ASD-STE100 Skill
A skill that rewrites dense, ambiguous English into ASD-STE100 Simplified Technical English so another agent cannot misread it
- 6,384 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill is instructions and rule references
- The Python linter runs locally and reads only the file passed to it, with no network access
Install
- Works in
Manual install
git clone https://github.com/danyuchn/asd-ste100-skill.git
cp -r asd-ste100-skill ~/.claude/skills/asd-ste100Copy the repository into the skills directory. The folder name must match name in SKILL.md, that is asd-ste100.
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill is instructions and rule references
- The Python linter runs locally and reads only the file passed to it, with no network access
This is third-party code. Review the repository files before installing.
What it does
The skill takes ASD-STE100, the controlled-language standard the aerospace and defense industry built so maintenance instructions cannot be read two ways, and applies it to a different reader: an agent parsing another agent's output, a tool description, an error message or an inter-agent instruction with no human to resolve ambiguity. It picks a mode: strict for procedures, error messages and tool descriptions, STE-flavored for READMEs and explanatory prose. It then reviews the text sentence by sentence, flags rule violations such as passive voice with an unclear actor, complex tenses, several instructions in one sentence and oversized noun clusters, and rewrites the sentences without dropping facts or conditions. On request it shows a before and after table naming each broken rule. A deterministic Python linter ships with it and checks structural patterns like semicolons, phrasal verbs and over-long sentences.
Who it is for. For engineers and technical writers who author tool descriptions, system prompts and error messages that agents or pipelines parse without a human.
Good fit when
- The text will be read by another agent, a translation pipeline or a non-native reader and misreading has a real cost
- A tool description, error message or instruction reads as dense and allows more than one reading
- You need a before and after table showing exactly which rule was broken
Not a fit when
- You need creative or marketing copy where voice and nuance matter: STE is deliberately flat and literal
- You need certified standard-compliant documentation: the skill does not reproduce ASD's official dictionary
Example request
Rewrite this tool description so an agent cannot read it two ways and show which rules were brokenLimitations
The skill does not reproduce ASD's roughly 900-word official dictionary: the standard is free to obtain but not free to redistribute. So the lexical rules are applied as a direction of travel rather than a checkable standard, and the skill says so in its output. The linter checks structural patterns only and does not compare the original with the rewrite or prove that meaning was preserved. Certified standard-compliant documentation needs the real standard with a word-by-word check against the dictionary.
How to disable. Remove the asd-ste100 folder from the agent's skills directory, for example ~/.claude/skills/.
FAQ
How does strict mode differ from STE-flavored?
Strict mode for procedures, error messages, tool descriptions and inter-agent instructions applies every rule, including the hard length caps. STE-flavored mode for READMEs and prose keeps the structural rules but drops the one-word-one-meaning lockdown.
Does it replace the official STE standard?
No. The skill encodes the rule categories and their principle, not the official dictionary. Certified documentation needs the real standard.
Discussion
No questions or reviews yet.
Related
SkillsA skill that rewrites technical text in ASD-STE100 Simplified English: short sentences, active voice, warnings before the step.
A skill that makes an agent write docs and replies in plain English on ASD-STE100 rules: short sentences, one term per meaning, condition before command
Skill that rewrites Chinese technical text into controlled language: one action per sentence, active voice, one term per idea.
Simplified Technical English Skill
simplified-technical-english
A skill that makes a model write in Simplified Technical English (ASD-STE100), a controlled English for technical documentation. Unofficial
A skill that strips defensive caveats, apologies and excess hedging from text and makes claims direct while keeping needed limits
An editing skill that strips stock AI phrasing but keeps the author's vocabulary, rhythm and bluntness, not a flat style.
README in short
The README explains why aerospace Simplified Technical English rules fit agents: a model parsing another agent's output has no back-channel to clarify meaning, just like a mechanic with an instruction. The skill runs in two modes and splits the rules into structural ones it applies with confidence and lexical ones it offers as a direction because ASD's dictionary is not free to redistribute. It ships before and after examples, a rule summary with citations and a Python linter that checks structural patterns and deliberately leaves hedges and modality alone. MIT licensed.
README badge
Original SKILL.md
--- name: asd-ste100 description: "Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified Technical English, plain-language rewrite, controlled-language rewrite, rewrite so an agent cannot misread this. Not for creative or marketing copy." version: 0.4.0 --- # Simplified Technical English (ASD-STE100) ASD-STE100 is a controlled-language standard built by the aerospace and defense industry (ASD, the AeroSpace and Defense Industries Association of Europe) to stop maintenance technicians from misreading English instructions. The standard removes the two biggest sources of misreading: words with more than one meaning, and sentences with more than one possible structure. This skill borrows that same discipline for a different reader: an **AI agent or a downstream system** that has to parse an English string — an error message, a tool description, an inter-agent instruction, a status report — without a human in the loop to resolve ambiguity. ## When to Use This Skill - 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.