AI Agent Skills

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

PPT image-first skill for Codex/Claude Code/Opencode CLI

μscope 🔬

AI Agent Evaluator & Red Team Platform

HTTP Toolkit is a beautiful & open-source tool for debugging, testing and building with HTTP(S) on Windows, Linux & Mac :tada: Open an issue here to give feedback or ask…

Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review st…

Claude Code skill that translates entire books (PDF/DOCX/EPUB) into any language using parallel subagents

[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the mode…

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plu…

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinemen…

DEPRECATED: Like diff but for PostgreSQL schemas

Rust task runner and build tool.

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

Kint - Advanced PHP dumper

Instant Markdown previews from Vim

REST implementation of Django authentication system.