code-mate-kimi-code
Runs Kimi Code in non-interactive prompt mode and parses its event stream. Use when the user asks to delegate a bounded repository task to Kimi Code.
git clone --depth 1 https://github.com/CherryHQ/cherry-studio /tmp/code-mate-kimi-code && cp -r /tmp/code-mate-kimi-code/resources/code-cli-skills/code-mate-kimi-code ~/.claude/skills/code-mate-kimi-codeSKILL.md
# Kimi Code ## Run 1. Set the Bash working directory to the smallest directory the user authorized and set a finite timeout, normally 10 minutes. 2. Check availability with `command -v kimi`. If it is missing, stop and ask the user to install Kimi Code in Code Mate. 3. Run one prompt and exit: ```bash kimi -p "<prompt>" --output-format stream-json ``` Pass the prompt as one quoted argument. Parse stdout as JSONL, preserve event order, and extract the final assistant result. Treat an error event or nonzero exit as failure. Never start the interactive UI or `kimi login`. ## Authentication And Permissions If Kimi reports missing login, model, or provider configuration, stop and ask the user to configure Kimi Code in Code Mate. Never request, read, print, or copy credentials. Prompt mode automatically approves tool calls and rejects `--yolo`, `--auto`, and `--plan`; those flags cannot make it safer. 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. Kimi writes session state under `KIMI_CODE_HOME` (normally `~/.kimi-code`) before running workspace tools. If the host Bash reports a sandbox denial there for an explicitly approved write task, retry the exact command once with the narrowest host escalation. In DSH, request `sandbox_permissions: danger-full-access` with a justification naming Kimi's session storage, then wait for approval. Keep the working directory constrained; leave Kimi's config and credential files in place. Example: for an approved implementation, ask Kimi to change only named files, run it in that project, parse the final JSONL event, and inspect the resulting diff.
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.