● Covered by 1 source · 1 reportLow impact1 neutral
New Agent Skill Forces LLMs to Write Documentation in ASD-STE100 Simplified Technical English
Key points
- The agent skill enforces ASD-STE100 Simplified Technical English for LLM outputs.
- It is compatible with various agent harnesses including Claude Code, Cursor, and VS Code Copilot.
- Testing showed a 72.9% reduction in STE violations and decreased output tokens.
- Installation involves a simple CLI command or manual prompt integration for unsupported LLMs.
Introduction of Simplified Technical English Skill
An agent skill has been developed to guide Large Language Models (LLMs) in producing documentation that conforms to ASD-STE100 Simplified Technical English. This standard, established in 1983 for the aerospace industry, focuses on clear, unambiguous language to prevent misinterpretation of instructions. The skill is designed to mitigate 'AI slop' by enforcing structured writing.
Compatibility and Performance
The skill integrates with numerous agent harnesses, including Claude Code, Cursor, VS Code Copilot, OpenAI Codex, and Gemini CLI, among others. Performance metrics from tests across six Claude models and eight tasks showed a 72.9% reduction in STE violations per 100 words and a decrease in output tokens. The mean sentence length was also reduced from 11.2 to 9.7 words, indicating more concise writing.
Installation and Usage
Users can install the skill via a command-line interface (CLI) using 'npx skills add AminBlg/SimpleEnglish', which detects and installs the skill for compatible agents. For LLMs without native skill support, such as ChatGPT and Gemini, users can integrate a provided system prompt into custom instructions or project settings. The skill can be activated by asking for technical writing or by explicitly requesting a rewrite with 'simple-english'.
Underlying Principles
The skill is based on 53 numbered rules across nine sections of the ASD-STE100 standard. These rules were originally formulated to ensure clarity in technical communication, especially in contexts where ambiguity could lead to significant issues. The skill applies these principles to various forms of technical writing, including READMEs, error messages, incident reports, and release notes.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub cmc_internal/api GitHub github/collect GitHub AminBlg/SimpleEnglish GitHub _private/browser GitHub get-started/accessibility GitHub open-source/sponsorsReporting from
A new agent skill has been released that compels Large Language Models (LLMs) to generate technical documentation adhering to the ASD-STE100 Simplified Technical English standard. This tool aims to improve clarity and reduce ambiguity in AI-generated technical content, which is particularly relevant for industries where precise instructions are critical.