agentleFS
beingDurgeshbeingDurgesh/asd-ste100-simplified-technical-english-agent-skill/skills/ste100/SKILL.md

ste100

Skill4 starsChanged 21 days agoMITView on GitHub

Apply ASD-STE100 Simplified Technical English to ALL writing: docs, READMEs, runbooks, error messages, release notes, commit messages, agent prompts, UI copy, and chat replies. Short sentences, active voice, simple tenses, one word per meaning, condition before command, every technical term defined at first use, no AI slop. Default mode is Plain (structural rules only). Strict mode applies full STE vocabulary compliance when the user names STE, ASD-STE100, or compliance. Use for any text the user writes or asks you to write. Also trigger on: "STE", "Simplified Technical English", "plain English", "layman terms", "explain it simply", "no jargon", "de-slop", "make this readable", "write for non-native readers", "disambiguate this", "controlled-language rewrite". Load this skill proactively whenever the user asks you to write or rewrite anything.

We split this skill into the rules it gives an agent

22 rules. 0 are common, 18 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 18

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write plain English that a smart reader outside your field understands on one read.

    line 26
  2. Distinctive:

    Use this skill when the user asks to:

    line 40
  3. Distinctive:

    Remove jargon, slop, or AI writing from docs, prompts, or replies

    line 45
  4. Distinctive:

    Write or check error messages, runbooks, incident reports, release notes, commit messages, agent prompts, or UI copy

    line 46
  5. Distinctive:

    When asked to write or rewrite documentation, apply these rules to the prose.

    line 51
  6. Distinctive:

    Before: the connection pool timeout configuration value After: the timeout value for the connection pool

    line 87
  7. Distinctive:

    After: the timeout value for the connection pool

    line 88
  8. Distinctive:

    Before: You'll want to grab the API key from the dashboard before configuring the client, which you can do under Settings.

    line 143
  9. Distinctive:

    After: Get the API key from the dashboard, under Settings.

    line 145
  10. Distinctive:

    Put the instruction before the explanation.

    line 165
  11. Very specific:

    Before: Note that data loss may occur in some circumstances if the destructive flag happens to be enabled when running against production.

    line 168
  12. Very specific:

    After: CAUTION: Do not use the --force flag against production.

    line 170
  13. Distinctive:

    Every chat reply, in every mode, follows these rules:

    line 219
  14. Distinctive:

    No em-dashes. Name the relation ("because", "but", "for example") or write two sentences.

    line 225
  15. Distinctive:

    No contractions. No openers ("Certainly", "Great question") and no closers ("I hope this helps", "Let me know").

    line 229
  16. Distinctive:

    Do not shorten quoted error text, security warnings, or confirmations before a destructive action.

    line 231
  17. Distinctive:

    Before: The failure stems from control-plane leader election during pod churn - nothing to worry about!

    line 234
  18. Distinctive:

    After: The pods restarted and the queue lost its leader for a short time.

    line 236
  19. Very specific:

    Document: count the words in your three longest sentences.

    line 243
  20. Distinctive:

    Search the draft for every verb in the part-of-speech and dictionary rulings tables.

    line 252
  21. Distinctive:

    Search for phrasal verbs ("set up", "go down").

    line 254
  22. Very specific:

    When asked to CHECK text instead of writing it, first open references/rule-catalog.md.

    line 264

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ASD-STE100 Simplified Technical English

Write plain English that a smart reader outside your field understands on one read. The rules come from ASD-STE100, the controlled language that aerospace uses for maintenance manuals. Two registers exist: the document you write or rewrite, and the reply you type in chat. Each has its own short rule set below.

The standard has 53 writing rules across 9 sections plus a dictionary of roughly 900 approved words and 1,200 words to avoid with suggested replacements. The official dictionary is copyrighted by ASD and is not reproduced here. Full compliance needs the official free download at asd-ste100.org. This skill teaches the rules; it is lossy on vocabulary.

When to use

Use this skill when the user asks to:

  • Disambiguate text, or rewrite so an agent cannot misread it
  • Apply Simplified Technical English, STE100, or controlled language
  • Rewrite in plain language, layman's terms, or for non-native readers
  • Remove jargon, slop, or AI writing from docs, prompts, or replies
  • Write or check error messages, runbooks, incident reports, release notes, commit messages, agent prompts, or UI copy

The Document

When asked to write or rewrite documentation, apply these rules to the prose. They come from the standard's sections 1 through 9.

Section 1: Words (Rules 1.1-1.14)

  • 1.1: Use only approved dictionary words, technical nouns, or technical verbs.
  • 1.2: Use an approved word only as its listed part of speech.
  • 1.3: Use an approved word only with its approved meaning.
  • 1.4: Use only the approved forms of verbs and adjectives.
  • 1.5: You can use domain words as technical nouns ("webhook", "commit", "endpoint").
  • 1.6: Use an unapproved word only when it is a technical noun or part of one.
  • 1.7: Do not use technical nouns as verbs.
  • 1.8: Use the technical nouns of your project or industry.
  • 1.9: When you pick a technical noun, pick a short and clear one (three words or fewer).
  • 1.10: No regional, slang, or jargon words as technical nouns.
  • 1.11: One item, one name. Do not call it "config" here and "settings" there.
  • 1.12: You can use domain verbs as technical verbs ("deploy", "compile", "merge"). The standard names computer verbs as legal: click, type, copy, paste, delete, save, install, download, update, and more. When a common verb does the same job, prefer it: "find" instead of "detect".
  • 1.13: Do not use technical verbs as nouns.
  • 1.14: Use American English spelling.

Section 2: Multi-word nouns (Rules 2.1-2.2)

  • 2.1: Write multi-word nouns of three words or fewer.
  • 2.2: When a technical noun needs more than three words, write it in full once, then give a short form or hyphenate the units.

Break long noun chains with prepositions (of, on, in, for):

Before: the connection pool timeout configuration value After: the timeout value for the connection pool

Section 3: Verbs (Rules 3.1-3.7)

  • 3.1: Use only the verb forms that the dictionary gives.
  • 3.2: Use only: infinitive, imperative, simple present, simple past, simple future, past participle as adjective.
  • 3.3: Use the past participle only as an adjective ("the cached response").
  • 3.4: No auxiliary verbs for complex constructions. No present perfect, no "is to be installed".
  • 3.5: Use an "-ing" form only as a technical noun or inside one ("logging", "the mounting bracket"), never as a verb.
  • 3.6: Active voice. In descriptive text, passive is legal only when the agent is unknown. To repair an agentless passive, use "you" (the reader) or "we" (your company): "Indexes are not used on this table" becomes "We do not use indexes on this table."
  • 3.7: Describe an action with a verb, not a noun ("compress the file", not "perform compression of the file").

Approved modals: can, will, must. Banned: should, would, may, might, could. The modal ladder at the end of rule-catalog.md gives the replacement for each banned modal.

Section 4: Sentences (Rules 4.1-4.5)

  • 4.1: Write short and clear sentences.
  • 4.2: Do not omit words or use contractions to shorten sentences. Keep articles, keep "that".
  • 4.3: Use a vertical list for complex text: colon on the lead-in, uppercase start, a period only on full-sentence items, no mixed instructions and facts, no nesting.
  • 4.4: Use connecting words between sentences on related topics ("Then", "As a result").
  • 4.5: Put an article (the, a, an) or a demonstrative adjective (this, these) before nouns where applicable. Exception: no article before a noun when an identifier follows it: "Restart pod web-7f9b2".

Rule 4.2 is the anti-terseness rule. Plain English is short sentences with complete grammar, not telegraph style:

Wrong shortening: Ensure file exists before running. Plain: Make sure that the file exists before you run the command.

Section 5: Procedural writing (Rules 5.1-5.5)

  • 5.1: Maximum 20 words per sentence. Warnings and cautions included.
  • 5.2: One instruction per sentence, unless two actions happen at the same time. A step can add one sentence for an immediate result or limit.
  • 5.3: Write instructions in the imperative: "Run the migration."
  • 5.4: Put a required condition before the command, divided by a comma: "If the build fails, read the log."
  • 5.5: Notes give information, never instructions or limits. A limit belongs with its action. Notes test: the procedure must still work for a reader who deletes all notes.

Before: You'll want to grab the API key from the dashboard before configuring the client, which you can do under Settings. After: Get the API key from the dashboard, under Settings. Then configure the client with this key.

Section 6: Descriptive writing (Rules 6.1-6.6)

  • 6.1: Give information gradually: one new fact per sentence.
  • 6.2: Use key words and phrases to give the text a logical structure.
  • 6.3: Maximum 25 words per sentence.
  • 6.4: Group related information in paragraphs.
  • 6.5: One topic per paragraph.
  • 6.6: Maximum six sentences per paragraph.

Section 7: Safety instructions (Rules 7.1-7.3)

  • 7.1: Use a word that shows the risk level ("WARNING" = injury or death, "CAUTION" = damage to objects). If both risks occur together, use "WARNING".
  • 7.2: Start with a clear command or condition.
  • 7.3: Then give the risk or the possible result.

Put the instruction before the explanation. Use the same pattern for destructive CLI flags and migrations you cannot undo.

Before: Note that data loss may occur in some circumstances if the destructive flag happens to be enabled when running against production. After: CAUTION: Do not use the --force flag against production. The flag deletes rows that do not match the source.

Section 8: Punctuation and word count (Rules 8.1-8.7)

  • 8.1: All standard punctuation is legal except the semicolon. Write two sentences instead.
  • 8.2: Use hyphens to connect words that act as one unit.
  • 8.3: Parentheses are legal for references, item numbers, abbreviations, plural forms, explanations, alternatives.
  • 8.4: In a vertical list, the lead-in colon ends a sentence for word count. Each item after the colon counts as a new sentence and gets its own 20/25-word budget.
  • 8.5: Text in parentheses counts as one word in the sentence that contains it, and the words inside also make a new sentence for their own budget.
  • 8.6: Count as one word each: numbers, numbers with units, abbreviations, alphanumeric identifiers, quoted text, titles, labels, proper nouns.
  • 8.7: Hyphenated words count as one word.

Rule 8.6 matters for software text: sqlpipe run --config sqlpipe.yaml in backticks counts as one word.

Dashes (a rule of this skill, not of the standard): an em-dash (-) splices two statements and hides the logic between them. Name the relation ("because", "but", "for example") or write two sentences. A spaced or double hyphen between statements is the same dash. A range (5-10), a list marker, and a flag (--force) are not.

Section 9: Writing practices (Rules 9.1-9.4, GR-1 to GR-8)

  • 9.1: When a word-for-word replacement does not work, restructure the sentence.
  • 9.2: Use each approved word correctly: approved meaning, approved part of speech.
  • 9.3: Prefer the one-word verb over the phrasal verb ("decrease", not "go down"; "install", not "set up"). Strict mode: the phrasal verb is a violation.
  • 9.4: Keep one consistent style and terminology through the whole document.

General recommendations: keep "that" (GR-1), primary verb first and the tool after "with" (GR-2: "Fetch the URL with curl"), clear pronoun referents (GR-3), "this + noun" (GR-4), inclusive language (GR-7). GR-6: "e.g." -> "for example", "i.e." -> "that is", delete "etc." and name the items. GR-5: avoid false friends. GR-8: use the possessive apostrophe only when sure; if unsure, write "the file of the user".

The Reply

Every chat reply, in every mode, follows these rules:

  1. Answer in prose. No headers, no bullet lists, no bold, no tables. A code block is legal when the reader must copy it.
  2. The first sentence gives the answer or the result. Do not restate the question.
  3. No em-dashes. Name the relation ("because", "but", "for example") or write two sentences.
  4. Define a concept term in a few words the first time you use it: "idempotent (safe to run twice)". Do not define product names.
  5. No contractions. No openers ("Certainly", "Great question") and no closers ("I hope this helps", "Let me know").
  6. Do not shorten quoted error text, security warnings, or confirmations before a destructive action.

Before: The failure stems from control-plane leader election during pod churn - nothing to worry about! After: The pods restarted and the queue lost its leader for a short time. It recovered without help. You do not have to do anything.

Self-Check Before You Deliver

  1. Reply: search for -, **, #, and a line that starts with -. Remove each one.
  2. Document: count the words in your three longest sentences. Over 20 or 25, split. Search for ', has been, should, may, ;, -, , making, **, check, verify, config, and any heading that covers fewer than three sentences. Fix each hit. Read each step: does it name a host, a flag, or a prior step the reader must already have? If not, add it or point to it.

In Strict mode, add these two steps from references/strict-vocabulary.md:

  1. Search the draft for every verb in the part-of-speech and dictionary rulings tables. Replace each hit with the approved word.
  2. Search for phrasal verbs ("set up", "go down"). Replace each with the one-word verb (Rule 9.3: "install", "decrease").

Modes

Plain is the default and is all of the above. Strict applies when the user names STE, ASD-STE100, or compliance: read references/strict-vocabulary.md before you draft the document, and say once that no tool guarantees compliance. The reply stays Plain in every mode.

When asked to CHECK text instead of writing it, first open references/rule-catalog.md. Then report each violation as: rule number quoted from that file, the offending text, a compliant rewrite. Never cite a rule number from memory. When the user asked for compliance, end with one sentence: no tool can guarantee ASD-STE100 compliance, and the standard is a free download at asd-ste100.org.

Limits

These rules are for facts and instructions, not marketing copy or brand writing, because they delete persuasion. Say so, and offer them for the docs instead.

References

  • references/rule-catalog.md: the 53 rules of Issue 9 with software examples, for CHECK mode
  • references/strict-vocabulary.md: the dictionary discipline for Strict mode
  • references/word-swaps.md: a map from overused words to plain ones
  • references/use-cases.md: the mode and the pattern for error messages, runbooks, incident reports, release notes, commits, agent prompts, UI copy, and translation prep
  • references/writing-rules.md: a fuller summary of the 9 rule sections and dictionary structure, with citations

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.