TIL

Project-specific skills in Claude Code

The superpowers /using-superpowers skill is basically a table of contents of related skills you can use together. Good pattern to steal for your own project.

Skills in .claude/skills/ are already auto-detected — Claude picks them up and uses them when relevant. So bvdr-write, add-stack-entry, bvdr-add-til all live there and Claude will reach for them when it thinks they match the task. That's the passive mode — it works, but Claude decides when to use what.

A master command like /using-bvdr-skills flips that. Instead of waiting for Claude to recognize the context, you enforce it upfront. Load the table of contents at the start of a session and Claude knows exactly which skills are available, how they relate to each other, and when to use them. Passive availability vs active enforcement.

Two ways to think about it: reference them in CLAUDE.md if you want them always loaded for the project, or use the master command when you want granular control — load the full context for a deep session, skip it for a quick fix.

Go to Claude Code /plugins , search for superpowers and install it. Once installed restart and start a new session with /using-superpowers

Claude Code Skills

Found out the best way to create custom skills for Claude Code is by using a specialised skill that knows exactly how to build it for you. What you’re looking for:

• To get it fire automatically when detecting some keywords
• Agents should know how to use it

There's also a writing-skills one that applies TDD thinking to writing these. Used it to put together a tech blog writing skill. 👌

AI to ALLOW or DENY commands in Claude Code

I am following Boris Cherny and in this tweet he mentions:

c. Route permission requests to Opus 4.5 via a hook — let it scan for attacks and auto-approve the safe ones (see code.claude.com/docs/en/hooks#permissionrequest)

Based on this I steered Claude to build a plugin called smart-permissions - there are two layers, one regex search that automatically allow non harmful commands, everything else that escapes is catched by layer 2 which is an AI evaluation tool that decide ALLOW or DENY. It’s not perfect.

I’m having some trouble getting the default dialog to show when AI denies the tool call.

Notion As CRM

Using Notion as a CRM for the website is really cool! I've had this in mind for a long time, but back then the Notion API wasn't public, so it was only possible in hacky ways. Cool!

Claude code /insignts command that would show you what it knows about you