Skip to content

Instantly share code, notes, and snippets.

View HiChen404's full-sized avatar
:octocat:
Focusing

Pika HiChen404

:octocat:
Focusing
View GitHub Profile
@dabit3
dabit3 / pi_tutorial.md
Last active August 25, 2026 10:27
How to Build a Custom Agent Framework with PI: The Agent Stack Powering OpenClaw

PI is a TypeScript toolkit for building AI agents. It's a monorepo of packages that layer on top of each other: pi-ai handles LLM communication across providers, pi-agent-core adds the agent loop with tool calling, pi-coding-agent gives you a full coding agent with built-in tools, session persistence, and extensibility, and pi-tui provides a terminal UI for building CLI interfaces.

These are the same packages that power OpenClaw. This guide walks through each layer, progressively building up to a fully featured coding assistant with a terminal UI, session persistence, and custom tools.

By understanding how to compose these layers, you can build production-grade agentic software on your own terms, without being locked into a specific abstraction.

Pi was created by @badlogicgames. This is a great writeup from him that explains some of the design decisions made when creating it.

The stack

@spboyer
spboyer / skills-mcp-development-guide-v2.md
Last active August 24, 2026 07:34
Skills, Tools & MCP Development Guide v3 - Cross-model description compatibility, WHEN: triggers, anti-trigger deprecation

Skills, Tools & MCP Development Guide

A Practical Guide for Building Agent Capabilities

"Skills orchestrate the how. MCP Tools execute the what."

This guide consolidates learnings from building AI agent capabilities for Azure, focusing on the relationship between Skills (workflow orchestration) and MCP Tools (discrete operations). Whether you're creating a new Copilot Skill, building an MCP server, or integrating both, this document provides the architecture patterns, development best practices, and real-world case studies you need to build effective, non-conflicting agent capabilities. The core principle is simple: Skills act as the "brain" that orchestrates complex workflows, while MCP Tools serve as the "hands" that execute individual operations—and Skills should invoke MCP Tools, not duplicate them.


@Zamua
Zamua / apply-claude-code-2.0.76-lsp-fix.sh
Last active August 3, 2026 01:57
script to patch claude-code 2.0.76 to fix lsp plugin
#!/bin/bash
#
# Claude Code LSP Fix
# ====================
# Fixes the LSP plugin bug: https://github.com/anthropics/claude-code/issues/13952
#
# THE BUG:
# Claude Code's LSP manager has an empty initialize() function that should
# load and register LSP servers from plugins, but instead does nothing.
# This causes "No LSP server available for file type" errors.
{
"apiVersion": "dashboard.grafana.app/v2beta1",
"kind": "Dashboard",
"metadata": {
"name": "claude-code-metrics",
"generation": 12,
"creationTimestamp": "2025-12-10T13:33:56Z",
"labels": {},
"annotations": {}
},

Opencode plugin development guide

Generated with LLM assistance on 2 Nov 2025 with minimal human verification.

Overview

Opencode plugins extend the functionality of the Opencode AI assistant by allowing you to add custom tools, authentication providers, event handlers, and hooks into the core system. This guide covers how to create, configure, and distribute plugins.

Source files: