菜单
Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.
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/CherryHQ/cherry-studio --skill code-mate-gemini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。
Use when Cherry Studio 用户希望报告、提交或整理 BUG、UI/UX 问题或功能建议，但未明确要求创建 GitHub Issue。
Runs Antigravity CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Antigravity CLI or compare its result with another coding agent.
Prepare a new release by collecting commits, generating bilingual release notes, updating version files, and creating a release branch. Use when asked to prepare/create a release, bump version, or run `/prepare-release`.
基于 SOC 职业分类
正在显示 SKILL.md
| name | code-mate-gemini |
| description | Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent. |
command -v gemini. If it is missing, stop and ask the user to install Gemini CLI in Code Mate.gemini -p "<prompt>" --output-format json
Pass the prompt as one quoted argument. Parse the JSON result and treat a JSON error or nonzero exit as failure. Never start interactive Gemini or an authentication flow.
If Gemini reports missing authentication, project, or provider configuration, stop and ask the user to finish Gemini setup in Code Mate. Never request, read, print, or copy credentials.
Keep headless approval policy at its read-only default. Only when the user explicitly requests workspace changes may the command use the narrowest policy and tool permissions needed; do not enable unrestricted approval.
Example: ask Gemini to review a module without editing, run the command above from the repository, and summarize the parsed response and any reported error.