news

Qwen3.6-35B-A3B

Qwen3.6-35B-A3B is an open-weight LLM) from the Qwen family (Alibaba Cloud), released in April 2026. Following the Qwen MoE naming convention, the model has 35B total parameters with ~3B active per token (the `A3B` suffix), making it runnable on consumer hardware via quantization.

Gemini 3.1 Flash TTS

Google's latest Text-to-Speech (TTS)) model (April 2026), part of the Gemini family. Focused on controllability, expressivity, and quality for developers and enterprises building speech applications. Complements Gemini 3.1 Flash Live (real-time dialogue) with higher-quality, more controllable offlin

Gemini 3.1 Flash Live

Google's highest-quality audio and voice model (March 2026). Designed for natural real-time dialogue with improved precision and lower latency. Part of the Gemini model family.

Claude Code Auto Mode

Auto mode is a permission mode in Claude Code where Claude makes permission decisions on behalf of the user, with a background classifier reviewing each action before it runs. It sits between the default mode (approve everything) and `bypassPermissions` / `--dangerously-skip-permissions` (approve no

Claude Code Tips and Best Practices

- Course correct early and often: cancel whatever Claude is doing and adapt your prompt whenever needed - Use `claude --continue` to continue your last conversation - Use `/clear` to keep the context "clean" (focused) - Use `/add-dir <new dir>` to work with multiple directories in a single session -

Claude Opus 4.7

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.

AI Agent Skills in Chrome

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.

My Published AI Skills

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.

Two New AI Skill Suites for Research Papers (arXiv and OpenAlex)

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

Expander plugin for Obsidian

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.

Obsidian Plugin Template (Bun)

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.

Hidden Folders Access plugin for Obsidian

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