Neura Market Logo

GitHub AI Trends

Generate GitHub AI trending project reports as formatted text leaderboards. Fetches top-starred AI/ML/LLM repos by daily, weekly, or monthly period and renders a styled leaderboard…

toller892

@toller892

What This Skill Does

Fetches top-starred AI/ML/LLM repositories from GitHub by daily, weekly, or monthly period and outputs a formatted markdown leaderboard. Uses GitHub API search with deduplication and star sorting.

Replaces manually browsing GitHub trending pages or writing custom API scripts to track popular AI projects.

When to Use It

  • Find the most starred AI repositories from the past week
  • Generate a daily leaderboard of trending machine learning projects
  • Identify popular open-source LLM tools released this month
  • Export a raw JSON list of trending AI repos for further analysis
  • Share a formatted markdown report of top AI projects with a team

Install

$ openclaw skills install @toller892/github-ai-trends

GitHub AI Trends

Generate formatted leaderboard of trending AI projects on GitHub, output directly to chat.

Usage

Run the script and paste its stdout as the reply:

python3 scripts/fetch_trends.py --period weekly --limit 20

Parameters

  • --period: daily | weekly | monthly (default: weekly)
  • --limit: Number of repos (default: 20)
  • --token: GitHub token for higher rate limits (or set GITHUB_TOKEN env)
  • --json: Output raw JSON instead of formatted text

How It Works

  1. Searches GitHub API for AI-related repos (by keywords + topics) pushed within the period
  2. Deduplicates and sorts by star count
  3. Outputs a formatted markdown leaderboard ready for chat display

Notes

  • Without a GitHub token, API rate limit is 10 requests/minute. With token: 30/minute.
  • No pip dependencies, uses only stdlib.
  • Output is markdown formatted for direct chat display.

Top skills in this category

description: 将用户讲稿一键生成乔布斯风极简科技感竖屏HTML演示稿。当用户需要生成PPT、演示文稿、Slides、幻灯片，或要求科技风/极简风/乔布斯风格的演示时触发此技能。输出为单个可直接运行的HTML文件。

@wwlyzzyorg

将讲稿一键生成乔布斯风极简科技感竖屏HTML演示稿

8533k

Feishu Evolver Wrapper

@autogame-17

(Depreciated: This skill is no longer maintained; its related functions have been absorbed by the Evolver main body.) Feishu-integrated wrapper for the capability-evolver. Manages the evolution loop lifecycle (start/stop/ensure), sends rich Feishu card reports, and provides...

1073k

Resume Assistant

@wscats

Assist job seekers by polishing, customizing, scoring, and exporting resumes with detailed checklist reviews and multi-format support.

1721k

Smart Model Switching

@millibus

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: architecture decisions, complex debugging, multi-file refactoring, strategic planning, nuanced judgment, deep research, critical production decisions. Rule: If a human needs >30 seconds of focused thinking, escalate. If Sonnet struggles with complexity, go to Opus. Save 50-90% on API costs by starting cheap and escalating only when needed.

216.6k

Writing Plans

@zlc000190

Use when you have a spec or requirements for a multi-step task, before touching code

713k