菜单
Use when the user wants to use Google Gemini for analysis, large files or codebases, sandbox execution, or brainstorming. Uses headless Gemini CLI scripts (no MCP). Triggers on "use Gemini", "analyze with Gemini", "large file", "sandbox", "brainstorm with Gemini".
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/oimiragieo/agent-studio --skill omega-gemini-cli命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Agent frontmatter enhancements — disallowedTools, mcpServers scoping, fork_eligible field
Context management — pre-compact persistence, threshold alignment, microcompact/circuit breaker detection
Hook enhancements — updatedInput for bash safety prefixes, suppressOutput for verbose blocks, denial-based routing feedback
正在显示 SKILL.md
基于 SOC 职业分类
| verified | true |
| lastVerifiedAt | 2026-02-28 |
| name | omega-gemini-cli |
| description | Use when the user wants to use Google Gemini for analysis, large files or codebases, sandbox execution, or brainstorming. Uses headless Gemini CLI scripts (no MCP). Triggers on "use Gemini", "analyze with Gemini", "large file", "sandbox", "brainstorm with Gemini". |
| version | 2.0.0 |
| model | sonnet |
| invoked_by | both |
| user_invocable | true |
| tools |
| ["Bash","Read"] |
| best_practices | ["Always run verify-setup.mjs before first invocation to check CLI availability","Use stdin prompt delivery (built into ask-gemini.mjs) -- never pass prompt as positional arg directly to gemini CLI","For file review, embed file content in prompt text -- no dedicated --file flag exists","Use --json flag for machine-parseable output (wraps response in {\"response\":\"...\"} envelope)","Use --sandbox / -s flag for code execution tasks requiring isolated sandbox","Use --model gemini-2.5-flash or gemini-2.5-flash-lite to reduce quota/latency",{"Set user expectations":"simple queries ~2 min, large file/codebase review ~5-10 min"}] |
| error_handling | graceful |
| streaming | not_supported |
| source | builtin |
| trust_score | 100 |
| provenance_sha | 2c82246edc8159e1 |
Headless wrapper for Google Gemini CLI. Sends prompts via stdin to gemini -p "" --yolo.
Free tier available — no API key required (Google OAuth only).
Gemini CLI runs as a subprocess and includes model startup time:
Set expectations with the user before running long tasks.
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "What is the best caching strategy for a Node.js API?"
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Explain async/await" --model gemini-2.5-flash
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Explain async/await" -m gemini-2.5-flash
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "List 5 design patterns" --json
# Returns: {"response":"..."} on success, {"error":"...","raw":"..."} on parse failure
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Write and run a fibonacci function" --sandbox
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Write and run a fibonacci function" -s
echo "Explain recursion" | node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs
node .claude/skills/omega-gemini-cli/scripts/ask-gemini.mjs "Review this code: $(cat src/auth.ts)"
node .claude/skills/omega-gemini-cli/scripts/verify-setup.mjs
# Exit 0 = available (Node 18+ and Gemini CLI found)
# Exit 1 = not installed or too old
| Script | Purpose |
|---|---|
ask-gemini.mjs | Core headless wrapper — sends prompt via stdin |
parse-args.mjs | Argument parser (--model/-m, --json, --sandbox/-s) |
verify-setup.mjs | Availability check (Node 18+, Gemini CLI via PATH or npx) |
format-output.mjs | Output normalization (JSON envelope handling) |
| Flag | Short | Description |
|---|---|---|
--model MODEL | -m | Gemini model (e.g., gemini-2.5-flash, gemini-2.5-pro) |
--json | Machine-readable JSON output: {"response":"..."} envelope | |
--sandbox | -s | Code execution sandbox mode |
| Model ID | Notes |
|---|---|
gemini-3-pro-preview | Latest (2026), highest capability |
gemini-3-flash-preview | Latest (2026), faster |
gemini-2.5-pro | Stable, high capability |
gemini-2.5-flash | Recommended: lower quota/latency |
gemini-2.5-flash-lite | Lightest, fastest, lowest quota usage |
| Code | Meaning |
|---|---|
| 0 | Success |
| 1 | Error (CLI failure, auth issue, JSON parse failure with --json) |
| 9009 | Windows: command not found (falls back to npx automatically) |
| Command | Purpose |
|---|---|
/analyze | Run headless script with user's prompt (and any @ file refs) |
/sandbox | Run with --sandbox; execute or test code |
/omega-gemini | Alias: run headless for analysis, sandbox, or brainstorm as appropriate |
/brainstorm | Brainstorm mode (build prompt with challenge + optional methodology) |
/omega-gemini-setup | Verify Node and Gemini CLI; guide user to install and auth. No MCP. |
^[a-zA-Z0-9._-]+$ on Windows)@google/gemini-cli fallback automaticallygemini interactive session (run gemini once to sign in)shell: true with model validation; non-Windows uses array args (no shell)npx -y @google/gemini-cli--json wraps output as {"response":"..."} on success or {"error":"...","raw":"..."} on failurenpm install -g @google/gemini-cli) with one-time Google sign-inBefore work: Read .claude/context/memory/learnings.md
After work: Append findings to learnings or issues as needed.
Note: Use pnpm search:code to discover references to this skill codebase-wide.