posthog/ai-plugin

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.

ソースを見る
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

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

RuleDoDo not
One meaning per wordPick one verb per action and reuse it every timeRotate "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 length20 words or fewer for instructions, 25 or fewer for descriptionsChains of subordinate clauses
Noun clusters3 words or fewer ("fuel pump valve")"high pressure fuel pump inlet valve assembly"
No missing wordsKeep 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One hedge, at most"The client version is probably out of date.""An error may have occurred which could be caused by..."
ParagraphsOne topic, 6 sentences or fewerMulti-topic paragraphs
ListsUse a list for 3 or more steps or conditionsA sequence buried in one sentence
JargonKeep the technical term you need, and define it onceUse 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.
同じリポジトリから

関連する Skills

すべての Skills
posthog
公式

assessing-heatmaps

Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements.\nTRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap/click data, or to 'analyze/assess/review the heatmap' for a URL.\nDO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).

導入数
1
GitHub Stars
80
更新日
9月4日
posthog
公式

auditing-endpoints

Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.

導入数
1
GitHub Stars
80
更新日
9月4日
posthog
公式

auditing-experiments-flags

Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.

導入数
1
GitHub Stars
80
更新日
9月4日
posthog
公式

authoring-data-quality-checks

Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Use when asked to test a model, validate a view, check for nulls or duplicates, add data quality checks, find out why a number looks wrong, or judge whether a warehouse table is trustworthy before using it in an analysis. To describe what data means (metrics, certifications, joins), see setting-up-data-catalog instead. Trigger terms: data quality, data test, dbt test, not null check, uniqueness check, freshness check, referential integrity, row count check, validate model, is this table trustworthy.

導入数
1
GitHub Stars
80
更新日
9月4日