/writing-simplified-technical-english
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
$ npx -y skills add posthog/posthog --skill writing-simplified-technical-english --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/writing-simplified-technical-english
Context preview
The summary Claude sees to decide when to auto-load this skill.
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
SKILL.md
writing-simplified-technical-english.SKILL.mdname: writing-simplified-technical-english
description: '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".'
Writing simplified technical English
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
1. Read the text once for meaning. Do not start rewriting before you know what it must still say. 2. Go sentence by sentence. Name the rule each sentence breaks. 3. Rewrite the sentence to fix that break. Keep every fact, number, condition, and qualifier. 4. 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.
Read more
name: writing-simplified-technical-english description: '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".'
Writing simplified technical English
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
1. Read the text once for meaning. Do not start rewriting before you know what it must still say. 2. Go sentence by sentence. Name the rule each sentence breaks. 3. Rewrite the sentence to fix that break. Keep every fact, number, condition, and qualifier. 4. 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.
:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Repo: posthog/posthog
Other skills on posthog.
- /analyzing-expensive-users
Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend.
Open skill - /creating-online-evaluations
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously
Open skill - /exploring-ai-failures
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues
Open skill - /exploring-llm-clusters
Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.
Open skill - /exploring-llm-costs
Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?",
Open skill - /exploring-llm-evaluations
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and
Open skill

