code-mate-openclaw
Runs a local OpenClaw agent non-interactively and returns its structured response. Use when the user asks to delegate a bounded task to the OpenClaw main agent.
git clone --depth 1 https://github.com/CherryHQ/cherry-studio /tmp/code-mate-openclaw && cp -r /tmp/code-mate-openclaw/resources/code-cli-skills/code-mate-openclaw ~/.claude/skills/code-mate-openclawSKILL.md
# OpenClaw ## Run 1. Set the Bash working directory to the exact directory the user authorized and set a finite outer timeout, normally 11 minutes. 2. Check availability with `command -v openclaw`. If it is missing, stop and ask the user to install OpenClaw in Code Mate. 3. Run the local main agent once: ```bash openclaw agent --local --agent main --message "<prompt>" --json --timeout 600 ``` Pass the prompt as one quoted argument. Parse the JSON payload even when the process exits zero: OpenClaw can encode failure in a successful process exit. Report payload errors and timeouts as failures. Never start onboarding, the interactive TUI, or a login flow. ## Authentication And Permissions If OpenClaw reports missing onboarding, provider, model, or credentials, stop and ask the user to configure OpenClaw in Code Mate. Never request, read, print, or copy credentials. The local agent can invoke configured tools. Keep the prompt read-only by default and do not ask it to mutate files or external systems unless the user explicitly requested workspace changes or that external effect. Limit it to the selected working directory. Example: ask the main agent to explain a module without changing it, then accept the response only when the JSON payload reports 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 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.
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.