GitHub Trending Report
by coderyi
Use the `github-discover` CLI to fetch real-time GitHub data and generate structured trending reports — discover fast-rising repositories, newly popular projects, and hot topic tags.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/coderyi/github-trending-report文档
Use the github-discover CLI to fetch real-time GitHub data and generate structured trending reports — discover fast-rising repositories, newly popular projects, and hot topic tags.
Installation
npm install -g github-discover
Requires Node.js 18+. Check with
node --version.
Prerequisites
- Node.js ≥ 18
github-discoverinstalled globally (see Installation above)
Commands
trending — Fastest-growing repositories
Ranked by daily average stars with a 30-day smoothing factor, removing age bias to surface genuinely fast-rising projects.
github-discover trending [options]
| Option | Description | Default |
|---|---|---|
-p | Period: daily / weekly / monthly / yearly | daily |
-n | Number of results (1–100) | 50 |
-l | Filter by programming language (e.g. python, typescript) | all |
-s | Minimum star threshold | auto by period |
--json | Output as JSON | — |
popular — New high-star repositories
Sorted by raw star count descending, focused on recently created high-popularity projects.
github-discover popular [options]
Same options as trending.
topic — Hot topic tags
Scored by repoCount × log10(starSum) to surface trending technology topics.
github-discover topic [options]
| Option | Description | Default |
|---|---|---|
-p | Period: daily / weekly / monthly / yearly | daily |
-n | Number of results (1–100) | 30 |
--json | Output as JSON | — |
Data Windows (trending command)
| Period | Repository creation range |
|---|---|
| daily | Created within last 7 days |
| weekly | Created within last 28 days |
| monthly | Created within last 90 days |
| yearly | Created within last 730 days |
Standard Workflow for Generating a Report
When a user requests a GitHub trending report, follow these steps:
Step 1: Verify the tool is available
github-discover --version
If the command is not found, prompt the user to run npm install -g github-discover, then stop.
Step 2: Determine the time period
Infer the period from the user's request:
- "today" / "latest" / "right now" →
daily - "this week" / "weekly" →
weekly - "this month" / "monthly" →
monthly - "this year" / "annual" →
yearly - Not specified → default to
daily
Step 3: Fetch all three data sets in parallel
github-discover trending -p <period> -n 10 --json
github-discover popular -p <period> -n 10 --json
github-discover topic -p <period> -n 10 --json
If the user specified a language (e.g. Python, TypeScript), append -l <language> to the trending and popular commands.
Step 4: Generate the structured report
Combine the JSON output from all three commands and produce a report in the following format:
📈 GitHub <Period> Trending Report
1. Fastest-Growing Projects
Source:
trending— reflects real growth velocity, age bias removed
List Top 5–10 entries, each with:
- Repository name (with link)
- Short description
- Star count / daily average growth
- Primary language
2. Newly Popular Repositories
Source:
popular— recently created projects gaining rapid traction
List Top 5–10 entries, same format as above.
3. Hot Topics
Source:
topic— scored by repository count × star magnitude
List Top 10 topic tags with a brief description of each technology area.
4. AI Insights
Based on the data above, provide:
- A 2–3 sentence summary of the key technical trends this period
- Projects or movements worth watching closely
- If a language filter was applied, a brief analysis of that ecosystem's current state
Limitations
- Data is sourced from the GitHub Search API; freshness depends on GitHub's indexing lag
- The
trendinggrowth score is estimated from creation time and star count, and it is not GitHub's official Trending page data - The
-llanguage filter matches only the repository's primary language; multi-language projects may be excluded
相关 Skills
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
相关 MCP 服务
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。