baoyu-skills is a TypeScript MIT-licensed collection of AI agent skills with 24,562 stars, focusing on Claude and Codex integration; last push 2026-07-04. It supports plugin-style installation and ClawHub publishing among other workflows.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
baoyu-skills is a repository that provides a collection of AI agent skills (Content, AI generation, and utility skills) for daily work efficiency, with integration pathways for Claude/Codex and related backends. It is organized as multiple skills that can be installed individually or as a bundled plugin in the Agent environment.
How it works
The project exposes a set of skills categorized under Content Skills, AI Generation Skills, and Utility Skills. It includes tooling to publish skills to ClawHub/OpenClaw and to register as a plugin marketplace. Skills can be installed via the Agent command surface or through marketplace workflows. It includes per-skill commands and examples for using specific skills like baoyu-xhs-images, baoyu-infographic, baoyu-diagram, baoyu-cover-image, etc., each with its own options and usage patterns.
Getting started
Prerequisites
- Node.js environment installed
- Ability to run
npx buncommands
Quick Install (Recommended)
npx skills add jimliu/baoyu-skills
Publish to ClawHub / OpenClaw
# Preview what would be published
./scripts/sync-clawhub.sh --dry-run
# Publish all changed skills from ./skills
./scripts/sync-clawhub.sh --all
Install Skills (Marketplace/Plugin workflow)
/plugin marketplace add JimLiu/baoyu-skills
# Install the marketplace's single plugin
/plugin install baoyu-skills@baoyu-skills
Available Skills (examples)
- baoyu-xhs-images: Xiaohongshu image card series generator with Style × Layout system and palette override. Usage examples include style/layout flags and direct content input.
- baoyu-infographic: Generate infographics with multiple layouts and styles, including aspect, language, and layout options.
- baoyu-diagram: Generate SVG diagrams with types such as flowchart, sequence, structural, and illustrative. Usage includes --type, --lang, and --out options.
Recent releases
- v2.5.2 (2026-06-18): Fixes in codex-imagegen to prevent copying unrelated pre-existing images; general update.
- v2.5.1 (2026-06-13): Documentation updates for Image generation backend and guidance on aspect ratios and backend selection.
- v2.5.0 (2026-06-12): Features including per-group fact memory via memory.md for baoyu-wechat-summary.
- v2.4.1 (2026-06-01): Bump npm package versions for baoyu-md and baoyu-chrome-cdp and refresh dependencies.
Traction
- 24,562 stars
Behind the repo
- Publisher/maintainer is JimLiu, and the repository is linked to Baoyu skills ecosystem; ClawHub/OpenClaw publishing workflow is described, with marketplace integration steps.
Caveats
- License: MIT
- Created: 2026-01-13
- Last push: 2026-07-04
- Open issues: 5
- Language: TypeScript
- Prerequisites require Node.js and bun tooling as described in the README