Simplified Technical English logo

Simplified Technical English

Community
0xpili
simplified-technical-english

Writes and rewrites text in Simplified Technical English (ASD-STE100), a controlled language for clear technical documentation. Use when the user asks for STE, Simplified Technical English, controlled language, or plain technical writing, and when the user asks to write, rewrite, review, or check technical documentation, procedures, manuals, instructions, warnings, or reports.

Overview

Publisher0xpili
Repositorysimplified-technical-english
Skill namesimplified-technical-english
Stars
970
Forks
47
Bundled files
6
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.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by 0xpili on GitHub. Read the source before you install it.

Installation

Install the Simplified 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/0xpili/simplified-technical-english/tree/main
  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/0xpili/simplified-technical-english.git \
  .claude/skills/simplified-technical-english
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Simplified 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 Simplified 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 Simplified 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.

Simplified Technical English

This skill makes you write in Simplified Technical English (STE). STE is a controlled language for technical documentation. The specification ASD-STE100 gives 53 writing rules and a dictionary of approved words. Text in STE is clear to readers who do not know much English.

Obey the rules in this file for all the technical text that you write. The rules in this file are the most important rules. The full set of rules is in references/writing-rules.md. The approved words are in references/word-list.md.

Scope

Apply STE to technical output: documentation, procedures, manuals, instructions, reports, error messages, and answers about technical subjects.

Do not apply STE to:

  • Marketing text or brand text
  • Poems, stories, or conversation
  • Code blocks, identifiers, commands, file paths, and quoted error messages
  • Quoted text and official names of products, parts, and documents.

If the user asks for a different style, the request of the user wins.

Step 1: Classify the text

Before you write, classify each part of the text:

  • Procedural text tells the reader to do something. Example: "Remove the four bolts."
  • Descriptive text gives information. Example: "The pump supplies fuel to the engine."

The two types have different limits. Do not mix the two types in one paragraph.

Step 2: Obey the verb rules

  • Use only these verb forms: infinitive, imperative, simple present, simple past, future with "will", and past participle as an adjective.
  • Do not use the "-ing" form of a verb. Approved "-ing" words are only: mating, missing, remaining, lighting, opening, routing, servicing, during.
  • Do not use a helping verb with a past participle. Write "the operator adjusted the linkage", not "the operator has adjusted the linkage".
  • Use the active voice. Write "a relay connects the circuits", not "the circuits are connected by a relay".
  • In procedures, use the imperative. Write "Set the switch to ON."
  • If there is no agent, use "you" or "we" as the subject.
  • Use only "can", "must", and "will" as helping verbs. Do not use "should", "would", "may", "might", or "shall".
  • A past participle after "is" or "are" shows a condition and is permitted. "The wires are disconnected."

Step 3: Obey the sentence rules

  • Procedural sentences: maximum 20 words.
  • Descriptive sentences: maximum 25 words.
  • Paragraphs: maximum 6 sentences, and only one topic.
  • Write only one instruction in each sentence. Two actions are permitted only when they occur at the same time.
  • Write only one topic in each sentence.
  • When a condition comes before a command, put a comma after the condition. "If the light comes on, stop the engine."
  • Keep the articles, the subjects, the verbs, and the conjunction "that". Write "make sure that the file exists".
  • Do not use contractions. Write "do not", not "don't".
  • Do not use semicolons. Write two sentences.
  • Use a vertical list for complex text. In a list of commands with "not", write "not" again in each item.

Step 4: Obey the word rules

  • Use only: approved words from references/word-list.md, technical names, and technical verbs.
  • A technical name is the official name of a part, tool, material, system, document, or term of your subject. Examples: "engine", "firewall", "torque wrench", "SKILL.md".
  • Use an approved word only as its given part of speech. "Test" is a noun, not a verb. Write "do a test", not "test the system".
  • Use one name for one item in the full text. Do not change between names for the same item.
  • Write noun clusters of maximum three words. Break long clusters with "of", "on", "in", or "for".
  • Do not make phrasal verbs. Write "extinguish the fire", not "put out the fire".
  • Do not use vague words. Write the specific quantity, name, or action.
  • Use American English spelling.
  • Common replacements are in references/substitutions.md.

Step 5: Write safety instructions correctly

  • Use "WARNING" for a risk of injury or death to persons.
  • Use "CAUTION" for a risk of damage to objects.
  • Start with a simple command or condition. Then give the risk.
  • Example: "WARNING: Do not touch the connector. The connector can have a dangerous voltage."

Step 6: Check your text

After you write, check your text. Do these steps:

  1. If you can run scripts, run: python3 scripts/ste_check.py --mode <procedural|descriptive> <file>.
  2. If you cannot run scripts, do a manual scan of the checklist below.
  3. Correct each error.
  4. Check the text again. Stop only when the text has no errors.

Manual scan checklist:

  • Find semicolons and contractions. Remove them.
  • Find "has", "have", and "had" before a past participle. Use the simple past tense.
  • Find "should", "would", "may", "might", and "shall". Replace them or remove them.
  • Find "-ing" words that are not approved and are not in technical names. Rewrite them.
  • Find passive voice. Make the agent the subject, or use the imperative.
  • Count the words in the longest sentences. Divide sentences that are too long.
  • Count the sentences in each paragraph. Divide paragraphs that have more than 6 sentences.
  • Find words that are not approved and are not technical names. Replace them.

The check tool cannot find all the errors. The tool cannot know if a word has its approved meaning. You must also compare your words with references/word-list.md.

Reference files

  • references/writing-rules.md — all 53 rules and 4 recommendations, with examples. Read this file when you rewrite a document or when a rule is not clear.
  • references/word-list.md — the 869 approved words with their parts of speech and forms.
  • references/substitutions.md — replacements for frequent unapproved words, and the categories of technical names and technical verbs.
  • examples/before-after.md — examples of text before and after the change to STE.

Basis

The source of this skill is ASD-STE100 Issue 7 (2017). ASD releases new issues of the specification. You can get the specification free of charge from https://www.asd-ste100.org. This skill is not an official ASD document. This skill cannot make sure that your text obeys the official specification fully. Refer to NOTICE.md for the copyright information.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Simplified Technical English AI skill do?

Writes and rewrites text in Simplified Technical English (ASD-STE100), a controlled language for clear technical documentation. Use when the user asks for STE, Simplified Technical English, controlled language, or plain technical writing, and when the user asks to write, rewrite, review, or check technical documentation, procedures, manuals, instructions, warnings, or reports.

Why use Simplified Technical English on TypingMind?

Because you install it once and use it with any model. Simplified 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 Simplified Technical English in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/0xpili/simplified-technical-english/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Simplified 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 Simplified Technical English?

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

Is the Simplified Technical English AI skill free?

It is published on GitHub by 0xpili. Check the repository for licensing terms. 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 👇