Claude Opus 4.7 is the Claude Opus model released by Anthropic on 2026-04-16. It was the frontier model for long-running agentic work until Claude Opus 4.8 (released 2026-05-27) succeeded it, with stronger instruction adherence, self-verification, and cross-session context handling than Opus 4.6.
Google's "Skills in Chrome" (April 2026) lets users save frequently-used prompts as reusable one-click workflows inside Gemini in Chrome. A Skill is a saved prompt that can be re-applied to the current page and any selected tabs, turning repeated AI tasks into named, editable tools.
Here's a list of the AI Agent Skills I've created & published. I have many more, but these are the ones I've decided to publish as individual & reusable skills on GitHub.
I shipped two open-source Agent Skill suites today for anyone who searches/reads research papers with the help of AI. Both are MIT-licensed, have zero dependencies, and conform to the open Agent Skills specification. Thus they work with Claude, Cursor, Gemini CLI, OpenCode, Goose, and every other sk
Obsidian plugin that is able to replace variables across your vault using HTML comment markers. Supports static values and dynamic functions for values, and can also automatically update metadata properties.
Opinionated GitHub template for building Obsidian Community Plugins on top of Bun and TypeScript. Wraps the full toolchain (bundler, linter, formatter, test runner, commit tooling, release workflow) and a structured `AGENTS.md` so coding agents can ship features end-to-end without guesswork.
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.
A clear roadmap to building your own knowledge system. Subscribe and get it straight to your inbox.
6,000+ readers. No spam. Unsubscribe anytime.
