Review and rewrite agent output using ASD-STE100 Simplified Technical English

• An agent's output (explanation, instruction, log message, tool description) reads as dense, jargon-heavy, or ambiguous.
• Text will be consumed by another agent, a translation pipeline, or a non-native English reader, and misparsing has a real cost.
• You are writing a prompt, system message, or tool description and want to remove ambiguity before a model ever sees it.
• You want a before/after comparison showing exactly which rule was violated and how the rewrite fixes it.

This skill is not for creative or marketing copy — STE is deliberately flat and literal. Do not apply it to text where voice, nuance, or persuasion is the point.

ORE Studio requires this style in all user-facing agent prose. The rules apply to every explanation and instruction an agent writes — not only to text it rewrites on request. Write compliant text first. Do not write dense text and then rewrite it.

Do not apply the rules to structured output. JSON, diffs, code, commit messages, and command output keep their own conventions.

1. Read the input text once for meaning — do not start rewriting before you understand what it must still say afterward.
2. Walk it sentence by sentence and flag every rule violation (word ambiguity, tense, voice, length, ellipsis, noun stacking).
3. Rewrite each flagged sentence to fix the violation while preserving the original meaning exactly. If a rewrite would drop necessary precision (a safety condition, a scope qualifier, a number), keep the longer phrasing and flag it instead of silently simplifying.
4. Produce a before/after table (see examples) with columns: rule violated, original, simplified. Add a one-line note for anything deliberately left unsimplified.
5. If the input already complies, say so — do not force changes onto compliant text.

Apply the 11 core STE100 rules from the writing rules reference — one meaning per word, one part of speech, active voice, simple tenses, one instruction per sentence, ≤20-25 word sentences, ≤3-word noun clusters, no ellipsis, one topic per paragraph, lists for sequences, and defined domain terms.

Boundaries

• Will: rewrite ambiguous or dense English into short, single-meaning, active-voice sentences; flag exactly which rule a sentence violates before rewriting it; preserve every fact, condition, and scope qualifier in the original; suggest a one-line glossary entry for domain terms that must stay.
• Will not: reproduce ASD's official ~900-word dictionary as if it were memorised verbatim; simplify creative, marketing, or persuasive copy where voice and nuance are the point; silently drop a safety condition, exception, or scope qualifier to shorten a sentence; guarantee an aerospace/defense-grade STE-compliant document — this is a general-purpose clarity tool inspired by STE, not a certified STE authoring tool.

• How do I create a new doc? — for when the skill needs to refer to project conventions while rewriting.

• Writing rules — fuller summary of the 9 STE100 rule sections and dictionary structure, with citations.
• Before/after examples — worked examples of official STE rules and agent-output rewrites built for this skill.
• ASD-STE100 official site — download the full standard (Issue 9, Jan 2025) for word-by-word dictionary checks.
• Upstream repo — original skill by Dustin Yuchen Teng (MIT license), adapted for ORE Studio.