code-mate-antigravity
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.
git clone --depth 1 https://github.com/CherryHQ/cherry-studio /tmp/code-mate-antigravity && cp -r /tmp/code-mate-antigravity/resources/code-cli-skills/code-mate-antigravity ~/.claude/skills/code-mate-antigravitySKILL.md
# Antigravity CLI ## Run 1. Set the Bash working directory to the exact project the user named and set a finite timeout, normally 10 minutes. 2. Check availability with `command -v agy`. If it is missing, stop and ask the user to install Antigravity CLI in Code Mate. 3. Run one task and exit: ```bash agy -p "<prompt>" --output-format json ``` Pass the prompt as one quoted argument. Print mode waits up to `--print-timeout` (5m by default); pass a shorter value when the caller's own timeout is tighter. Parse the JSON result and read its `status` field: anything other than a success status is a failure, and `error` carries the reason. Treat unparseable output as failure too. Never start interactive Antigravity or an authentication flow. ## Authentication And Permissions Antigravity refuses to run headlessly until it is signed in — it returns `status: "ERROR"` with `authentication failed or timed out` and tells you to run `agy` to log in. Do not do that: stop and ask the user to finish Antigravity setup in Code Mate. Never request, read, print, or copy credentials. Headless mode inherits the permission mode persisted in user settings, and reading and writing files inside the active workspace are auto-approved by default — the default is not a read-only boundary, and a prompt cannot make it one. Do not run it against a writable project for a read-only task. Use a disposable or read-only copy instead. Run against the real project only when the user explicitly requests workspace changes, constrain the directory, and inspect the diff afterward. Never pass `--dangerously-skip-permissions`, which auto-approves every tool request including outside the workspace. Example: for an approved edit, ask Antigravity to touch only named files, run it in that project, parse the `response` and any reported `error`, and inspect the resulting diff before reporting success.
从当前安装包查询 Cherry Studio 产品信息并排查运行问题。当用户询问功能、路由、快捷键、Provider、语言、Agent、频道、定时任务、Code CLI、当前版本，或报告运行错误、连接失败、配置异常并需要诊断时触发。
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools inspection, lag or jank investigation, CPU and memory monitoring, leak checks, and startup-performance analysis; reuse a verified workspace instance across instructions and launch or replace one only when required.
当用户明确要求搜索、安装、查看、卸载或创建 Skill，或内置 Skill / 工具出现能力缺口、无法完成当前任务时触发。通过 `mcp__skills__search_skills` 搜索并用 `mcp__skills__install_skill` 安装；已安装 Skill 的查看和删除通过产品清单导航到 Skills UI；没有合适结果时调用内置 `skill-creator` 创建并验证自定义 Skill，再继续原任务。普通任务仍先尝试内置能力。
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。
Cherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with `bun <file>` and one-off JS tools with `bun x`; run Python with `uv run [--with <pkg>] python` and one-off Python CLIs with `uvx`; search with `rg`. Load this guide before changing project dependencies, deciding whether a tool should be ephemeral or reusable, reading or converting local Office/PDF files, coordinating or delegating across Agent Sessions, or using Cherry-owned web/browser, knowledge, persistent memory, schedules/notifications, IM channels, image generation, artifact reporting, managed CLI, skill, or MCP-server-registration capabilities—even if the user names no tool. Consult it before shell/file workarounds; live tool schemas are authoritative.
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
Runs Claude Code non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Claude Code or compare its result with another coding agent.
Runs Codex CLI non-interactively for code analysis and implementation tasks. Use when the user asks to delegate repository work to Codex or obtain a second coding-agent result.