Animations for System Builders(brooker.co.za)
55 points by KraftyOne | 3 comments
Marc Brooker blog post showing LLM-built animations of system failures: Raft lost writes from lying fsync, and metastable failures in Postgres and etcd.
#llm-tools on Hacker News
8 stories tagged llm-tools, newest first.
Agent-Skills.market(agent-skills.market)
7 points by agentsmithvl | 3 comments
Agent Skills is a searchable directory of 256 AI agent skills for non-developers and developers, with categories and skill submissions.
AI-assisted PCB design for KiCad 10(github.com)
115 points by ofrzeta | 42 comments
GitHub repository for Konnect, a native KiCad 10 plugin in Rust exposing 217 PCB design tools to Claude or other LLMs for AI-assisted design.
Creating a Garmin "MCP"(jackantico.io)
51 points by ricotico060 | 56 comments
A personal project write-up about building a Garmin "MCP" to ask an AI questions about one's workout and health data.
What is Codemode(lucumr.pocoo.org)
138 points by Tomte | 60 comments
Armin Ronacher blog post explaining Codemode and why Pi 1.0 added MCP support through it, revisiting his earlier argument that agents should use code over tools.
I was banned from Claude for scaffolding a Claude.md file?(hugodaniel.com)
686 points by hugodan | 588 comments
A personal blog post recounting how the author's paid Claude Max account was disabled after using Claude Code to scaffold a CLAUDE.md file.
OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI(simonwillison.net)
524 points by simonw | 303 comments
Simon Willison blog post reporting that OpenAI has quietly added Anthropic-style skills support to ChatGPT's Code Interpreter and the Codex CLI.
MCP: An (Accidentally) Universal Plugin System(worksonmymachine.substack.com)
729 points by Stwerner | 322 comments
A Substack essay by Scott Werner arguing that Anthropic's Model Context Protocol works as an accidental universal plugin system, using a USB-C analogy.