution - get explicit user approval first.
- Assemble the command with appropriate options:
-m, --model <MODEL>- Model selection-y, --yolo- Auto-approve all tool calls (enables writes)-s, --sandbox- Run in Docker isolation-o, --output-format <text|json>- Output format
- Important: extract the JSON response with:
``bash gemini "prompt" -o json 2>/dev/null | perl -0777 -pe 's/^[^{]*//s' | jq -r '.response' ` The perl stage is required: gemini CLI (>= 0.37) prints status noise (e.g. MCP issues detected. Run /mcp list for status.) on **stdout** before the JSON object, so piping straight to jq fails with Invalid numeric literal. The perl filter strips everything before the first {`.
Critical Note
YOLO mode does NOT prevent planning prompts. Use forceful language: "Apply now", "Start immediately", "Do this without asking for confirmation".
Quick Reference
EXTRACT below stands for perl -0777 -pe 's/^[^{]*//s' | jq -r '.response' (always write it out in full when running commands).
| Use case | Mode | Command pattern | ||
|---|---|---|---|---|
| Read-only analysis | read-only | `gemini "..." -o json 2>/dev/null \ | EXTRACT` | |
| Apply local edits | write | `gemini "..." --yolo -o json 2>/dev/null \ | EXTRACT` | |
| Sandboxed write | sandbox | `gemini "..." --yolo --sandbox -o json 2>/dev/null \ | EXTRACT` |
Example Commands
Following Up
- Resume:
echo "follow-up" | gemini -r latest -o json 2>/dev/null | perl -0777 -pe 's/^[^{]*//s' | jq -r '.response' - List sessions:
gemini --list-sessions
Error Handling
- jq parse error (
Invalid numeric literal): stdout noise before the JSON — make sure theperl -0777 -pe 's/^[^{]*//s'stage is in the pipe. - Rate limit: CLI auto-retries with backoff. Use
-m gemini-2.5-flashfor lower priority tasks. - Command failure: Check with
gemini --version, use--debugfor details. - Always validate Gemini's output for security vulnerabilities (XSS, injection) before using.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/AI-skill/skills/gemini-cli/SKILL.md
Popularity
- Repository stars
- 39
- Repository forks
- 4
- 7-day trend score
- 18
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 25 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/caidish/cai-tools/gemini-cli)