conardli

Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.

Visit Website

Total Products

Software by conardli

Open Source

easy-dataset

<div align="center"> ![](./public//imgs/bg2.png) <img alt="GitHub Repo stars" src="https://img.shields.io/github/stars/ConardLi/easy-dataset"> <img alt="GitHub Downloads (all assets, all releases)" src="https://img.shields.io/github/downloads/ConardLi/easy-dataset/total"> <img alt="GitHub Release" src="https://img.shields.io/github/v/release/ConardLi/easy-dataset"> <img src="https://img.shields.io/badge/license-AGPL--3.0-green.svg" alt="AGPL 3.0 License"/> <img alt="GitHub contributors" src="https://img.shields.io/github/contributors/ConardLi/easy-dataset"> <img alt="GitHub last commit" src="https://img.shields.io/github/last-commit/ConardLi/easy-dataset"> <a href="https://arxiv.org/abs/2507.04009v1" target="_blank"> <img src="https://img.shields.io/badge/arXiv-2507.04009-b31b1b.svg" alt="arXiv:2507.04009"> </a> <a href="https://trendshift.io/repositories/13944" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13944" alt="ConardLi%2Feasy-dataset | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> **A powerful tool for creating fine-tuning datasets for Large Language Models** [简体中文](./README.zh-CN.md) | [English](./README.md) | [Türkçe](./README.tr.md) [Features](#features) • [Quick Start](#local-run) • [Documentation](https://docs.easy-dataset.com/ed/en) • [Contributing](#contributing) • [License](#license) If you like this project, please give it a Star⭐️, or buy the author a coffee => [Donate](./public/imgs/aw.jpg) ❤️! </div> ## Overview Easy Dataset is an application specifically designed for building large language model (LLM) datasets. It features an intuitive interface, along with built-in powerful document parsing tools, intelligent segmentation algorithms, data cleaning and augmentation capabilities. The application can convert domain-specific documents in various formats into high-quality structured datasets, which are applicable to scenarios such as model fine-tuning, retrieval-augmented generation (RAG), and model performance evaluation. ![](./public/imgs/arc3.png) ## News 🎉🎉 Easy Dataset Version 1.7.0 launches brand-new evaluation capabilities! You can effortlessly convert domain-specific documents into evaluation datasets (test sets) and automatically run multi-dimensional evaluation tasks. Additionally, it comes with a human blind test system, enabling you to easily meet needs such as vertical domain model evaluation, post-fine-tuning model performance assessment, and RAG recall rate evaluation. Tutorial: [https://www.bilibili.com/video/BV1CRrVB7Eb4/](https://www.bilibili.com/video/BV1CRrVB7Eb4/) ## Features ### 📄 Document Processing & Data Generation - **Intelligent Document Processing**: Supports PDF, Markdown, DOCX, TXT, EPUB and more formats with intelligent recognition - **Intelligent Text Splitting**: Multiple splitting algorithms (Markdown structure, recursive separators, fixed length, code-aware chunking), with customizable visual segmentation - **Intelligent Question Generation**: Auto-extract relevant questions from text segments, with question templates and batch generation - **Domain Label Tree**: Intelligently builds global domain label trees based on document structure, with auto-tagging capabilities - **Answer Generation**: Uses LLM API to generate comprehensive answers and Chain of Thought (COT), with AI optimization - **Data Cleaning**: Intelligent text cleaning to remove noise and improve data quality ### 🔄 Multiple Dataset Types - **Single-Turn QA Datasets**: Standard question-answer pairs for basic fine-tuning - **Multi-Turn Dialogue Datasets**: Customizable roles and scenarios for conversational format - **Image QA Datasets**: Generate visual QA data from images, with multiple import methods (directory, PDF, ZIP) - **Data Distillation**: Generate label trees and questions directly from domain topics without uploading documents ### 📊 Model Evaluation System - **Evaluation Datasets**: Generate true/false, single-choice, multiple-choice, short-answer, and open-ended questions - **Automated Model Evaluation**: Use Judge Model to automatically evaluate model answer quality with customizable scoring rules - **Human Blind Test (Arena)**: Double-blind comparison of two models' answers for unbiased evaluation - **AI Quality Assessment**: Automatic quality scoring and filtering of generated datasets ### 🛠️ Advanced Features - **Custom Prompts**: Project-level customization of all prompt templates (question generation, answer generation, data cleaning, etc.) - **GA Pair Generation**: Genre-Audience pair generation to enrich data diversity - **Task Management Center**: Background batch task processing with monitoring and interruption support - **Resource Monitoring Dashboard**: Token consumption statistics, API call tracking, model performance analysis - **Model Testing Playground**: Compare up to 3 models simultaneously ### 📤 Export & Integration - **Multiple Export Formats**: Alpaca, ShareGPT, Multilingual-Thinking formats with JSON/JSONL file types - **Balanced Export**: Configure export counts per tag for dataset balancing - **LLaMA Factory Integration**: One-click LLaMA Factory configuration file generation - **Hugging Face Upload**: Direct upload datasets to Hugging Face Hub ### 🤖 Model Support - **Wide Model Compatibility**: Compatible with all LLM APIs that follow the OpenAI format - **Multi-Provider Support**: OpenAI, MiniMax, Ollama (local models), Zhipu AI, Alibaba Bailian, OpenRouter, and more - **Vision Models**: Support Gemini, Claude, etc. for PDF parsing and image QA ### 🌐 User Experience - **User-Friendly Interface**: Modern, intuitive UI designed for both technical and non-technical users - **Multi-Language Support**: Complete Chinese, English, Turkish and Portuguese language support 🇹🇷 - **Dataset Square**: Discover and explore public dataset resources - **Desktop Clients**: Available for Windows, macOS, and Linux ## Quick Demo https://github.com/user-attachments/assets/6ddb1225-3d1b-4695-90cd-aa4cb01376a8 ## Local Run ### Download Client <table style="width: 100%"> <tr> <td width="20%" align="center"> Windows </td> <td width="30%" align="center" colspan="2"> MacOS </td> <td width="20%" align="center"> Linux </td> </tr> <tr style="text-align: center"> <td align="center" valign="middle"> <a href='https://github.com/ConardLi/easy-dataset/releases/latest'> <img src='./public/imgs/windows.png' style="height:24px; width: 24px" /> Setup.exe </a> </td> <td align="center" valign="middle"> <a href='https://github.com/ConardLi/easy-dataset/releases/latest'> <img src='./public/imgs/mac.png' style="height:24px; width: 24px" /> Intel </a> </td> <td align="center" valign="middle"> <a href='https://github.com/ConardLi/easy-dataset/releases/latest'> <img src='./public/imgs/mac.png' style="height:24px; width: 24px" /> M </a> </td> <td align="center" valign="middle"> <a href='https://github.com/ConardLi/easy-dataset/releases/latest'> <img src='./public/imgs/linux.png' style="height:24px; width: 24px" /> AppImage </a> </td> </tr> </table> ### Install with NPM 1. Clone the repository: ```bash git clone https://github.com/ConardLi/easy-dataset.git cd easy-dataset ``` 2. Install dependencies: ```bash npm install ``` 3. Start the development server: ```bash npm run build npm run start ``` 4. Open your browser and visit `http://localhost:1717` ### Using the Official Docker Image 1. Clone the repository: ```bash git clone https://github.com/ConardLi/easy-dataset.git cd easy-dataset ``` 2. Modify the `docker-compose.yml` file: ```yml services: easy-dataset: image: ghcr.io/conardli/easy-dataset container_name: easy-dataset ports: - '1717:1717' volumes: - ./local-db:/app/local-db - ./prisma:/app/prisma restart: unless-stopped ``` > **Note:** It is recommended to use the `local-db` and `prisma` folders in the current code repository directory as mount paths to maintain consistency with the database paths when starting via NPM. > **Note:** The database file will be automatically initialized on first startup, no need to manually run `npm run db:push`. 3. Start with docker-compose: ```bash docker-compose up -d ``` 4. Open a browser and visit `http://localhost:1717` ### Building with a Local Dockerfile If you want to build the image yourself, use the Dockerfile in the project root directory: 1. Clone the repository: ```bash git clone https://github.com/ConardLi/easy-dataset.git cd easy-dataset ``` 2. Build the Docker image: ```bash docker build -t easy-dataset . ``` 3. Run the container: ```bash docker run -d \ -p 1717:1717 \ -v ./local-db:/app/local-db \ -v ./prisma:/app/prisma \ --name easy-dataset \ easy-dataset ``` > **Note:** It is recommended to use the `local-db` and `prisma` folders in the current code repository directory as mount paths to maintain consistency with the database paths when starting via NPM. > **Note:** The database file will be automatically initialized on first startup, no need to manually run `npm run db:push`. 4. Open a browser and visit `http://localhost:1717` ## Documentation - View the demo video of this project: [Easy Dataset Demo Video](https://www.bilibili.com/video/BV1y8QpYGE57/) - For detailed documentation on all features and APIs, visit our [Documentation Site](https://docs.easy-dataset.com/ed/en) - View the paper of this project: [Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents](https://arxiv.org/abs/2507.04009v1) ## Community Practice - [Complete test set generation and model evaluation with Easy Dataset](https://www.bilibili.com/video/BV1CRrVB7Eb4/) - [Easy Dataset × LLaMA Factory: Enabling LLMs to Efficiently Learn Domain Knowledge](https://buaa-act.feishu.cn/wiki/GVzlwYcRFiR8OLkHbL6cQpYin7g) - [Easy Dataset Practical Guide: How to Build High-Quality Datasets?](https://www.bilibili.com/video/BV1MRMnz1EGW) - [Interpretation of Key Feature Updates in Easy Dataset](https://www.bilibili.com/video/BV1fyJhzHEb7/) - [Foundation Models Fine-tuning Datasets: Basic Knowledge Popularization](https://docs.easy-dataset.com/zhi-shi-ke-pu) ## Contributing We welcome contributions from the community! If you'd like to contribute to Easy Dataset, please follow these steps: 1. Fork the repository 2. Create a new branch (`git checkout -b feature/amazing-feature`) 3. Make your changes 4. Commit your changes (`git commit -m 'Add some amazing feature'`) 5. Push to the branch (`git push origin feature/amazing-feature`) 6. Open a Pull Request (submit to the DEV branch) Please ensure that tests are appropriately updated and adhere to the existing coding style. ## Join Discussion Group & Contact the Author https://docs.easy-dataset.com/geng-duo/lian-xi-wo-men ## License This project is licensed under the AGPL 3.0 License - see the [LICENSE](LICENSE) file for details. ## Citation If this work is helpful, please kindly cite as: ```bibtex @misc{miao2025easydataset, title={Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents}, author={Ziyang Miao and Qiyu Sun and Jingyuan Wang and Yuchen Gong and Yaowei Zheng and Shiqi Li and Richong Zhang}, year={2025}, eprint={2507.04009}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2507.04009} } ``` ## Star History [![Star History Chart](https://api.star-history.com/svg?repos=ConardLi/easy-dataset&type=Date)](https://www.star-history.com/#ConardLi/easy-dataset&Date) <div align="center"> Built with ❤️ by <a href="https://github.com/ConardLi">ConardLi</a> • Follow me: <a href="./public/imgs/weichat.jpg">WeChat Official Account</a>｜<a href="https://space.bilibili.com/474921808">Bilibili</a>｜<a href="https://juejin.cn/user/3949101466785709">Juejin</a>｜<a href="https://www.zhihu.com/people/wen-ti-chao-ji-duo-de-xiao-qi">Zhihu</a>｜<a href="https://www.youtube.com/@garden-conard">Youtube</a> </div>

AI & Machine Learning Data Labeling

14.4K Github Stars

Open Source

garden-skills

<div align="center"> # Garden Skills **A curated collection of production-ready [Agent Skills](https://support.claude.com/en/articles/12512176-what-are-skills) for Claude Code, Cursor, Codex, and other AI coding agents.** <a id="skills-gallery"></a> <table> <tr> <td width="50%" valign="top"> <a href="#web-video-presentation"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video-presentation-skill.webp" alt="Web Video Presentation Skill" width="100%"></a> <a href="#web-video-presentation">web-video-presentation</a> Web video / presentation </td> <td width="50%" valign="top"> <a href="#web-design-engineer"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design-skill.webp" alt="Web Design Skill" width="100%"></a> <a href="#web-design-engineer">web-design-engineer</a> Design / frontend </td> </tr> <tr> <td width="50%" valign="top"> <a href="#gpt-image-2"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/gpt-image-2-skill.webp" alt="GPT Image 2 Skill" width="100%"></a> <a href="#gpt-image-2">gpt-image-2</a> Image generation / prompting </td> <td width="50%" valign="top"> <a href="#beautiful-article"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/banner.webp" alt="Beautiful Article Skill" width="100%"></a> <a href="#beautiful-article">beautiful-article</a> Any source → beautiful article </td> </tr> </table> [![License: MIT](https://img.shields.io/github/license/ConardLi/garden-skills?style=flat-square&color=blue)](./LICENSE) [![GitHub stars](https://img.shields.io/github/stars/ConardLi/garden-skills?style=flat-square)](https://github.com/ConardLi/garden-skills/stargazers) [![PRs welcome](https://img.shields.io/badge/PRs-welcome-brightgreen?style=flat-square)](#contributing) [![Skills count](https://img.shields.io/badge/skills-5-orange?style=flat-square)](#skills-gallery) [![Spec](https://img.shields.io/badge/spec-SKILL.md-black?style=flat-square)](https://agentskills.io) [English](./README.md) · [中文文档](./README.zh-CN.md) · [日本語](./README.ja-JP.md) </div> --- ## Table of contents | Install | Use | Contribute | |---|---|---| | [Install](#install) [`skills` CLI (npx)](#option-a--skills-cli-npx) [Claude Code plugin marketplace](#option-b--claude-code-plugin-marketplace) [Pinned `.zip` from Releases](#option-c--pinned-zip-from-releases) [Manual copy](#option-d--manual-copy-into-your-project) [Git submodule](#option-e--git-submodule) | [Compatibility](#compatibility) [What is a Skill?](#what-is-a-skill) | [Contributing](#contributing) [Acknowledgments](#acknowledgments) [License](#license) | --- ### [`web-video-presentation`](./skills/web-video-presentation) ![Web Video Presentation Skill](https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video-presentation-skill.webp) **Category:** Web Video / Presentation Engineering **Best for:** turning scripts, articles, lessons, product demos, and talks into click-driven 16:9 web presentations that can be screen-recorded as cinematic videos. `web-video-presentation` builds record-ready Vite + React + TypeScript presentations that behave like video production surfaces. The workflow turns raw articles into narration scripts, maps script beats to full-screen scenes, pauses at required checkpoints, and can optionally synthesize narration audio after the visual outline is approved. Highlights: - Fixed 1920×1080 stage that scales to the viewport for stable screen recording - Click / keyboard driven `(chapter, step)` cursor, with one narration beat per visual step - Hard collaboration checkpoints for script, theme, outline, implementation mode, and optional audio - Hidden hover-only progress controls so the stage stays clean while recording - Theme-token architecture with **23 built-in themes**, each with its own design signature — editorial, terminal, engineering, Swiss International, and more - **Pluggable TTS** — provider-agnostic audio runner; ships **two built-in providers** (MiniMax `mmx-cli` + OpenAI TTS via curl) plus a contract + ready-to-paste snippets for ElevenLabs / edge-tts / Azure / Google Cloud / macOS `say` - Scaffolded Vite + React + TypeScript project with reusable stage primitives and recording guidance <table> <tr> <td align="center" width="25%"><a href="./skills/web-video-presentation/README.md#theme-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video/creative-voltage.webp" alt="creative-voltage preview" /></a> <code>creative-voltage</code> creative talks</td> <td align="center" width="25%"><a href="./skills/web-video-presentation/README.md#theme-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video/blueprint.webp" alt="blueprint preview" /></a> <code>blueprint</code> tech architecture</td> <td align="center" width="25%"><a href="./skills/web-video-presentation/README.md#theme-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video/swiss-ikb.webp" alt="swiss-ikb preview" /></a> <code>swiss-ikb</code> data reports</td> <td align="center" width="25%"><a href="./skills/web-video-presentation/README.md#theme-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video/chalk-garden.webp" alt="chalk-garden preview" /></a> <code>chalk-garden</code> popular science</td> </tr> </table> <a href="./skills/web-video-presentation/README.md#theme-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-video/gallery.webp" alt="Theme gallery — 23 built-in themes for web-video-presentation" /></a> ↑ All 23 themes at a glance — <a href="./skills/web-video-presentation/README.md#theme-gallery">open the full gallery</a> for live 16:9 previews, design signatures, and best-for tags. Links: [README](./skills/web-video-presentation/README.md) · [SKILL.md](./skills/web-video-presentation/SKILL.md) · [Download v1.2.2 .zip](https://github.com/ConardLi/garden-skills/releases/download/web-video-presentation-v1.2.2/web-video-presentation-1.2.2.zip) --- ### [`web-design-engineer`](./skills/web-design-engineer) ![Web Design Skill](https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design-skill.webp) **Category:** Design / Frontend **Best for:** web pages, landing pages, dashboards, interactive prototypes, HTML slide decks, animations, UI mockups, data visualizations, and design-system explorations. `web-design-engineer` turns AI-generated web artifacts from merely functional into polished, deliberate, and visually memorable front-end work. It treats the agent as a design engineer: first understanding product context, then declaring a design system, showing an early v0, building the full experience, and verifying the result. Highlights: - Defines a six-step design workflow: requirements → context → design system → v0 → full build → verification - Pushes beyond generic AI UI patterns with an anti-cliché blocklist and stronger visual judgment - Ships a **Design Direction Advisor (six differentiated schools) + 25 anchored style recipes** (Linear / Aesop / Pentagram / Bloomberg / Stripe Press / Mid-Century, etc.) — each recipe carries concrete palette, typography, signature moves, and anti-patterns ready to paste into the design-system declaration - Covers HTML / CSS / JavaScript / React prototypes, with guidance for responsive layout, motion, and interaction polish - Includes practical implementation rules for inline React + Babel, CSS tokens, `oklch()` color work, container queries, and reduced-motion handling - Ships an advanced patterns reference for device frames, slide engines, animation timelines, dashboards, and other reusable web artifacts <table> <tr> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/aesop.webp" alt="aesop preview" /></a> <code>aesop</code> apothecary pages</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/muji-kenya-hara.webp" alt="muji-kenya-hara preview" /></a> <code>muji-kenya-hara</code> object catalogues</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/monocle-magazine.webp" alt="monocle-magazine preview" /></a> <code>monocle-magazine</code> magazine contents</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/stripe-press.webp" alt="stripe-press preview" /></a> <code>stripe-press</code> book detail</td> </tr> <tr> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/bloomberg-terminal.webp" alt="bloomberg-terminal preview" /></a> <code>bloomberg-terminal</code> trading dashboards</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/linear.webp" alt="linear preview" /></a> <code>linear</code> dev tool landing</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/vercel-mesh.webp" alt="vercel-mesh preview" /></a> <code>vercel-mesh</code> deploy hero</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/tufte-dataink.webp" alt="tufte-dataink preview" /></a> <code>tufte-dataink</code> data narratives</td> </tr> <tr> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/mid-century-modern.webp" alt="mid-century-modern preview" /></a> <code>mid-century-modern</code> poster homage</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/y2k-retrofuturism.webp" alt="y2k-retrofuturism preview" /></a> <code>y2k-retrofuturism</code> Y2K portal</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/bloomberg-businessweek-turley.webp" alt="bloomberg-businessweek-turley preview" /></a> <code>businessweek-turley</code> editorial covers</td> <td align="center" width="25%"><a href="./skills/web-design-engineer/README.md#style-recipe-gallery"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/web-design/active-theory.webp" alt="active-theory preview" /></a> <code>active-theory</code> cinematic launch</td> </tr> </table> ↑ 12 of 25 anchored recipes — <a href="./skills/web-design-engineer/README.md#style-recipe-gallery">open the full gallery</a> for all 25 working artefacts (apothecary pages, trading workstations, magazine covers, Y2K portals, mid-century posters …) with signature moves and best-for tags. Links: [README](./skills/web-design-engineer/README.md) · [SKILL.md](./skills/web-design-engineer/SKILL.md) · [Website](./website/web-design-website) · [Demo](./demo/web-design-demo) · [Download v1.2.2 .zip](https://github.com/ConardLi/garden-skills/releases/download/web-design-engineer-v1.2.2/web-design-engineer-1.2.2.zip) --- ### [`gpt-image-2`](./skills/gpt-image-2) ![GPT Image 2 Skill](https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/gpt-image-2-skill.webp) **Category:** Image Generation / Prompt Engineering **Best for:** posters, UI mockups, product visuals, infographics, academic figures, technical diagrams, comics, avatars, storyboards, branding boards, and image-editing workflows. `gpt-image-2` is a focused image-generation skill for GPT Image 2 and OpenAI-compatible image APIs. It is designed to work across different agent environments: fully local Garden generation, host-native image-tool delegation, or prompt-only advisor mode when no image tool is available. Highlights: - Supports three runtime modes: **Mode A Garden local**, **Mode B host-native delegation**, and **Mode C advisor-only prompt writing** - Starts every task with mode detection so the skill does not silently choose the wrong execution path - Provides 18 visual categories and 79 structured prompt templates under `references/` - Covers both image generation and image editing through dedicated workflows and scripts - Saves prompts and generated images under `garden-gpt-image-2/` in Garden mode for reuse, review, and versioning #### Selected live cases <table> <tr> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/editing-workflows%2Fbackground-replacement%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/editing-workflows/background-replacement/1-thumb.webp" alt="Background replacement case" width="100%"></a> <code>background-replacement</code> Portrait edit with Times Square relighting. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/ui-mockups%2Fchat-interface-scene%2F3"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/ui-mockups/chat-interface-scene/3-thumb.webp" alt="AI assistant UI mockup case" width="100%"></a> <code>chat-interface-scene</code> Claude-style assistant product screenshot. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/ui-mockups%2Flive-commerce-ui%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/ui-mockups/live-commerce-ui/1-thumb.webp" alt="Live commerce UI case" width="100%"></a> <code>live-commerce-ui</code> Celebrity livestream commerce interface. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/ui-mockups%2Fproduct-card-overlay%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/ui-mockups/product-card-overlay/1-thumb.webp" alt="Product card overlay case" width="100%"></a> <code>product-card-overlay</code> Skincare landing-page hero. </td> </tr> <tr> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/infographics%2Fbento-grid-infographic%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/infographics/bento-grid-infographic/1-thumb.webp" alt="Bento grid infographic case" width="100%"></a> <code>bento-grid-infographic</code> High-density iPhone 16 Pro explainer. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/technical-diagrams%2Fsystem-architecture%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/technical-diagrams/system-architecture/1-thumb.webp" alt="System architecture diagram case" width="100%"></a> <code>system-architecture</code> Multi-tenant AI SaaS production diagram. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/slides-and-visual-docs%2Fdense-explainer-slides%2F2"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/slides-and-visual-docs/dense-explainer-slides/2-thumb.webp" alt="Dense explainer slide case" width="100%"></a> <code>dense-explainer-slides</code> AI Agent mechanism in one page. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/maps%2Ffood-map%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/maps/food-map/1-thumb.webp" alt="Food map case" width="100%"></a> <code>food-map</code> City-walk editorial food guide. </td> </tr> <tr> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/product-visuals%2Fexploded-view-poster%2F2"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/product-visuals/exploded-view-poster/2-thumb.webp" alt="Exploded product poster case" width="100%"></a> <code>exploded-view-poster</code> Vision Pro 2 optical and compute teardown. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/academic-figures%2Fneural-network-architecture%2F2"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/academic-figures/neural-network-architecture/2-thumb.webp" alt="Neural network architecture case" width="100%"></a> <code>neural-network-architecture</code> ViT-B/16 model figure for papers. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/branding-and-packaging%2Fcosmetic-packaging%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/branding-and-packaging/cosmetic-packaging/1-thumb.webp" alt="Cosmetic packaging case" width="100%"></a> <code>cosmetic-packaging</code> Premium skincare gift-box composition. </td> <td width="25%" align="center"> <a href="https://gpt-image2.mmh1.top/#/case/storyboards-and-sequences%2Fanime-key-visual%2F1"><img src="https://cdn.jsdelivr.net/gh/ConardLi/gpt-image-2-101@main/public/case/storyboards-and-sequences/anime-key-visual/1-thumb.webp" alt="Anime key visual case" width="100%"></a> <code>anime-key-visual</code> Game-launch key art with crop-safe layout. </td> </tr> </table> ↑ 12 selected cases from the 160+ public case library — <a href="./skills/gpt-image-2/README.md#case-gallery">open the skill gallery</a> for more templates, or browse the <a href="https://gpt-image2.mmh1.top/#/case">live website</a>. Links: [README](./skills/gpt-image-2/README.md) · [SKILL.md](./skills/gpt-image-2/SKILL.md) · [Website](./website/gpt-image2-website) · [Download v1.0.4 .zip](https://github.com/ConardLi/garden-skills/releases/download/gpt-image-2-v1.0.4/gpt-image-2-1.0.4.zip) --- ### [`kb-retriever`](./skills/kb-retriever) ![Kb Retriever Skill](https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/kb-retriever-skill.webp) **Category:** Retrieval / Local Knowledge Base **Best for:** answering questions from a local `knowledge/` directory, searching structured documentation, and extracting evidence from Markdown, text, PDF, and Excel files without flooding the agent context. `kb-retriever` is a local knowledge-base retriever built around careful, progressive search. Instead of loading whole files, it navigates hierarchical index files, narrows the candidate set, processes complex file types correctly, and answers with sources. Highlights: - Uses layered `data_structure.md` files to navigate the knowledge base before searching content - Enforces a **learn-before-process** rule for PDF and Excel files, using the included reference docs before extraction or analysis - Combines precise keyword search, local windowed reads, synonyms, and iterative refinement - Bounds retrieval to at most 5 search rounds so exploration stays controlled - Includes workflows for `grep`, `pdftotext`, `pdfplumber`, and `pandas`, with source-aware answer formatting Links: [README](./skills/kb-retriever/README.md) · [SKILL.md](./skills/kb-retriever/SKILL.md) · [Download v1.0.1 .zip](https://github.com/ConardLi/garden-skills/releases/download/kb-retriever-v1.0.1/kb-retriever-1.0.1.zip) --- ### [`beautiful-article`](./skills/beautiful-article) ![Beautiful Article Skill](https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/banner.webp) **Category:** Editorial · Any source → beautiful article **Best for:** turning URLs, PDFs, DOCX, Markdown, plain text, screenshots, and pasted notes into a **polished, share-ready article** — long-form, briefings, explainers, tutorials, post-mortems, visual essays, dialogue transcripts. `beautiful-article` is an editorial harness skill: it does not just "make a webpage", it edits and designs the source material into a polished article that is easier to read, share, and archive than the original. The skill flows through a small `source → plan → double-confirmation → build → final review → repair` loop and pauses at three hard checkpoints so the user keeps editorial control over article type, theme, layout, image strategy, cover, and delivery format. Highlights: - **Article first** — the focus is the *article*: better reading, better pacing, better aesthetics. Delivery is a self-contained file (HTML, optional PDF), but that's a delivery detail, not the goal - **Reacticle component protocol** — prose-first semantic components (Hero / Lead / Section / Quote / Callout / Image / Formula / CodeBlock / Table…) plus a theme-token-only `Raw` free layer; the underlying React library lives at [`ConardLi/reacticle`](https://github.com/ConardLi/reacticle) - **10 article types with bundled retention ratios** — `longform · ~100%` / `tutorial · ~90%` / `full-report · ~80%` / `explainer · ~80%` / `dialogue · ~80%` / `review · ~70%` / `essay · ~70%` / `briefing · ~50%` / `visual-essay · ~40%` / `interactive-explainer · ~25% excerpt + 75% AI-rebuild` - **11 authoring theme profiles** (`tufte`, `press`, `bayer`, `bodoni`, `vignelli`, `sottsass`, `freddie`, `andy`, `fuller`, `knuth`, `shannon`) — each is a Markdown contract for the agent rather than a CSS file - **Hard collaboration checkpoints** with item-by-item decision capture (no silent defaults), plus a 3:4 book-style cover, default-on TOC, and language-aware translation step - **Per-node quality protocol** — main-agent inline checks for plan, sub-agent reviewers for first spread / sections / final review, repair as minimal slices #### Theme gallery <table> <tr> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/tufte.webp" alt="tufte" width="100%"> tufte</td> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/press.webp" alt="press" width="100%"> press</td> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/bayer.webp" alt="bayer" width="100%"> bayer</td> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/bodoni.webp" alt="bodoni" width="100%"> bodoni</td> </tr> <tr> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/vignell.webp" alt="vignelli" width="100%"> vignelli</td> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/sottsass.webp" alt="sottsass" width="100%"> sottsass</td> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/freddie.webp" alt="freddie" width="100%"> freddie</td> <td width="25%" align="center"><img src="https://cdn.jsdelivr.net/gh/ConardLi/assets@main/imgs/article/andy.webp" alt="andy" width="100%"> andy</td> </tr> </table> Links: [README](./skills/beautiful-article/README.md) · [SKILL.md](./skills/beautiful-article/SKILL.md) · [Download v0.1.0 .zip](https://github.com/ConardLi/garden-skills/releases/download/beautiful-article-v0.1.0/beautiful-article-0.1.0.zip) --- ## Install There are five supported install paths. Pick the one that fits your stack: | # | Method | Best for | Pinned version? | |---|---|---|---| | A | [`skills` CLI (`npx skills add`)](#option-a--skills-cli-npx) | Any agent, one-line install, pick & choose skills | ✅ via tag URL | | B | [Claude Code plugin marketplace](#option-b--claude-code-plugin-marketplace) | Claude Code users who want to subscribe to plugin packs | ✅ via marketplace version | | C | [Pinned `.zip` from GitHub Releases](#option-c--pinned-zip-from-releases) | CI / air-gapped envs / reproducible installs | ✅ ✅ (immutable) | | D | [Manual copy after `git clone`](#option-d--manual-copy-into-your-project) | Local hacking on the skill itself | ❌ (tracks `main`) | | E | [Git submodule](#option-e--git-submodule) | Vendored into a larger project, want upstream updates | ✅ via submodule SHA | > Each skill section above also has a **`Download v<version> .zip`** link in > its "Links:" row that points at the current pinned release artifact. Those > URLs are auto-rewritten by [`scripts/release/update-readme.mjs`](./scripts/release/update-readme.mjs) > on every release, so they always advertise the latest immutable version. ### Option A · `skills` CLI (npx) The fastest agent-agnostic path. Uses the standard [`npx skills` CLI](https://www.npmjs.com/package/skills), which auto-detects your agent (Claude Code, Cursor, Codex, etc.) and drops the skill into the right directory. ```bash # Install all four skills (latest) npx skills add ConardLi/garden-skills # Install just one skill (latest) npx skills add ConardLi/garden-skills -s web-design-engineer # Install globally (~/.skills) instead of per-project (./.skills) npx skills add ConardLi/garden-skills -s gpt-image-2 --global # Target a specific agent npx skills add ConardLi/garden-skills -s kb-retriever -a claude-code ``` > **Defaults to the latest commit on `main`.** That's what you want 95% of the > time — the CLI tracks each skill's most recent published `SKILL.md` straight > from the source tree. **Want a pinned version? (CI / production)** Use a tag-scoped `tree/` URL — this points at the exact commit a release was cut from: ```bash # Pin one skill to a specific release npx skills add ConardLi/garden-skills/tree/web-design-engineer-v1.0.0/skills/web-design-engineer ``` For each skill, the current pinned `.zip` URL is also shown inline in its "Links:" row above (the `Download v<version> .zip` link). Useful sub-commands: ```bash npx skills list # what's installed npx skills find web-design # search registries npx skills update # bump everything npx skills remove kb-retriever # uninstall ``` ### Option B · Claude Code plugin marketplace If you use [Claude Code](https://docs.anthropic.com/en/docs/claude-code), you can subscribe to the marketplace and install plugin packs that bundle one or more skills together: ```bash /plugin marketplace add ConardLi/garden-skills /plugin install presentation-skills@garden-skills /plugin install web-design-skills@garden-skills /plugin install knowledge-base-skills@garden-skills /plugin install image-generation-skills@garden-skills ``` Plugin packs are declared in [`.claude-plugin/marketplace.json`](./.claude-plugin/marketplace.json): | Plugin pack | Skills included | |---|---| | `presentation-skills` | `web-video-presentation` | | `web-design-skills` | `web-design-engineer` | | `knowledge-base-skills` | `kb-retriever` | | `image-generation-skills` | `gpt-image-2` | ### Option C · Pinned `.zip` from Releases Every formal release publishes an immutable `.zip` (with a SHA-256 checksum) to [GitHub Releases](https://github.com/ConardLi/garden-skills/releases). Pin to this from CI, Dockerfiles, or air-gapped installers when you need the exact bytes to never move under you. ```bash # Replace <skill> and <version> with the version you want. SKILL=web-design-engineer VERSION=1.0.0 curl -fsSL -o "${SKILL}.zip" \ "https://github.com/ConardLi/garden-skills/releases/download/${SKILL}-v${VERSION}/${SKILL}-${VERSION}.zip" # Verify the checksum (highly recommended for unattended installs) curl -fsSL -o "${SKILL}.zip.sha256" \ "https://github.com/ConardLi/garden-skills/releases/download/${SKILL}-v${VERSION}/${SKILL}-${VERSION}.zip.sha256" shasum -a 256 -c "${SKILL}.zip.sha256" # Drop the folder into the agent's skills directory unzip -q "${SKILL}.zip" -d .claude/skills/ # or .agents/skills/, .codex/skills/, ... ``` A floating "always-latest" URL is also available — useful for one-off installs: ```bash https://github.com/ConardLi/garden-skills/releases/latest/download/<skill>-<version>.zip ``` > **Pinned URLs for every skill are listed inline in this README** — see the > "Download" line under each skill's "Links" entry above. They are kept in sync > automatically by the release pipeline. ### Option D · Manual copy into your project Clone the repo and copy the skill folder you want — handy if you want to fork or hack on the skill itself. ```bash git clone https://github.com/ConardLi/garden-skills.git cp -r garden-skills/skills/web-design-engineer your-project/.claude/skills/ # Cursor / generic agent: cp -r garden-skills/skills/web-design-engineer your-project/.agents/skills/ ``` The agent discovers the skill the next time it scans the workspace. ### Option E · Git submodule For vendoring into a larger project where you want to track upstream updates: ```bash git submodule add https://github.com/ConardLi/garden-skills.git vendor/garden-skills ln -s ../../vendor/garden-skills/skills/web-design-engineer .claude/skills/web-design-engineer ``` Pin to a release tag for reproducibility: ```bash cd vendor/garden-skills git checkout web-design-engineer-v1.0.0 ``` --- ## Compatibility | Agent / Runtime | Skill location | Status | |---|---|---| | **Claude Code** | `.claude/skills/<name>/` or via plugin marketplace | ✅ Tested | | **Claude.ai** (web) | Settings → Capabilities → Skills | ✅ Tested | | **Cursor** | `.agents/skills/<name>/` | ✅ Tested | | **Codex CLI** | `.codex/skills/<name>/` | ✅ Tested | | **Gemini CLI** | extension manifest | ✅ Tested | | **OpenCode** | `.opencode/skills/<name>/` | ✅ Tested | > The `SKILL.md` format is portable by design — if your agent supports skills, copy the folder into the directory it scans, and it should work. PRs welcome to extend this matrix. --- ## What is a Skill? A **Skill** is a self-contained folder the agent can load on-demand. It's just a `SKILL.md` (YAML frontmatter + instructions), optionally accompanied by reference docs, scripts, and assets: ```text <skill-name>/ ├── SKILL.md ← required: when to use it + how to do it ├── README.md ← human-facing docs ├── references/ ← optional: extended docs the agent loads on demand ├── scripts/ ← optional: deterministic executable helpers └── assets/ ← optional: templates, fonts, icons ``` The agent decides whether to activate the skill from the `description` line in the frontmatter — so the description is the contract between you and the agent. For the full spec, see [agentskills.io](https://agentskills.io) and [Anthropic's reference repository](https://github.com/anthropics/skills). --- ## Contributing Bug reports, new skills, and tooling improvements are all welcome. The maintainer-facing docs — repository layout, release process, version rules, CI workflow, troubleshooting — live in [**`CONTRIBUTING.md`**](./CONTRIBUTING.md) ([中文](./CONTRIBUTING.zh-CN.md)). Read that first if you want to add a skill or cut a release. Quick orientation: ```bash git clone https://github.com/ConardLi/garden-skills.git cd garden-skills npm run list # show all skills + manifest status npm run validate # the same check CI runs on every PR ``` --- ## Acknowledgments This collection stands on the shoulders of: - **[Anthropic](https://www.anthropic.com)** for the [Agent Skills spec](https://agentskills.io) and the [`anthropics/skills`](https://github.com/anthropics/skills) reference repository. - **[Claude Design](https://www.anthropic.com/news/claude-design-anthropic-labs)** — the system prompt that inspired `web-design-engineer`. The original is preserved in [`dist/prompt/claude-design-system-prompt.md`](./dist/prompt/claude-design-system-prompt.md) for reference. - The broader OSS skill community — see [`travisvn/awesome-claude-skills`](https://github.com/travisvn/awesome-claude-skills) and [`obra/superpowers`](https://github.com/obra/superpowers) for further discovery. --- ## Connect | 平台 | 账号名称 | 链接 | | --- | --- | --- | | X/Twitter | code秘密花园 | https://x.com/GardenConardLi | | B 站 | code秘密花园 | https://space.bilibili.com/474921808 | | 抖音 | code秘密花园 | https://v.douyin.com/i5b33Xfv/ | | YouTube | code秘密花园 | https://www.youtube.com/@garden-conard | | 小红书 | code秘密花园 | https://www.xiaohongshu.com/user/profile/5af45e78f7e8b903d6e04618 | | 公众号 | code秘密花园 | https://cdn.jsdelivr.net/gh/ConardLi/easy-dataset@main/public/imgs/weichat.jpg | | GitHub | ConardLi | https://github.com/ConardLi | | 个人网站 | Easy AI | https://mmh1.top | --- ## License [MIT](./LICENSE) © [ConardLi](https://github.com/ConardLi)

Design & Creative AI Agents

7.6K Github Stars