I help you organize your thoughts, life & work⚡
An Obsidian plugin that makes hidden root-level folders (names starting with a dot, e.g. `.claude`, `.github`) fully visible to Obsidian — file explorer, search, graph, metadata cache, and Bases — while keeping their names unchanged on disk so external tools (like Claude Code, git, editors, ...) kee
I built a new Obsidian plugin this morning; one adding a feature I've been missing for a long while now.
Today I shipped a few things around health tracking in my Obsidian vault. They all click together.
A Routine is a saved Claude Code configuration (prompt, repositories, environment, connectors) that runs automatically on Anthropic-managed cloud infrastructure. Routines generalize the earlier Claude Code Web Scheduled Tasks concept by adding multiple trigger types to the same saved session. Resear
An open-source AI Agent Skill (MIT License) that fetches health and exercise data from Garmin Connect and makes it available to AI agents. I built it to pipe data from my Garmin Venu 3 straight into my Obsidian daily notes.
#pillar-creator-systems
Your AI skill works perfectly on your machine, then falls apart for everyone else. Here are the twelve portability traps that break AI skills the moment they leave your environment, and exactly how to fix every single one of them.
I've just launched a new News page on my blog and a matching newsletter: DeveloPassion's News Flash.
Open-source LiteLLM configuration that lets Claude Code run against an Azure AI Foundry deployment instead of Anthropic's hosted API. Published by National Bank of Belgium. It's a thin wrapper: a `litellmconfig.yaml` with a wildcard model route, a `startproxy.sh` launcher, a Dockerfile, and a `.env`
Adds Tufte-style sidenotes and margin notes rendered in the margin of an Obsidian note. Inspired by Gwern.net and Edward Tufte's CSS conventions. Combines a CSS snippet with a plugin to handle behavior CSS can't (editing in margin, re-sequencing, etc.).
LiteLLM is an open-source AI Gateway that exposes 100+ LLM providers through a single OpenAI-compatible interface. It ships in two forms: a Python SDK for embedding the gateway logic inside applications, and a self-hostable proxy server (the "LLM Gateway") that centralizes access, spend tracking, an
This is my (Sébastien Dubois) Communications plan. It describes where/how I share information and ideas. It's part of my business flywheel.
Claude Code uses Anthropic's prompt cache to reuse large, stable chunks of context (system prompt, tool definitions, CLAUDE.md, prior turns) across requests instead of resending and re-billing them every turn. Cache reads are cheaper than uncached tokens; cache writes are more expensive than normal
A clear roadmap to building your own knowledge system. Subscribe and get it straight to your inbox.
6,000+ readers. No spam. Unsubscribe anytime.
