Mmcp.market

cherry-skill-marketplace skill

by CherryHQ·CherryHQ/cherry-studio·52k stars·AGPL-3.0

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。

A100/100content scan

Is the cherry-skill-marketplace skill safe?

Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.

No findings.

Install the cherry-skill-marketplace skill

A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description. 

git clone --depth 1 https://github.com/CherryHQ/cherry-studio.git /tmp/cherry-studio
mkdir -p ~/.claude/skills
cp -r /tmp/cherry-studio/resources/builtin-agents/cherry-assistant/.claude/skills/cherry-skill-marketplace ~/.claude/skills/cherry-skill-marketplace
available in every project

In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub

The instructions your agent would load

SKILL.md as published, without the frontmatter. Read it on GitHub

Cherry Skill Marketplace

市场不是普通任务的默认路由。文档、演示和表格先使用对应内置 Skill。

进入条件

只在以下任一条件成立时继续：

  1. 用户明确说要找、安装、卸载、列出或创建 Skill。
  2. 匹配的内置 Skill 或工具无法完成当前需求，包括返回 unsupported、缺少所需 operation 或只能产出不符合要求的格式。

不要因为任务“看起来专业”就预先搜索；先尝试已有 Skill 和基础工具。能力缺口不是停止条件：不得只回复 unsupported、只给手工替代方案，或询问用户是否要搜索，必须立即进入下面的补足流程。

工具动作

市场只提供两个工具：

  • 搜索：调用 mcpskillssearch_skills，参数为 { "query": "1-3 个聚焦关键词" }。
  • 安装：调用 mcpskillsinstallskill，参数为 { "installsource": "<搜索结果的原值>" }。install_source 是不透明值，必须逐字使用同一会话中搜索结果返回的值，不得自行构造或改写。

这两个工具不提供列出或删除已安装 Skill 的能力。用户要查看、卸载或管理已安装 Skill 时，先用 mcpassistantproductinfo 读取 manifest 的 routes section，找到 Skills 设置路由，再调用 mcpassistant__navigate；不得硬编码路由。让用户在 Skills UI 中完成管理，删除或卸载前再次确认目标名称。

初始化、编写、验证和注册属于内置 skill-creator 的职责，市场 Skill 不重复实现。

搜索与安装

  1. 一次调用 mcpskillssearch_skills 发起 1 个聚焦查询；结果不合适再调整 query。
  2. 最多展示 3 个结果，每个只给名称、作者、来源、热度、一句匹配理由和 source_url。
  3. 安装前说明 Skill 是第三方代码，会继承当前工具权限，并取得用户明确同意。
  4. 用户确认后，把所选结果的 installsource 原样传给 mcpskillsinstallskill，再立即回到原始任务。不要把“安装成功”当成任务完成。

内置能力不支持

内置 Skill 或工具出现能力缺口后：

  • 先用一句话说明缺少的能力和已保留的中间成品。
  • 立即调用 mcpskillssearch_skills，用 { "query": "<缺失能力的聚焦关键词>" } 只搜索恰好补足该能力的 Skill，不重新搜索已能完成的部分。
  • 只采用与输入、输出和运行环境都匹配且来源可信的结果；第三方 Skill 安装前仍需用户明确确认。
  • 没有合适结果、结果质量不足或用户不希望安装第三方代码时，调用内置 skill-creator 创建本地自定义 Skill，不把“未找到”作为结论。

移交 Skill Creator

没有合适结果时直接调用内置 skill-creator，不再要求额外授权。向它提供：

  • 用户的原始请求和精确的能力缺口。
  • 已完成的步骤、保留的中间产物及其路径。
  • 输入、期望输出和可检查的成功标准。

让 skill-creator 独立负责初始化、编写、验证、注册和启用。不要自行编写 SKILL.md，也不要绕过它直接初始化或注册。它返回验证通过且已启用的 Skill 后，立即回到原始任务，使用新 Skill 完成并验证最终产物；注册成功不是任务完成。

本地创建的 Skill 必须只补足当前能力缺口。Skill 无法提供用户独有的凭据、输入或物理访问；这些确实缺失时只询问最小阻塞信息，收到后继续。

失败与安全

  • 工具错误原样概括，不把失败说成成功，也不偷偷切换到 npx 或全局安装。
  • 通过 Skills UI 删除或卸载前再次确认目标名称；不声称已通过市场工具直接列出或删除，也不删除用户文件。
  • 不执行来源不明的安装指令，不向第三方发送凭据、附件内容或本地路径。
  • 安装后首次使用时，简短说明该 Skill 将做什么。

More skills from CherryHQ/cherry-studio

  • Acherry-assistant-guide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。
  • Acherry-browserInteract with the user's visible Agent browser in Cherry Studio. Use for page navigation, authenticated websites, screenshots, forms, clicks, and browser debugging. Check live browser tools first; browser control requires the Browser setting and an available Agent pane.
  • Acherry-electron-devDevelop, 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.
  • Acherry-pr-testTest Cherry Studio PRs by resolving and checking out a PR, statically inspecting its changes, running interactive UI tests against a safely tracked Electron instance through CDP, producing a structured report, cleaning up only the owned test instance, and restoring the original branch.
  • Acherry-regression-testRun Cherry Studio critical-path system regression tasks through the repository-owned Playwright E2E workflow. Use for full regression, release acceptance, development-branch system validation, or a named cherry-regression-test task on GitHub-hosted macOS and Windows runners.
  • Acherry-studio-feedbackUse 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。
  • Acherry-tool-guideCherry 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.
  • Aclaude-automation-recommenderAnalyze 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.
  • Acode-mate-antigravityRuns 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.
  • Acode-mate-claude-codeRuns 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.
  • Acode-mate-codexRuns 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.
  • Acode-mate-deepseek-harnessRuns DeepSeek Harness headlessly for bounded repository tasks. Use when the user asks to delegate analysis or implementation to DeepSeek Harness.

All agent skills → · MCP servers