agentleFS
parthjshah95parthjshah95/visual-planning-skills/skills/asd-ste100/SKILL.md

asd-ste100

Skill14 starsChanged 2 months agoMITView on GitHub

Write in ASD-STE100 Simplified Technical English — one meaning per word, active voice, simple tenses, short sentences, small noun clusters. The visual-explainer and visual-plan skills require it for every human-readable string they produce. Also use it whenever the user asks for Simplified Technical English, or for plain, unambiguous prose.

32 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handoff, tdd and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 5 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write English in ASD-STE100 Simplified Technical English.

    line 8
  2. Distinctive:

    Do not write a marketing phrase, a tagline, or an abstract slogan.

    line 50
  3. Very specific:

    If the project has no CONTEXT.md, do not invent one.

    line 62
  4. Distinctive:

    Never drop a fact, a condition, a caveat, or a scope qualifier to meet a limit.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 31 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 English in ASD-STE100 Simplified Technical English. STE is a controlled language. The aerospace industry built it so a reader who cannot ask a follow-up question still reads the text one way only. The rules are countable. Check your prose against them as you write.

When to use

  • A skill requires it. The visual-explainer and visual-plan skills require it for every human-readable string in their output.
  • The user asks for Simplified Technical English, or for plain, unambiguous prose.

Precedence

These rules set the default shape of the English you write. A more specific instruction takes precedence on whatever it addresses. This includes an instruction from the user, from project instructions, from an invoked skill, or from an established convention in the file you edit. Where the more specific instruction is silent, these rules apply.

Follow the more specific instruction without comment. Do not cite this style as a reason to override it. Do not ask permission. This exception applies to an explicit instruction only. Do not relax these rules because a topic feels casual or because other prose seems friendlier.

Never apply these rules to

  • Code. This includes identifiers, syntax, and string literals.
  • Quoted material. This includes error output, command output, file contents, and another person's words. To rewrite a quotation is falsification, not simplification.
  • Text where the exact wording carries the meaning. This includes a command to run, an API name, a config key, and an exact error string.

Rules

RuleLimit
Noun clustersMaximum 3 words stacked as a modifier. Break a longer stack apart and name the relationship.
Sentence lengthMaximum 20 words for an instruction or a procedure. Maximum 25 words for descriptive text.
One instruction per sentenceDo not join two instructions with "and" or "then".
Active voiceUse the passive voice in descriptive text only, and only when the actor is unknown or irrelevant.
Simple tenses onlyUse the infinitive, the imperative, the simple present, the simple past, and the simple future. Use a past participle as an adjective only. Do not use the present perfect, the past perfect, or a compound auxiliary.
No -ing verb formsUse an -ing word as a technical noun, or as part of one, only.
No hedge stackingDo not chain modal verbs, as in "may have been caused by". State the uncertainty as its own plain sentence: "The cause is not confirmed."
One word, one meaningUse one term for one concept and repeat it. Do not rotate synonyms for the same idea.
Plainest available wordPrefer the short common word to the formal or rare word.
Define domain termsDefine a term that is not common English at its first use. Do not carry undefined shorthand forward.
No ellipsisKeep the subject, the verb, and the article explicit, even when the sentence reads longer.
ParagraphsOne topic. Maximum 6 sentences.
Vertical listsUse a numbered or bulleted list for 3 or more steps or conditions.

Headings and titles

A heading names its subject. It is not a slogan. A reader who sees only the heading must understand what the section is about.

  • Name the real workflow, system, page, endpoint, or step.
  • Do not write a marketing phrase, a tagline, or an abstract slogan.
  • Bad (slogan): "From customer task to phone conversation".
  • Good (plain): "How the phone-call workflow works".

This rule applies to every title, scene heading, and section heading.

Project vocabulary

STE permits a project to define its own approved vocabulary of technical nouns and verbs. A CONTEXT.md file at a repository root is that vocabulary.

If the project has a CONTEXT.md, use its terms exactly as it defines them, in the part of speech it defines. Never substitute a synonym for a term it defines. Never use a word that its _Avoid_ lines reject. Do not redefine its terms inline, because the glossary is the definition.

If the project has no CONTEXT.md, do not invent one. Do not present any term as already established. The rules above apply without change: define a term at first use, prefer the plainest word, and use one term for one concept.

Length is not terseness

The caps apply to each sentence, not to the response. Clarity is the goal, not concision. A long answer in short sentences is correct.

Never drop a fact, a condition, a caveat, or a scope qualifier to meet a limit. Split the sentence instead.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.