mirror of https://github.com/cexll/myclaude.git synced 2026-02-14 03:31:58 +08:00

Files

swe-agent[bot] 916b970665 feat: 支持通过环境变量配置 skills 模型

- 新增 CODEX_MODEL 环境变量覆盖 codex 默认模型
- 新增 GEMINI_MODEL 环境变量覆盖 gemini 默认模型
- 更新文档说明环境变量用法
- 保持向后兼容，未设置环境变量时使用原默认值

修复 #23

Generated by swe-agent

2025-11-19 09:27:15 +00:00

3.9 KiB

Raw Blame History

name, description

name	description
gemini	Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for complex reasoning tasks.

Gemini CLI Integration

Overview

Execute Gemini CLI commands with support for multiple models and flexible prompt input. Integrates Google's Gemini AI models into Claude Code workflows.

When to Use

Complex reasoning tasks requiring advanced AI capabilities
Code generation and analysis with Gemini models
Tasks requiring Google's latest AI technology
Alternative perspective on code problems

Usage

推荐方式（使用 uv run，自动管理 Python 环境）：

uv run ~/.claude/skills/gemini/scripts/gemini.py -m <model> -p "<prompt>" [working_dir]

备选方式（直接执行或使用 Python）：

~/.claude/skills/gemini/scripts/gemini.py -m <model> -p "<prompt>" [working_dir]
# 或
python3 ~/.claude/skills/gemini/scripts/gemini.py -m <model> -p "<prompt>" [working_dir]

Environment Variables

GEMINI_MODEL: Override default model (default: gemini-3-pro-preview)
- Example: export GEMINI_MODEL=gemini-3
GEMINI_TIMEOUT: Override timeout in milliseconds (default: 7200000 = 2 hours)
- Example: export GEMINI_TIMEOUT=3600000 for 1 hour

Timeout Control

Built-in: Script enforces 2-hour timeout by default
Override: Set GEMINI_TIMEOUT environment variable (in milliseconds)
Bash tool: Always set timeout: 7200000 parameter for double protection

Parameters

-m, --model (optional): Model to use (default: gemini-3-pro-preview)
- gemini-3-pro-preview: Latest flagship model
-p, --prompt (required): Task prompt or question
working_dir (optional): Working directory (default: current)

Return Format

Plain text output from Gemini:

Model response text here...

Error format (stderr):

ERROR: Error message

Invocation Pattern

When calling via Bash tool, always include the timeout parameter:

Bash tool parameters:
- command: uv run ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "<prompt>"
- timeout: 7200000
- description: <brief description of the task>

Alternatives:

# Direct execution (simplest)
- command: ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "<prompt>"

# Using python3
- command: python3 ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "<prompt>"

Examples

Basic query:

# Recommended: via uv run
uv run ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "explain quantum computing"
# timeout: 7200000

# Alternative: direct execution
~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "explain quantum computing"

Code analysis:

uv run ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "review this code for security issues: $(cat app.py)"
# timeout: 7200000

With specific working directory:

uv run ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "analyze project structure" "/path/to/project"
# timeout: 7200000

Using fast model:

uv run ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "quick code suggestion"
# timeout: 7200000

Using python3 directly (alternative):

python3 ~/.claude/skills/gemini/scripts/gemini.py -m gemini-3-pro-preview -p "your prompt here"

Notes

Recommended: Use uv run for automatic Python environment management (requires uv installed)
Alternative: Direct execution ./gemini.py (uses system Python via shebang)
Python implementation using standard library (zero dependencies)
Cross-platform compatible (Windows/macOS/Linux)
PEP 723 compliant (inline script metadata)
Requires Gemini CLI installed and authenticated
Supports all Gemini model variants
Output is streamed directly from Gemini CLI

3.9 KiB Raw Blame History Unescape Escape