Hey Clief Notes, I'm Bas, and I want to share something I built for anyone working with AI: Praxis Library at praxislibrary.com. It started as a personal reference, the kind of thing I wished existed when I was learning prompting, frameworks, and how AI systems actually behave. It's grown into a living, free, open knowledge base, and I'd love feedback from this community. What's inside - A glossary of 5,319 AI terms, searchable and defined in plain language. No jargon walls. - 175 techniques and frameworks across 14 categories, including Chain-of-Thought, CO-STAR, CRISP, CRISPE, ReAct, and Flipped Interaction. Each has examples, use cases, and tips. - A full AI history timeline, five eras from the foundations through today's LLMs, with 61 techniques placed in their original context. Free interactive tools (Works in progress!) - Prompt Analyzer: paste a prompt, get a structural breakdown. - Prompt Builder: build a structured prompt step by step. - Technique Finder: describe what you're trying to do, get matched to the right technique. - Persona Architect: design a clean, reusable AI persona. - Hallucination Spotter: practice catching common hallucination patterns. - Preflight Checklist: a quick gut-check before sending a prompt to production. - Readiness Quiz: a self-assessment for where your AI literacy sits today. - Patterns Library and an AI Safety hub. It's also built with a strict A+ Content Security Policy, no external trackers, no third-party fonts, no analytics following you around. Just the content. It's designed to be neurodivergent-friendly and WCAG 2.1 AA accessible, with a built-in accessibility dashboard for text size, high contrast, read-aloud, and screen dimming. (This is a P.O.P - Product of Passion, and to be candid, I have limited time to work with AI. which brings me to the below) Information you can trust(?) Every external citation on the site is screenshot-verified by a human and registered in a public audit log before it goes live. The audit report is open, so you can see exactly what's verified and what isn't.

Most people customise Claude in one place: The prompt. The two surfaces that actually shape every session, you ignore. How Claude talks to you, and how you read what's happening. Both are configurable. Both compound across hundreds of hours. The framework I run, and how to set it up: Surface 1: The voice Claude has defaults. They're fine. They're not yours. I'm dyslexic. Walls of text are invisible to me. So my Claude has a non-negotiable response format, written into ~/.claude/CLAUDE.md: Every reply ends with a bold marker: → DECISION, → QUESTION, → NO DECISION NEEDED. I know what's required of me in under three seconds of skimming. Header tier = importance, not nesting depth. # is THE headline. ## is a main section. #### is an inline label. The size matches how load-bearing it is to read. `mono font` is reserved for paths, values, commands. Never for emphasis. The font swap is a signal. --- between major pivots like status to decision. The horizontal rule is the unmissable section break. Bold keywords inside sentences. Dyslexic eyes skim for bold anchors. Absolute paths only, so cmd+click opens them from inside the terminal. If you also use Codex, mirror the same rules to ~/.codex/AGENTS.md. Two harnesses, one voice. Surface 2: The interface The Claude Code statusline runs once per turn, costs zero tokens, can render colour. Mine shows: 47% · opus-4.7 · WORKSPACE · main* · 2🛠 · 02:41 Six fields: context %, model, workspace name, branch + dirty flag, dispatch worker count, session clock. Colour-coded by zone. Context % goes green under 50%, yellow at 50-75%, red at 90%. Branch yellow when dirty, red on conflict. Workspace gets a brand colour mapped from the path I'm in. The 50% threshold matches the rule already written into my voice config: write a session handoff at 50% context. Now I can see the threshold without asking. How to set this up Customise the voice. Open ~/.claude/CLAUDE.md. Write your own rules. Mine took an afternoon to draft and three weeks of iteration to lock down. Yours will start ugly. That's fine.