Technical English logo

Technical English

Community
jsath
technical-english

Rewrite or audit any text using the principles of ASD-STE100 Simplified Technical English, the aerospace writing standard built for flight manuals. Kills AI slop by force - short sentences, one approved meaning per word, active voice, no filler. Use when asked to "simplify this", "de-slop this", "make this clearer", "rewrite in plain English", "apply STE", or when documentation, instructions, README files, or AI-generated text need to be readable by every English speaker, including non-native ones.

Overview

Publisherjsath
Repositorysimplified-technical-english
Skill nametechnical-english
Stars
86
Forks
10
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jsath on GitHub. Read the source before you install it.

Installation

Install the Technical English AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jsath/simplified-technical-english/tree/main/skills/technical-english
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jsath/simplified-technical-english.git /tmp/simplified-technical-english
mkdir -p .claude/skills
cp -r /tmp/simplified-technical-english/skills/technical-english .claude/skills/technical-english
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Technical English in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Technical English on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Technical English is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Technical English (STE-inspired)

Aircraft maintenance manuals cannot afford ambiguity. A mechanic who misreads one sentence can kill people. So the aerospace industry built ASD-STE100 Simplified Technical English: a controlled language where every word has one meaning, every sentence has a length limit, and every instruction is a command.

AI-generated text fails in the exact opposite way: long sentences, hedged claims, five-syllable words doing two-syllable jobs, and filler that sounds like content. Applying STE principles to it is a mechanical de-slop pass.

This skill applies those principles. It is inspired by ASD-STE100 and is not the official specification (see the attribution note at the end).

The rules

Apply all of them. When two rules conflict, clarity wins.

1. One word, one meaning

Every word keeps its most common meaning and its most common part of speech. "Follow" means "come after", never "obey". "Check" is a verb, not a noun. If a word can be read two ways in context, replace it.

2. Sentence limits (count, do not guess)

  • Instructions: 20 words maximum.
  • Descriptions: 25 words maximum.
  • Paragraphs: 6 sentences maximum, one topic each. Count the words of every sentence you output. A 21-word instruction is a violation, not a style choice.

3. One instruction per sentence

"Remove the cover and disconnect the cable and check the seal" is three instructions. Write three sentences. Sequences become numbered lists.

4. Active voice, imperative instructions

  • Instruction: "Remove the bolt." Never "The bolt should be removed."
  • Description: name the agent. "The pump moves the fuel", not "the fuel is moved." Passive voice is permitted only when the agent is truly unknown or irrelevant, and never in an instruction.

5. Present tense

Write what is, not what will be or would be. "The valve opens when pressure reaches 30 psi." Use past or future only when the fact itself is past or future.

6. Keep the articles

Do not drop "the", "a", "an" to save words. "Close valve" reads like a telegram; "Close the valve" reads like an instruction.

7. Break noun clusters

More than three nouns in a row is a wall. "Main gearbox oil pressure warning light" becomes "the warning light for the oil pressure of the main gearbox."

8. Warnings come first

Command first, then the condition: "Do not open the cover before you disconnect the power." Never bury the danger at the end of the sentence.

9. The substitution table

Replace unapproved words with their plain equivalents:

Never writeWrite
utilize, leverageuse
commence, initiatestart
terminatestop
accomplish, perform, executedo
sufficientenough
demonstrate, indicateshow
ensuremake sure
facilitatehelp
prior tobefore
subsequent toafter
in order toto
additionally, furthermore, moreoveralso
approximatelyabout
numerousmany
obtainget
requireneed
attempttry
modificationchange

10. The AI-slop blocklist

Delete on sight, they carry no information: delve, crucial, comprehensive, seamless, robust, cutting-edge, game-changer, landscape, realm, tapestry, unlock, elevate, foster, streamline, "it's important to note", "it's worth mentioning", "in today's world", "at the end of the day". Also delete every em dash; use a comma, a colon, or a full stop.

How to run

Rewrite mode (default). Take the input text and:

  1. Read the whole text first. Identify its purpose: instruction, description, or mixed.
  2. List the violations you found (rule number + the offending words). Keep this list short and specific.
  3. Rewrite the full text under the rules above. Preserve every fact. Never add a fact, a number, or a claim that the input does not contain.
  4. Verify: recount sentence lengths, rescan for blocklist words and passive instructions. Fix what you find.
  5. Output the rewrite first, then the violation list under a ## What changed heading.

Audit mode. When asked to audit (not rewrite), output only the violation report: rule number, quoted offending text, suggested fix, one line each.

Light mode. For marketing copy, posts, or anything with a voice worth keeping, apply only rules 2, 4, 9, and 10, and say you did. Full STE strips personality by design; do not apply it to text that needs one unless asked.

What this skill refuses to do

  • It does not shorten by deleting facts. If the input is 40 facts, the output is 40 facts in shorter sentences.
  • It does not simplify quoted text, code, commands, or error messages. Those are exact strings; leave them exact.
  • It does not guess a missing fact to complete a sentence. It marks the gap: "[value missing]".

Example

Before (typical AI output, 44-word sentence):

In order to facilitate the seamless integration of the authentication module, it is important to note that developers should ensure that the configuration file has been comprehensively updated prior to commencing the deployment process, which can be accomplished via the CLI.

After (STE principles, longest sentence 11 words):

Update the configuration file before you start the deployment. Use the CLI to deploy. This connects the authentication module.

Same facts. A third of the words. No ambiguity.


Attribution: Inspired by ASD-STE100 Simplified Technical English, a specification maintained by the AeroSpace and Defence Industries Association of Europe. This skill applies its principles and is not the official specification or its dictionary. The official specification is available free from asd-ste100.org.

Frequently asked questions

What does the Technical English AI skill do?

Rewrite or audit any text using the principles of ASD-STE100 Simplified Technical English, the aerospace writing standard built for flight manuals. Kills AI slop by force - short sentences, one approved meaning per word, active voice, no filler. Use when asked to "simplify this", "de-slop this", "make this clearer", "rewrite in plain English", "apply STE", or when documentation, instructions, README files, or AI-generated text need to be readable by every English speaker, including non-native ones.

Why use Technical English on TypingMind?

Because you install it once and use it with any model. Technical English is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Technical English in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jsath/simplified-technical-english/tree/main/skills/technical-english. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Technical English?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Technical English?

As many as you like. As long as a model supports skills, you can use Technical English with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Technical English AI skill free?

Yes. It is published on GitHub by jsath under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇