使用的 Claude Plugin 完成特定任务,可利用如 Knowledge Work Plugins 中的专业技能
npx skills add https://github.com/cafe3310/public-agent-skills --skill plugin-search-and-use
此技能旨在帮助用户快速定位、理解并执行本地目录中的 Claude 插件(Plugins)及其关联的技能(Skills)。
在开始检索前,必须确保用户已经将插件库所在的目录添加到当前上下文中。
skills/use-claude-plugin/knowledge-work-plugins。add dir 命令添加包含 Claude 插件的根目录。”GEMINI.md 或各子目录中包含 .claude-plugin/plugin.json。根据用户提出的具体任务(例如:“帮我做个竞品分析”或“审查这段代码”):
GEMINI.md 文件或参考下方的“受支持的插件库”列表,寻找与任务描述最匹配的插件名称。marketing/ 或 engineering/)。skills/ 目录下寻找相关的子目录及其 SKILL.md 文件。SKILL.md 的 frontmatter 和描述,确认其功能是否覆盖用户需求。一旦定位到正确的 SKILL.md:
CONNECTORS.md 或 .mcp.json)。SKILL.md 中定义的输出格式(Markdown 结构、表格样式等)进行回复。模拟该插件的身份,根据 SKILL.md 中的专家指令完成用户的具体任务。
/engineering:code-review)。[插件名] 插件中的 [技能名] 技能,现在将按照该专家的标准为您处理任务。”由于本项目是基于 Claude 设计的,在 Gemini CLI 中调用这些插件时,Agent 需遵循以下适配规则:
| Claude 机制 | Gemini CLI 处理方式 |
| :--- | :--- |
| Manifest (plugin.json) | 仅参考。获取插件元数据,不执行安装逻辑。 |
| Skills (skills/) | 重点阅读。读取 SKILL.md 并将其指令注入到当前对话逻辑。 |
| Commands (commands/) | 视作普通指令。按照 Markdown 中的步骤执行任务。 |
| Hooks (hooks.json) | 手动模拟。Gemini 不会自动触发。若有必要,Agent 需手动执行钩子定义的命令(如 npm run lint)。 |
| LSP (.lsp.json) | 跳过。Gemini CLI 暂不支持通过插件动态加载 LSP。 |
| Settings (settings.json) | 角色模拟。根据 agent 字段调整语气和系统指令。 |
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take cafe3310/plugin-search-and-use from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.