Writing Simplified Technical English

From the author

Write English that a reader cannot misread: one meaning per word, active voice, simple tenses, one idea per sentence, short sentences. Based on ASD-STE100 (Simplified Technical English), the controlled-language standard written for aircraft maintenance manuals. Use it for any prose an agent produces that someone else acts on. That covers reports and findings, PR descriptions and commit messages, instructions handed to another agent, tool descriptions, error messages, status summaries, and prompts. Also use it on request, with triggers like "simplify this", "make this readable", "too dense", "rewrite in STE", "simplified technical english", "ASD-STE100".

— the description by PostHog

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill implements the ASD-STE100 controlled-language standard to improve the readability and precision of agent-generated text. By enforcing rules such as active voice, simple tenses, and one idea per sentence, it eliminates ambiguity that often leads to misinterpretation. It is designed for technical documentation, instructions, error messages, and reports where clarity is critical for the reader or another agent to perform a task correctly. The skill provides a structured approach to rewriting dense or complex text while preserving essential technical details.

What it does

Enforces one meaning per word to prevent confusion.
Mandates active voice and simple tenses for direct communication.
Limits sentence length and complexity to ensure readability.
Restricts noun clusters to improve clarity.
Provides a framework for rewriting technical prose.
Ensures instructions are actionable and unambiguous.

When to use it

When writing reports, findings, or status summaries.
When drafting PR descriptions or commit messages.
When creating instructions or prompts for other agents.
When writing error messages, tool descriptions, or log lines.
When you need to simplify dense or overly complex technical text.

Advantages

Reduces the risk of misinterpretation by humans or agents.
Increases the efficiency of reading and acting on technical content.
Standardizes the style of agent-generated documentation.
Eliminates ambiguity caused by synonym rotation or complex grammar.
Maintains precision while improving overall clarity.

Usage examples

“Simplify this error message: An error may have occurred while processing your request due to a possible mismatch in the expected data format, which could be caused by an outdated client version.”: The request failed. The data format did not match what the server expected. Check your client version. An outdated client is the most common cause.
“Rewrite this instruction in STE: Once the upstream job has completed and assuming no errors were raised, the downstream agent should proceed to consume the output artifact.”: Wait for the upstream job to finish with no errors. Then read the output artifact.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/posthog/writing-simplified-technical-english/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip writing-simplified-technical-english.zip -d .agents/skills

Documentation by PostHog

ASD-STE100 is a controlled-language standard. The aerospace and defense industry wrote it so that a technician cannot misread a maintenance instruction. It removes the two biggest sources of misreading: words that carry more than one meaning, and sentences that support more than one structure.

The same discipline fixes the usual failure of agent-written prose. Agent output is often correct and unreadable: long sentences, stacked hedges, passive voice, and a synonym rotation that makes one action look like three. The reader has no author to ask, so ambiguity costs them a re-read at best and a wrong action at worst.

Apply the rules below as you write. Do not write a dense draft and clean it up afterward.

When to use this

Use it for text that a person or another agent must act on:

Reports, findings, and summaries.
PR descriptions, commit messages, and code comments.
Instructions passed to another agent, and prompts.
Tool descriptions, error messages, empty states, and log lines.

Do not use it where voice is the point: marketing copy, blog posts, or anything persuasive. STE is deliberately flat. Also leave quoted text alone. If you quote a user, a log, or a document, quote it as it is.

The rules

Rule	Do	Do not
One meaning per word	Pick one verb per action and reuse it every time	Rotate "check", "verify", and "confirm" for the same action
One part of speech per word	"Apply oil to the valve"	"Oil the valve"
Active voice	"The worker deletes the file."	"The file is deleted."
Simple tenses	"We received the report."	"We have received the report."
One idea per sentence	"Open the file. Read line 3."	"Open the file and read line 3, then check it matches."
Sentence length	20 words or fewer for instructions, 25 or fewer for descriptions	Chains of subordinate clauses
Noun clusters	3 words or fewer ("fuel pump valve")	"high pressure fuel pump inlet valve assembly"
No missing words	Keep the subject, the verb, and the article, even if it reads longer	"Files not backed up will be lost", which hides which files
One hedge, at most	"The client version is probably out of date."	"An error may have occurred which could be caused by..."
Paragraphs	One topic, 6 sentences or fewer	Multi-topic paragraphs
Lists	Use a list for 3 or more steps or conditions	A sequence buried in one sentence
Jargon	Keep the technical term you need, and define it once	Use an internal name the reader has never seen

PostHog house style sits on top of these rules and wins where the two disagree. We use American English, sentence case, and the Oxford comma. We do not use the em-dash.

How to rewrite

Read the text once for meaning. Do not start rewriting before you know what it must still say.
Go sentence by sentence. Name the rule each sentence breaks.
Rewrite the sentence to fix that break. Keep every fact, number, condition, and qualifier.
Check the result against the rules again. A rewrite often introduces a new long sentence.

Precision beats brevity. If a shorter sentence would drop a safety condition, a scope qualifier, or a number, keep the longer sentence and say why.

If the text already follows the rules, say so. Do not change compliant text.

Self-check

Before you send the text, read it once and ask:

Does any sentence run past 25 words?
Does any sentence carry two instructions?
Does the same action appear under two different verbs?
Can a passive sentence name its actor?
Would a reader who joins here, with no context, know what to do next?

References

references/writing-rules.md: the detail behind the table, plus sources.
references/before-after.md: worked examples of the rewrite, including agent output.

Files

ATTRIBUTION.mdAdded by AutoGineer891 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md5.4 KiB
references/before-after.md4.0 KiB
references/writing-rules.md2.9 KiB

references/writing-rules.md

ASD-STE100 writing rules

This file gives the detail behind the rule table in SKILL.md. It paraphrases the rule categories of the standard. It does not reproduce the text of the standard or its dictionary.

What the standard is

ASD-STE100 is a controlled natural language. European airlines asked for it, because most of their maintenance staff read English as a second language. A misread instruction on an aircraft can kill people. The standard first shipped in 1986. ASD (the AeroSpace and Defense Industries Association of Europe) maintains it through the Simplified Technical English Maintenance Group. It has been free to download since 2013. The current edition is Issue 9, from January 2025.

The standard has two parts:

53 writing rules across 9 sections. They cover word choice, grammar, sentence structure, and style.
A dictionary of about 900 approved words. Each word has one meaning and one part of speech. About 1,200 more words are listed as words to avoid, each with a replacement.

An organization may add its own approved technical nouns and verbs on top of the base dictionary. That is how a domain term survives the rules: approve it once, define it once, then use it the same way every time.

Detail behind the rules

Verb forms. Use the infinitive, the imperative, the simple present, the simple past, the simple future, and the past participle as an adjective. Do not use the present perfect, the past perfect, or other compound forms. Use an "-ing" form only inside a technical noun, never as a verb form.

Voice. Use the active voice for procedures and instructions. The passive voice is allowed in descriptive text, and only when the actor is unknown or irrelevant to the reader.

Missing words. Do not drop the verb, the subject, or the article to shorten a sentence. The standard warns that this creates ambiguity rather than clarity. This is the rule that most often surprises a writer who equates short with clear.

Safety instructions. Open a safety-critical instruction with the command or the condition. Do not bury it mid-sentence. The reader must know the risk before they read the detail.

What this skill does not do

It does not reproduce the approved dictionary. When exact approved wording matters, download the standard and check word by word.
It does not certify a document as STE compliant. It is a clarity tool built on the same rules.

Sources

This skill is adapted from danyuchn/asd-ste100-skill, published under the MIT license.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Writing Fragments
Matt Pocock· Community
A collaborative writing tool for capturing raw, unstructured ideas and fragments before formal drafting begins.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Writing Shape
Matt Pocock· Community
A structured, iterative workflow to transform raw notes and transcripts into polished, coherent articles.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Writing Beats
Matt Pocock· Community
A structured, interactive workflow for assembling raw notes into a coherent narrative through a beat-by-beat, choose-your-own-adventure process.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository317.5k
Humanizer
Siqi Chen· Community
Rewrite AI-generated text to remove robotic patterns and restore a natural, human voice.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository65.9k
Copy Editing
Corey Haines· Community
A systematic, seven-sweep framework for refining existing marketing copy to improve clarity, voice, and conversion while removing AI-generated patterns.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository59k
Applying Brand Guidelines
AnthropicOfficial
A comprehensive set of corporate branding standards for consistent visual and textual communication across documents.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository54.4k

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download writing-simplified-technical-english.zip