Muratcan Koylan

Agent-Skills-for-Context-Engineering. A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

ralph-wiggum-marketer. A Claude Code Plugin that provides an autonomous AI copywriter.

AI-Investigator. An automated AI system (Python framework) designed to analyze any type of website content and generate structured reports using Claude 3.5 Sonnet API and Firecrawl. While currently configured for enterprise AI case studies, the architecture can be adapted for various content analysis needs.

The-Rosetta-Prompt. A prompt optimization system that adapts your prompts for different AI providers.

readwren. An adaptive multi-agent system that extracts your literary DNA through conversation and generates actionable reading profiles.

Food-tour-planner-agent. Food tour planner using LangChain DeepAgents, Google Maps API, and Tavily research. Explore multi-agent coordination patterns: task delegation via SubAgentMiddleware, planning with TodoListMiddleware

linkedin-analyzer. The LinkedIn Profile Insight Tool is designed to leverage advanced AI models, such as Cohere Command R+, to provide detailed analysis and insights into LinkedIn profiles.

book-training. A complete pipeline for training language models to write in a specific author's style using Supervised Fine-Tuning (SFT) with LoRA.

prompts.

actual_code. ActualCode is a code assessment platform that analyzes real GitHub repositories and generates personalized, realistic coding challenges using a 7-agent AI architecture powered by Google's Gemini models and the A2A (Agent-to-Agent) protocol.

memory-routing-agent. Prompt distillation with Thinking Machines: training a small, specialized model to outperform the large model that generated its training data.

Impossible-Moments. A 420-scenario AGI benchmark for creative constraint satisfaction, built entirely in a single Claude Code session with Opus 4.6.

composioskills. A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

peoplereadmes. Open-source persona context systems for studying exceptional public builders, artists, researchers, and creative operators.

feed2context. One‑click feed → report for LinkedIn and X. Capture a post, auto‑shape a research query, search with reasoning, and get a detailed research report in seconds.

BACKPRESSURE. A file format for defining deterministic self-verification checks that AI coding agents run on their own output. Like AGENTS.md tells agents how to behave, BACKPRESSURE.md tells agents how to know they are wrong.

Intent-based-Prompt-Calibration. A system for automatic prompt optimization using Claude 3.5 models. IPC enables dynamic prompt refinement through iterative testing and improvement cycles, particularly useful for complex tasks like content moderation.

Prompt-Obfuscation. Embedding Space Manipulation

MiniMax-M2-Interleaved-Thinking. Interactive demo showcasing MiniMax-M2's interleaved thinking for agentic workflows, demonstrating adaptive strategy after each tool call with transparent traces and cost benchmarking.

digital-forks. TypeScript

langgraph-studio. Desktop app for prototyping and debugging LangGraph applications locally.

awesome-llm-role-playing-with-persona. Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas

youtune. Fine tune SDXL on YouTube videos

suna. Suna - Open Source Generalist AI Agent

jeezaieduchain. Python

feed2report. Python

browser-use. Make websites accessible for AI agents