Skip to content

Instantly share code, notes, and snippets.

@raoulbia-ai
raoulbia-ai / a2a_agent_connector.py
Created January 15, 2026 12:52
A2A Agent Connector Component for Langflow. Connects to remote agents using Google's A2A (Agent-to-Agent) Protocol. Drop this file into your Langflow custom components directory. License: MIT
"""Requirements: pip install a2a-sdk httpx"""
from __future__ import annotations
import uuid
from typing import TYPE_CHECKING, Any
from langflow.custom import Component
from langflow.io import (
IntInput,
MessageInput,
@raoulbia-ai
raoulbia-ai / a2a_server_agent.py
Last active January 15, 2026 12:53
A2A Server Agent Component for Langflow. A tool-calling agent that exposes itself via Google's A2A (Agent-to-Agent) Protocol. Drop this file into your Langflow custom components directory. License: MIT
"""Requirements: pip install a2a-sdk"""
from __future__ import annotations
import uuid
from typing import TYPE_CHECKING
from langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent
from langflow.io import BoolInput, FloatInput, IntInput, Output, StrInput
from langflow.schema.message import Message

Claude Skills: How SKILL.md Works

Research findings on Anthropic's Skills system for Claude Code.

Overview

Skills are a filesystem-based mechanism for extending Claude's capabilities with domain-specific expertise. Each skill is a directory containing a SKILL.md file with optional supporting resources.

Directory Structure

@raoulbia-ai
raoulbia-ai / llm-finetuning-training-conversion-guide.md
Created December 14, 2025 21:57
LLM Fine-Tuning: Training & Conversion Guide - LoRA, GGUF, Ollama Pipeline

LLM Fine-Tuning: Training & Conversion Guide

A technical guide explaining the fine-tuning process for domain-specific LLMs, with rationale for each step.

1. Overview

Goal: Fine-tune Qwen2.5-Coder-14B for TagUI (browser automation DSL)

Why Fine-Tuning?: Base models don't know domain-specific syntax. Qwen-Coder is excellent at Python/JS but generates invalid TagUI code. Fine-tuning teaches the specific DSL patterns.

@raoulbia-ai
raoulbia-ai / devcontainer.json
Created August 3, 2025 08:09
claude-flow devcontainer json file
{
"name": "Claude Flow Development",
"image": "mcr.microsoft.com/devcontainers/base:debian",
"features": {
"ghcr.io/devcontainers/features/node:1": {},
"ghcr.io/devcontainers/features/python:1": {},
"ghcr.io/devcontainers/features/docker-in-docker:2.12.2": {
"version": "latest",
"moby": true
}
@raoulbia-ai
raoulbia-ai / mcp-obsidian-whatsapp-windows-setup-guide.md
Last active July 21, 2025 14:40
Complete step-by-step guide for installing and configuring MCP Obsidian and WhatsApp MCP servers on Windows. Includes Node.js setup with nvm-windows, device linking for WhatsApp, Claude Desktop configuration, troubleshooting common issues, and sample JSON configs. Perfect for getting both MCP servers running smoothly on Windows 10/11.

Installing & Running MCP Obsidian and WhatsApp MCP on Windows

Prerequisites

  • Admin rights on your system
  • Windows 10/11 (PowerShell or CMD for all terminal steps)
  • Node.js v23.10.0 or later (installed via nvm-windows is recommended)
  • Git
  • Claude Desktop or another MCP-compatible agent

Change any part of the paths to match your folders.

@raoulbia-ai
raoulbia-ai / claude-flow-codespace-setup-guide.md
Last active January 15, 2026 17:57
Complete setup guide for Claude-Flow AI agent swarms in GitHub Codespaces. Includes universal dev container config for Docker/Kubernetes/Codespaces, authentication workflow, and community-tested troubleshooting. Based on AI Code Chat community discussions.
"""
OpenAI Agent SDK & MCP Example: Rental Listings Orchestration
This script demonstrates orchestrating multiple AI agents using the OpenAI Agent SDK (`agents` library)
and its Model Context Protocol (MCP) extension (`openai-agents-mcp`)
to automate the process of finding rental listings and notifying users.
Key Concepts Illustrated:
- Agent Definition: Defining specialized agents (`ListingURLsAgent`, `IndividualListingAgent`, `EmailMetadataAgent`, `OrchestratorAgent`)
using both the core `agents.Agent` and MCP-enabled `agents_mcp.Agent` classes.