SpaceZephyr/creator-buddy

Creator Buddy: orchestrated Agent Skills for cross-platform content search, creator analysis, and viral trend research

What it solves

Creator Buddy provides a comprehensive toolkit for content creators and social media operators to move from a topic idea to a finished, publishable piece of content. It eliminates the guesswork of AI-generated topics by first pulling real-time platform data and trends, then guiding the user through the production of high-quality posts for WeChat Official Accounts, Xiaohongshu, and video platforms.

How it works

The project is a collection of "Skills" based on an open Agent Skills protocol, designed to run within AI agent runtimes like Claude Code, Cursor, or Codex. It operates in two primary phases:

  1. Intelligence Gathering: It uses tools like Redfox, Agent Reach, and various APIs to scrape public content, analyze viral trends, and generate structured reports on what is currently performing well.
  2. Content Production: It transforms these insights into actual assets, including writing long-form or short-form articles, generating viral titles, creating layout-ready HTML for WeChat, producing 3:4 images for Xiaohongshu, and generating video scripts, B-roll, subtitles, and audio.

Who it’s for

  • WeChat Official Account authors looking for positioning, trend analysis, and layout tools.
  • Xiaohongshu operators needing help with account setup, note writing, and performance auditing.
  • Video creators who need a pipeline for topic selection, scripting, B-roll generation, and editing.
  • Growth teams monitoring cross-platform content trends to reverse-engineer viral content.

Highlights

  • Multi-platform support: Dedicated skill sets for WeChat (gzh), Xiaohongshu (xhs), and Video.
  • Data-driven ideation: Pulls real-world data from platforms to inform content direction rather than relying on hallucinated AI ideas.
  • End-to-end pipeline: Covers everything from account positioning and trend spotting to final rendering of images and videos.
  • Agent-native: Compatible with multiple AI agent runtimes via the Agent Skills protocol.
  • Safety-first approach: Operates as a read-only tool for public data and does not perform automated posting or account actions.

Related

  • Project
  • Project
  • Project
  • Project
  • Project