Sync Trending
Keep up-to-date with technology trends by monitoring GitHub Trending, brainstorming their value against your current context, and autonomously verifying selected technologies.
Workflow
1. Monitor, Brainstorm & Summarize
When triggered, follow these steps:
- 1. Understand Context: Read the local
README.md, package.json, or search the current directory to understand the user's project context. Check save_memory for user preferences or other projects. - Fetch Trends: Use
web_fetch to retrieve content from the sources listed in sources.md (primarily GitHub Trending). - Analyze & Brainstorm: For the top repositories, brainstorm how they could benefit the user's specific project or role.
- Report: Present a "Contextualized Trend Report" including:
-
Facts: Repo Name, URL, Language, Stars, and a brief description.
-
Contextual Value: A one-sentence insight on why this matters (e.g., "Could replace your current auth implementation," "Relevant for the data visualization feature you're planning").
2. Permission & Deep Dive
If the user expresses interest in a specific repository:
- 1. Ask Permission: Clearly ask: "Shall I clone [Repo Name] and attempt to run it for verification?"
- Setup:
- Use
run_shell_command to
git clone the repository into a temporary directory (e.g., in
~/.gemini/tmp/).
- Read
README.md or
CONTRIBUTING.md to identify build/run instructions.
- 3. Execution:
- Detect project type (Node.js, Python, Rust, Go, etc.).
- Install dependencies (
npm install,
pip install -r requirements.txt, etc.).
- Run the application or demo (
npm start,
python main.py, etc.).
- 4. Verification:
- If it starts a web server, use
browser_navigate to check
http://localhost:<port>.
- If it's a CLI tool, check the output for success/failure.
- 5. Report Outcome: Summarize the setup process, any issues found, and the final verification result.
3. Generate Artifacts
Based on the deep dive and the initial brainstorming, offer to generate one of the following:
- -
todo.md: A concrete integration plan for the user's existing project, including technical snippets discovered during the deep dive. idea.md: A blueprint for a new project based on the trending tech.brief.md: A high-level summary suitable for sharing with a CEO, Board of Directors, or a Team.
Safety Guidelines
- - NEVER clone or execute code without explicit user permission.
- ALWAYS perform deep dives in a temporary or isolated directory.
- NEVER expose the user's local secrets or environment variables to the trending repository.
同步趋势
通过监控GitHub趋势、结合当前情境评估其价值，并自主验证所选技术，保持与技术趋势同步。
工作流程
1. 监控、评估与总结
触发时，按以下步骤操作：
- 1. 理解情境： 读取本地README.md、package.json，或搜索当前目录以了解用户项目情境。检查savememory中的用户偏好或其他项目。
- 获取趋势： 使用webfetch从sources.md列出的来源（主要为GitHub趋势）获取内容。
- 分析与评估： 针对热门仓库，评估它们如何能惠及用户的具体项目或角色。
- 报告： 呈现一份情境化趋势报告，包含：
-
事实： 仓库名称、URL、编程语言、星标数及简要描述。
-
情境价值： 一句话说明其重要性（例如：可替代您当前的认证实现、与您正在规划的数据可视化功能相关）。
2. 授权与深度探索
若用户对特定仓库表示兴趣：
- 1. 请求授权： 明确询问：我是否应克隆[仓库名称]并尝试运行以进行验证？
- 设置：
- 使用run
shellcommand将仓库git clone到临时目录（例如~/.gemini/tmp/）。
- 读取README.md或CONTRIBUTING.md以识别构建/运行说明。
- 3. 执行：
- 检测项目类型（Node.js、Python、Rust、Go等）。
- 安装依赖项（npm install、pip install -r requirements.txt等）。
- 运行应用程序或演示（npm start、python main.py等）。
- 4. 验证：
- 若启动Web服务器，使用browser_navigate检查http://localhost:<端口>。
- 若为CLI工具，检查输出以确认成功/失败。
- 5. 报告结果： 总结设置过程、发现的任何问题及最终验证结果。
3. 生成产出物
基于深度探索和初步评估，提供生成以下任一内容的选项：
- - todo.md： 针对用户现有项目的具体集成计划，包含深度探索中发现的技术片段。
- idea.md： 基于趋势技术的新项目蓝图。
- brief.md： 适合与CEO、董事会或团队分享的高层摘要。
安全指南
- - 绝不在未经用户明确许可的情况下克隆或执行代码。
- 始终在临时或隔离目录中进行深度探索。
- 绝不将用户的本地密钥或环境变量暴露给趋势仓库。
