garden-skills

ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.

What is garden-skills?

ConardLi's open-source Skills collection, featuring web design, knowledge retrieval, image generation, and more.

Overview of garden-skills

What it is

Garden Skills is a curated collection of production-ready Agent Skills for Claude Code, Cursor, Codex, and other AI coding agents. It is created by ConardLi and includes skills for web design, knowledge retrieval, image generation, and more.

Key features

  • Includes multiple skills: motion-showreel (code-rendered short video), web-video-presentation (web video/presentation), web-design-engineer (design/frontend), gpt-image-2 (image generation/prompting), beautiful-article (any source to beautiful article), and kb-retriever (local knowledge retrieval).- motion-showreel features a deterministic render(t) pipeline, one timeline for picture and sound, a 43-style library as a starting point, sound direction, two checkpoints, narration and long film support, and separate technical acceptance from taste.- web-video-presentation builds record-ready Vite + React + TypeScript presentations with a fixed 1920×1080 stage, click/keyboard-driven cursor, hard collaboration checkpoints, 23 built-in themes, and pluggable TTS with two built-in providers.- web-design-engineer converts briefs into a five-dial Design Read, distinguishes redesign modes, runs executable browser acceptance on request, includes an anti-cliché blocklist, and ships a Design Direction Advisor with 25 anchored style recipes.- gpt-image-2 is a focused image-generation skill for GPT Image 2 and OpenAI-compatible APIs.

Use cases

motion-showreel is best for showreels, product films, UI motion, kinetic typography, logo/title sequences, generative loops, retrospectives, and narrated explainers. web-video-presentation is best for turning scripts, articles, lessons, product demos, and talks into click-driven 16:9 web presentations. web-design-engineer is best for web pages, landing pages, dashboards, interactive prototypes, HTML slide decks, animations, UI mockups, data visualizations, and design-system explorations. gpt-image-2 is best for posters, UI mockups, product visuals, infographics, academic figures, technical diagrams, comics, avatars, storyboards, branding boards, and image-editing workflows.

Getting started

See the repository README for installation instructions, including the skills CLI (npx), Claude Code plugin marketplace, pinned .zip from Releases, manual copy, and Git submodule options.

License and pricing

The license is MIT. The project is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/conardligarden-skills.svg)](https://yunodb.com/tools/conardligarden-skills?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/conardligarden-skills?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/conardligarden-skills.svg" alt="Featured on YunoDB" height="20"></a>