Matt Pocock's Experiment with ASD-STE100 and Ubiquitous Language in CLAUDE.md

X postMatt PocockOpinion

Matt Pocock shares a new experimental directive for his global CLAUDE.md, instructing Claude to write in ASD-STE100 Simplified Technical English and adopt terminology from CONTEXT.md files.

Key points

  1. Pocock adds a rule instructing Claude to communicate strictly in ASD-STE100 Simplified Technical English.
  2. The directive mandates reading CONTEXT.md files and adopting their ubiquitous language.
  3. The experiment aims to enforce conciseness and project-specific consistency in agent outputs.

Why it matters

Global configuration files like CLAUDE.md set baseline behaviour across AI development workflows. Enforcing structured writing rules and domain glossaries minimises conversational drift and ambiguity.

Analysis

Pocock's rule combines two concepts: ASD-STE100, an aerospace standard designed to eliminate linguistic ambiguity through restricted vocabulary, and Domain-Driven Design's ubiquitous language. Rather than prompting the model to reason differently, this method anchors Claude to a formal technical writing standard while directing it to source its core terminology straight from CONTEXT.md.

Original post

Matt Pocock

@mattpocockuk · 4 August 2026

Experimenting with a rare addition to my global CLAUDE.md: "Always talk in ASD-STE100 Simplified Technical English. Always read CONTEXT.md files, and use their ubiquitous language."

5k likes223 replies6.1k bookmarks1m views

View on X
Selected replies (5)
  • @chuks_nwob @mmatthias @mattpocockuk Hey I tried it and I love it. I also have the I have adhd turned on by default
  • @chsweb @mattpocockuk Testing this exact same thing, except in my case, I am telling Claude and Open AI to use the frameworks & the language that I have created personally over the past 24 years. There's something inherently wonky about getting AI to follow instructions, which is really ironic.
  • @AIAppsAPI @mattpocockuk The ubiquitous language half is the sharp part. Most CLAUDE.md entries try to change how the model thinks. That one just tells it where the vocabulary already lives. The thing a static file cannot do is age. A convention you wrote in March and one your team actually uses daily
  • @W_RyanSmith @mattpocockuk Tried ASD-STE100 with Zinsser for Claude's writing style. STE's restricted vocabulary kills the voice Zinsser asks for, so dropped STE, kept the four Zinsser principles: simplicity, brevity, clarity, humanity. Shipped it as a Claude Code Output Style for one project via /config.
  • @FereydunHashemi @mattpocockuk Have you seen this: t.co/x6ELrFgeZn

Mentioned links

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:0xpili/simplified-technical-english

    Simplified Technical English as an Agent Skill for LLMs

    An open-source project provides prompt guidelines and checking tools to help LLMs like Claude write and review technical documentation according to the ASD-STE100 standard.

    790starsPython

    AI & LLMs· Tool

  • X post:pili 🪴

    ASD-STE100 Agent Skill: Cutting LLM Slop in Terminal Outputs

    A new open-source agent skill instructs language models to write in ASD-STE100 Simplified Technical English. Originally designed for aerospace documentation, the controlled language forces AI outputs to be concise, direct, and unambiguous.

    6kbookmarks307.4kviews

    AI & LLMs· Tool

  • X post:PostHog

    The Evolving Role of AGENTS.md and CLAUDE.md Context Files

    This discussion explores the effectiveness of using context files like AGENTS.md or CLAUDE.md to guide AI coding assistants. While some developers find them essential for project-specific instructions, others argue they often become technical debt that grows stale and hinders model performance.

    1.1kbookmarks48kviews

    AI & LLMs

  • Article:Anthropic

    How Claude Code Retains Project Context: CLAUDE.md and Auto Memory Explained

    Anthropic outlines the memory architecture of Claude Code. Because every session starts with a clean context window, the CLI tool relies on two complementary systems: user-defined CLAUDE.md files for explicit instructions and an auto memory feature that records learnings from user feedback.

    AI & LLMs· Resource

  • Article:Rui Sousa, Luis Sousa

    Tutorial: Building a CLAUDE.md File for Claude Code

    Rui and Luis Sousa share an approach to loading permanent business context into Claude Code via a root CLAUDE.md file, eliminating the need to repeatedly explain business details in every new session.

    AI & LLMs· Tutorial

  • Repository:multica-ai/andrej-karpathy-skills

    CLAUDE.md Ruleset Based on Andrej Karpathy's LLM Coding Observations

    This repository provides a single CLAUDE.md configuration file designed to improve Claude Code's performance. It translates Andrej Karpathy's observations on common LLM coding pitfalls into four actionable instructions to reduce overengineering and unintended code edits.

    210.3kstars

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.