Leonxlnx/taste-skill
Taste Skill provides portable AI Agent Skills designed to enhance the quality of AI-generated frontends and image-based design references, aiming to eliminate generic UI outputs.
Awesome AI Agents › AI Developer Toolkit
book-to-skill is a Python tool that turns long-form technical material into an agent skill packaged in the open Agent Skills SKILL.md format, readable by hosts such as GitHub Copilot CLI, Amp and Claude Code. The user points it at a single file, a folder or a glob, and it ingests PDF, EPUB, DOCX, Markdown, HTML, RTF and MOBI sources. Instead of producing a flat summary, it extracts structure: a core SKILL.md holding the mental models and a chapter index, one Markdown file per chapter loaded only when that topic is asked about, a glossary of key terms cross-referenced to chapters, a patterns file collecting techniques and algorithms, and a cheatsheet of decision tables and quick rules. The generated skill is written into the host agent skills directory, after which the material is invoked through a slash command with a topic argument; the agent opens the matching chapter file and answers from the extracted text rather than from model memory. The design goal is context economy, and the project reports measurements where answering one question through the generated skill consumes far fewer tokens than loading the whole book into the context window. The tool also supports folding new sources into an existing skill, so a growing collection of papers or documents stays a single unified skill. Although the name refers to books, the documented inputs are any structured prose: internal architecture decision records, runbooks and onboarding guides, brand and design system documents, research paper clusters with personal notes, and specifications or standards such as RFCs. It targets developers and technical readers who use agent CLIs and want durable, queryable reference material derived from documents they already own, rather than repeated retrieval over raw PDF files.
https://github.com/virgiliojr94/book-to-skill
Taste Skill provides portable AI Agent Skills designed to enhance the quality of AI-generated frontends and image-based design references, aiming to eliminate generic UI outputs.
Unsloth is a toolkit for fine-tuning and reinforcement learning of large language models, enabling faster training with significantly reduced VRAM usage across various advanced models and tasks.
AgentGPT is an open-source platform that allows users to assemble, configure, and deploy autonomous AI agents in a web browser to pursue custom goals by generating and executing tasks independently.
OpenClaude is an open-source command-line interface (CLI) coding-agent that supports various cloud and local model providers for unified AI-driven development workflows.
An open-source Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and integration within the Google ecosystem.
Oh My Pi is an AI coding agent for the terminal featuring hash-anchored edits, an optimized tool harness, LSP integration, and support for Python, browsers, and subagents.
React Doctor is an intelligent agent designed to diagnose and fix issues within React codebases, leveraging AI to improve code quality and developer efficiency.
A curated and comprehensive list of tools, projects, and resources centered around the LangChain framework for developing and deploying large language model applications.